Papers by Li Huang
Rule-Guided Extraction: A Hierarchical Rule Optimization Framework for Document-Level Event Argument Extraction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Document-level event argument extraction (EAE) is a critical task in natural language processing. |
| Approach: | They propose an LLM-driven HiErarchical Rule Optimization framework that iteratively generates and selects optimal hierarchical rules. |
| Outcome: | The proposed framework outperforms few-shot supervised methods and outperformed state-of-the-art prompting baselines. |
MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)
Copied to clipboard
Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored. |
| Approach: | They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios. |
| Outcome: | The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC. |
What’s Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing benchmarks often include a mixture of reasoning questions, making it difficult to truly assess VLMs’ causal reasoning abilities. |
| Approach: | They propose two new benchmarks specifically designed to isolate and rigorously evaluate VLMs’ causal reasoning abilities. |
| Outcome: | The proposed benchmarks show that vision-language models perform poorly on causal reasoning tasks, often only marginally surpassing random guessing. |
Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process. |
| Approach: | They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations. |
| Outcome: | The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction. |
CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds (2025.naacl-long)
Copied to clipboard
| Challenge: | Evaluating role-playing capabilities in large language models is challenging due to complex dynamics involved in role-playering. |
| Approach: | They propose a simulation sandbox that generates situational fine-grained character behavior trajectories to enhance LLM performance. |
| Outcome: | The proposed model generates situational fine-grained character behavior trajectories to enhance performance. |
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency (2022.acl-long)
Copied to clipboard
| Challenge: | Structured pruning has been extensively studied on monolingual pre-trained models . but little attention has been paid to evaluating the effectiveness of structured pruning on multilingual models. |
| Approach: | They investigate settings, algorithms, and efficiency of structured pruning on multilingual models . authors propose a simple approach that allows training the model once and adapting to different model sizes at inference . |
| Outcome: | The proposed approach allows training the model once and adapting to different model sizes at inference. |
Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for code retrieval struggle to balance scalability and annotation quality. |
| Approach: | They propose a method that integrates functions called within the repository and information on third-party APIs to enhance the annotation context. |
| Outcome: | The proposed method improves the annotation context by incorporating functions called within the repository and information on third-party API functionalities. |
OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality Interaction (2025.acl-long)
Copied to clipboard
Haonan Zhang, Run Luo, Xiong Liu, Yuchuan Wu, Ting-En Lin, Pengpeng Zeng, Qiang Qu, Feiteng Fang, Min Yang, Lianli Gao, Jingkuan Song, Fei Huang, Yongbin Li
| Challenge: | Existing methods focus on replicating dialogues in textual form, neglecting the role’s voice traits as a crucial effect in interaction, which tends to be more immersive experiences in realistic scenarios. |
| Approach: | They propose a first seamless speech-language personality interaction model to achieve immersive RPAs with low latency. |
| Outcome: | The proposed model exhibits role-specific personality traits and vocal traits throughout the interaction, enabling a mixture of speech and language responses. |
Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting (2026.acl-long)
Copied to clipboard
| Challenge: | Temporal knowledge graphs (TKGs) require predicting future facts by modeling structural dependencies within each snapshot and temporal evolution across snapshots. |
| Approach: | They propose an encoder-agnostic framework that provides persistent entity states . EST maintains a global state buffer and aligns structural evidence with sequential signals . |
| Outcome: | Experiments show that EST improves diverse backbones and achieves state-of-the-art performance. |
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)
Copied to clipboard
Changhao Jiang, Jiahao Chen, Zhenghao Xiang, Zhixiong Yang, Hanchen Wang, Jiabao Zhuang, Xinmeng Che, Jiajun Sun, Hui Li, Yifei Cao, Shihan Dou, Ming Zhang, Junjie Ye, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data. |
| Approach: | They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse. |
| Outcome: | The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures. |
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. |
| Approach: | They propose to apply world knowledge to enhance OOD detection performance through selective generation from large language models (LLMs) they propose to extract visual objects from each image to fully capitalize on the aforementioned world knowledge. |
| Outcome: | The proposed method outperforms the state-of-the-art on visual OOD detection on in-distribution (ID) samples. |
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | emergence of tool agent paradigm has broadened capability boundaries of the Large Language Model (LLM) but effectiveness of tool agents limited due to parameter failure during execution . |
| Approach: | They propose a parameter failure taxonomy to investigate parameter failure . they propose suggestions for standardizing tool return formats and improving error feedback mechanisms . |
| Outcome: | The proposed model is based on a tool agent invocation chain and a mainstream tool agent . it shows that parameter name hallucination failure stems from inherent limitations . |
SiLP: Enhancing Non-Dominant Language Capabilities with a Selective Bidirectional Language Projection Framework (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve performance of large language models rely on additional training objectives or language-specific parameters. |
| Approach: | They propose a bidirectional language projection framework that enables efficient multilingual alignment and language shift using the intrinsic parameters. |
| Outcome: | The proposed framework improves performance of non-dominant languages and improves internal representations. |
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models (2025.acl-long)
Copied to clipboard
Shilong Pan, Zhiliang Tian, Zhen Huang, Wanlong Yu, Zhihua Wen, Xinwang Liu, Kai Lu, Minlie Huang, Dongsheng Li
| Challenge: | Existing defenses, including post-training alignment and prompt engineering, struggle with adaptability to out-of-distribution (OOD) attacks. |
| Approach: | They propose an adversarial game-based defense method that dynamically adjusts LLMs’ internal representations to achieve a balanced trade-off between helpfulness and harmlessness. |
| Outcome: | The proposed method improves LLMs’ safety over all baselines. |
Agentic Economic Modeling (2026.acl-industry)
Copied to clipboard
| Challenge: | AEM is a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. |
| Approach: | They introduce a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. |
| Outcome: | The proposed framework improves RCT efficiency and establishes a foundation method for LLM-based counterfactual generation. |
SumSurvey: An Abstractive Dataset of Scientific Survey Papers for Long Document Summarization (2024.findings-acl)
Copied to clipboard
| Challenge: | a growing need for long document summarization datasets with 16k input is causing problems. |
| Approach: | They propose to use a dataset to analyze salient information in long document summarizations. |
| Outcome: | The proposed dataset outperforms existing models and LLMs in the distribution form of salient information and the distribution of salinal information is an indicator of quality. |
Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2026.acl-long)
Copied to clipboard
Zhong-Zhi Li, Xiao Liang, Zihao Tang, Lei Ji, Peijie Wang, Haotian Xu, Xing W, Haizhen Huang, Weiwei Deng, Yeyun Gong, Zhijiang Guo, Xiao Liu, Fei Yin, Cheng-Lin Liu
| Challenge: | Large Language Models (LLMs) have recently achieved remarkable progress on complex reasoning tasks by leveraging extended Chain-of-Thought (CoT) techniques. |
| Approach: | They propose a method that uses Extended Chain-of-Thought (EFT) to reduce the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning. |
| Outcome: | The proposed method reduces the number of output tokens by nearly 40% while maintaining the accuracy of the reasoning. |
An In-depth Study on Internal Structure of Chinese Words (2021.acl-long)
Copied to clipboard
Chen Gong, Saihao Huang, Houquan Zhou, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan
| Challenge: | Unlike English letters, Chinese characters have rich and specific meanings. |
| Approach: | They propose to model Chinese words' internal structures as dependency trees with 11 labels for distinguishing syntactic relationships. |
| Outcome: | The proposed model of Chinese word-internal structures shows it can be used to parse sentences . it shows that the model can be applied to a sentence-level task with a competitive dependency parser. |
Model Composition for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
| Challenge: | Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities. |
| Approach: | They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters. |
| Outcome: | The proposed model retains the modal understanding capabilities of each original model. |
Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages (2024.acl-long)
Copied to clipboard
Shih-Cheng Huang, Pin-Zu Li, Yu-chi Hsu, Kuang-Ming Chen, Yu Tung Lin, Shih-Kai Hsiao, Richard Tsai, Hung-yi Lee
| Challenge: | Despite the rapid development of large language models, the language capabilities of most open-source LLMs are primarily focused on English due to data constraints. |
| Approach: | They propose a chat vector to equip pre-trained language models with instruction following and human value alignment via simple model arithmetic. |
| Outcome: | The proposed method can be extended to include various languages, base models, and chat vectors. |
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)
Copied to clipboard
Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang
| Challenge: | Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target. |
| Approach: | They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success. |
| Outcome: | The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design. |
Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are hampered by hallucinations, a particularly challenging variant, knowledge overshadowing, which can lead to erroneous outputs even with high-quality training data. |
| Approach: | They propose a framework to analyze and detect knowledge overshadowing by using knowledge circuit analysis to dissect the function of key components in the circuit and how attention pattern dynamics contribute to the phenomenon. |
| Outcome: | Extensive experiments show that the framework can detect and analyze knowledge overshadowing and improves on existing models. |
FC-KBQA: A Fine-to-Coarse Composition Framework for Knowledge Base Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for question answering over knowledge bases (KBQA) suffer from generalization issues due to coarse-grained modeling of the logical expression. |
| Approach: | They propose a fine-to- coarse-grained framework for KBQA to ensure generalization and executability of the logical expression. |
| Outcome: | The proposed framework derives new state-of-the-art performance on GrailQA and WebQSP, and runs 4 times faster than baseline. |
UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model (2025.findings-naacl)
Copied to clipboard
Zhaowei Li, Wei Wang, YiQing Cai, Qi Xu, Pengyu Wang, Dong Zhang, Hang Song, Botian Jiang, Zhida Huang, Tao Wang
| Challenge: | Representative models like LLaVA and MiniGPT-4 have great capabilities in various tasks. |
| Approach: | They propose a unified model to represent various multi-modal tasks using a single representation. |
| Outcome: | The proposed model outperforms existing models in a variety of tasks while maintaining generality and scalability. |
Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)
Copied to clipboard
Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie
| Challenge: | Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency. |
| Approach: | They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%. |
| Outcome: | The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks. |
DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection (2026.acl-long)
Copied to clipboard
Tianle Liu, Zhiliang Tian, Zhen Huang, Tianlun Liu, Jingyuan Huang, Zhaoning Zhang, Chengcheng Shao, Dongsheng Li
| Challenge: | Existing methods for LGT detection assume that it is a single homogeneous distribution. |
| Approach: | They propose a framework for LGT detection based on density-aware manifold learning and hybrid Mahalanobis energy. |
| Outcome: | The proposed framework outperforms baselines in detecting LLM-generated text (LGT) it is based on density-aware manifold learning and hybrid Mahalanobis energy . |
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
Word Matters: What Influences Domain Adaptation in Summarization? (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generalize domain datasets unseen during training but are not able to predict domain adaptation performance. |
| Approach: | They propose to quantify dataset learning difficulty as the learning difficulty of generative summarization, which is determined by word-based compression rate and abstraction level. |
| Outcome: | The proposed model can predict performance on unknown domain datasets without training, and it is based on the findings. |
CULG: Commercial Universal Language Generation (2022.naacl-industry)
Copied to clipboard
| Challenge: | Pre-trained language models have improved performance for many NLP tasks in finance and healthcare. |
| Approach: | They propose a large-scale commercial universal language generation model which is pre-trained on a corpus drawn from 10 markets across 7 languages. |
| Outcome: | The proposed model outperforms other models on commercial generation tasks and on other markets, languages, and tasks. |
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition (2024.acl-long)
Copied to clipboard
| Challenge: | Experiments show that ChunkAttention can speed up the self-attention kernel by 3.2-4.8 compared to the start-of-the-art implementation. |
| Approach: | They propose a prefix-aware self-attention module that can detect matching prompt prefixes across multiple requests and share their key/value tensors in memory at runtime. |
| Outcome: | The proposed module can speed up the self-attention kernel by 3.2-4.8 compared to the start-of-the-art implementation, with the length of the system prompt ranging from 1024 to 4096. |
Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format (2026.findings-acl)
Copied to clipboard
Dingzirui Wang, Xuanliang Zhang, Rongyu Cao, Longxu Dou, Xianzhen Luo, Yingwei MA, Qingfu Zhu, Binhua Li, Fei Huang, Yongbin Li
| Challenge: | Prior work showed that multiple reasoning formats outperform a single format when generating multiple answers. |
| Approach: | They propose a method to measure reasoning error when generating multiple answers . they propose 'formatadapter' which generates and selects suitable reasoning formats . |
| Outcome: | The proposed method achieves a 4.3% performance improvement over previous works on math and commonsense reasoning tasks. |
Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters (2024.acl-long)
Copied to clipboard
Yinghui Li, Zishan Xu, Shaoshen Chen, Haojing Huang, Yangning Li, Shirong Ma, Yong Jiang, Zhongli Li, Qingyu Zhou, Hai-Tao Zheng, Ying Shen
| Challenge: | Existing studies focus on misspelled characters, ignoring faked characters which are more common and difficult to correct. |
| Approach: | They propose to use Chinese character checking to identify and correct wrong characters in texts by human annotation. |
| Outcome: | The proposed dataset is the first real-world visual and the largest human-crafted dataset for the Chinese character checking scenario. |
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection (2025.naacl-long)
Copied to clipboard
| Challenge: | Toolcalling has changed Large Language Model (LLM) applications by integrating external tools, but it also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied. |
| Approach: | They propose a framework that exploits vulnerabilities in Large Language Models through adversarial tool injection to execute privacy theft, launch denial-of-service attacks, and manipulate business competition. |
| Outcome: | The proposed framework exploits vulnerabilities in LLM tool-calling systems through adversarial tool injection. |
Unified Semantic Typing with Meaningful Label Inference (2022.naacl-main)
Copied to clipboard
| Challenge: | Semantic typing aims at classifying tokens into semantic categories such as relations, entity types, and event types. |
| Approach: | They propose a unified framework for semantic typing that captures label semantics by projecting both inputs and labels into a joint semantic embedding space. |
| Outcome: | The proposed framework achieves strong performance across three semantic typing tasks. |
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) rely on safety alignment to avoid malicious user inputs. |
| Approach: | They employ weak classifiers to explain LLM safety through the intermediate hidden states. |
| Outcome: | The proposed model can identify malicious and normal inputs and detect malicious ones without jailbreak. |
EmbodiedBERT: Cognitively Informed Metaphor Detection Incorporating Sensorimotor Information (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for metaphor detection rely on heuristics such as Metaphor Identification Procedure (MIP) and Selection Preference Violation (SPV). |
| Approach: | They propose a cognitively motivated module that leverages the cognitive information of embodiment that can be derived from word embeddings and explicitly models the process of sensorimotor change that has been demonstrated as essential for metaphor processing. |
| Outcome: | The proposed module can improve metaphor detection compared with the heuristic MIP that has been applied previously. |
Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog (2023.acl-industry)
Copied to clipboard
Kewei Cheng, Xian Li, Zhengyang Wang, Chenwei Zhang, Binxuan Huang, Yifan Ethan Xu, Xin Luna Dong, Yizhou Sun
| Challenge: | Existing methods for analyzing textual attributes in product catalogs are not effective on structured tabular data since they are trained on free-form natural language texts. |
| Approach: | They propose a model to handle error detection over tabular data following a pre-training paradigm. |
| Outcome: | The proposed model improves on a real-world Amazon Product Catalog table by 16% over state-of-the-art methods and by 11% on PR AUC over attribute value validation task. |
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities (2022.acl-long)
Copied to clipboard
Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-wen Yang, Shuyan Dong, Andy Liu, Cheng-I Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
| Challenge: | Existing evaluation methods for transfer learning are limited in speech research . authors show that pre-trained models transfer well across multiple tasks . |
| Approach: | They propose a benchmark to evaluate pre-trained models by increasing task diversity and difficulty over SUPERB. |
| Outcome: | The proposed benchmark increases task diversity and difficulty over SUPERB-SG. |
DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models (2024.findings-acl)
Copied to clipboard
Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang
| Challenge: | Large language models (LLMs) have shown impressive results, but still suffer from hallucination, i.e., the generation of false information. |
| Approach: | They propose a task of sequential model editing that aims to rectify mistakes continuously. |
| Outcome: | The proposed method significantly outperforms baselines in single-turn and sequential editing. |
TrInk: Ink Generation with Transformer Network (2025.emnlp-main)
Copied to clipboard
Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu
| Challenge: | Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples. |
| Approach: | They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies. |
| Outcome: | The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models. |
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for fine-grained opinion mining (OM) are based on span-based annotations, but they are not effective. |
| Approach: | They propose a unified span-based approach for the end-to-end OM setting using syntactic constituents and multi-task learning to integrate them into the proposed model. |
| Outcome: | The proposed approach achieves significant improvements over previous work on the MPQA 2.0 dataset and reduces the number of wrongly-predicted opinion expressions and roles. |
CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation (2022.findings-emnlp)
Copied to clipboard
Jian Yang, Shaohan Huang, Shuming Ma, Yuwei Yin, Li Dong, Dongdong Zhang, Hongcheng Guo, Zhoujun Li, Furu Wei
| Challenge: | Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. |
| Approach: | They propose a cross-lingual entity projection framework to enable zero-shot cross-linguistic NER with the help of a multilingual labeled sequence translation model. |
| Outcome: | The proposed method outperforms the baseline method on two benchmarks by a large margin of +3 7 F1 scores and achieves state-of-the-art performance. |
GCML: Gradient Coherence Guided Meta-Learning for Cross-Domain Emerging Topic Rumor Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing domain adaptation rumor detection methods ignore the data generalization differences and rely on a large amount of unlabeled target domain samples to achieve domain adaptation. |
| Approach: | They propose a Gradient Coherence guided Meta-Learning approach for emerging topics rumor detection that selectively learns more "generalizable" tasks that are more beneficial in adapting to the target domain. |
| Outcome: | The proposed method outperforms baselines on real-world datasets and significantly outperformed traditional methods on the in-domain condition. |
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2022.acl-long)
Copied to clipboard
Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei
| Challenge: | ELECTRA-style tasks are used to pretrain cross-lingual models for NLP tasks . masked language modeling tasks require massive computation resources, rendering such models quite expensive . |
| Approach: | They propose to use ELECTRA-style tasks to pre-train a cross-lingual language model . they propose to pretrain the model on multilingual and parallel corpora . |
| Outcome: | The proposed model outperforms baseline models on cross-lingual understanding tasks with much less computation cost. |
KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi (2020.coling-main)
Copied to clipboard
| Challenge: | low-resource African languages are traditionally left behind because of the lack of well-annotated data and effective preprocessing. |
| Approach: | They propose two news datasets for multi-class classification of news articles in two low-resource African languages. |
| Outcome: | The proposed datasets show that training embeddings on the higher-resourced Kinyarwanda yields successful cross-lingual transfer to Kirundi. |
NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human (2025.findings-emnlp)
Copied to clipboard
Shuo Huang, William Maclean, Xiaoxi Kang, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari, Lizhen Qu
| Challenge: | a large number of large language models are being used to protect user privacy . sanitizing sensitive text using two common strategies is the answer . |
| Approach: | They propose sanitizing sensitive text using deleting expressions and abstracting them . they propose a tool for text rewriting that uses crowdsourcing and large language models . |
| Outcome: | The proposed approach protects privacy before sending sensitive data to large language models . it combines crowdsourcing and large language modeling to create a text rewrite tool . |
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)
Copied to clipboard
Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified. |
| Approach: | They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
| Outcome: | Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)
Copied to clipboard
Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang
| Challenge: | PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks. |
| Approach: | They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks. |
| Outcome: | The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. |
VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text-to-SQL generation are prone to hallucinations and grounding . authors present a novel reasoning paradigm that transforms text- to-Sql from unverifiable textual rationales into step-wise executable semantics. |
| Approach: | They propose a reasoning paradigm that transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics. |
| Outcome: | The proposed reasoning paradigm transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics. |
Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)
Copied to clipboard
null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei
| Challenge: | Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts. |
| Approach: | They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis. |
| Outcome: | The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents. |
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing algorithms to improve the ability of LLMs to follow complex instructions are lacking. |
| Approach: | They propose a benchmark to improve the ability to follow complex instructions by using a IOPO alignment method to take input and output preference into consideration. |
| Outcome: | The proposed algorithm shows 8.15%, 2.18% improvements on in-domain data and 5.91%, 2.83% on out-of-domain datasets compared to SFT and DPO respectively. |
Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have shown excellent performance on knowledge-intensive tasks, but pretraining data tends to contain misleading and conflicting information. |
| Approach: | They systematically analyze LLMs’ learning preferences for data with conflicting knowledge. |
| Outcome: | The proposed model outperforms human-level models on knowledge-intensive tasks by analyzing pretraining data. |
Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information (P19-1)
Copied to clipboard
| Challenge: | Existing work on commenting based on textual content is focused on other modalities, such as graphics and images. |
| Approach: | They propose a task to integrate multiple modalities into automatic commenting . they construct a large-scale dataset and propose 'co-attention' model to capture dependency between textual and visual information. |
| Outcome: | The proposed model can achieve better performance than baselines. |
Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)
Copied to clipboard
Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu
| Challenge: | Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models. |
| Approach: | They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness. |
| Outcome: | The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models. |
An Unsupervised Framework for Adaptive Context-aware Simplified-Traditional Chinese Character Conversion (2024.lrec-main)
Copied to clipboard
| Challenge: | Traditional Chinese characters are still widely used in many areas of China . traditional methods to convert between simplified characters are ineffective . |
| Approach: | They propose an unsupervised adaptive context-aware conversion model that learns to convert between simplified and traditional Chinese characters under a denoising auto-encoder framework. |
| Outcome: | The proposed model outperforms strong unsupervised baselines and yields better conversion result for one-to-many cases. |
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)
Copied to clipboard
Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Triton is a high-level Python-like programming language for building efficient GPU kernels. |
| Approach: | They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs. |
| Outcome: | The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications. |
Budget-Constrained Tool Learning with Planning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for budget-constrained tool learning have been overlooked . et al., 2023b) compared tool learning with other methods to improve performance . |
| Approach: | They propose a method for budget-constrained tool learning by creating a preferable plan under the budget constraint before utilizing the tools. |
| Outcome: | The proposed method reduces the cost of tool learning and reaches competitive Pass Rate. |
Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for key point analysis rely on semantic similarity instead of measuring the existence of shared key points . |
| Approach: | They propose a key point analysis approach with pairwise generation and graph partitioning to summarize arguments into a concise set of key points. |
| Outcome: | The proposed model surpasses existing models on ArgKP and QAM datasets. |
MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognition (2025.emnlp-main)
Copied to clipboard
Xinkui Lin, Yuhui Zhang, Yongxiu Xu, Kun Huang, Hongzhang Mu, Yubin Wang, Gaopeng Gou, Li Qian, Li Peng, Wei Liu, Jian Luan, Hongbo Xu
| Challenge: | Existing methods for GMNER fail to address semantic ambiguity caused by polysemy and long-tail distribution of datasets. |
| Approach: | They propose a framework for Grounded Multimodal Named Entity Recognition that leverages a Multimodal Large Language Model to address semantic ambiguity. |
| Outcome: | Extensive experiments show that the proposed framework outperforms existing methods on two benchmark datasets. |
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning (2026.acl-long)
Copied to clipboard
Fan Gao, Sherry T. Tong, Jiwoong Sohn, Jiahao Huang, Junfeng Jiang, Ding Xia, Piyalitt Ittichaiwong, Kanyakorn Veerakanjana, Hyunjae Kim, Qingyu Chen, Edison Marrese-Taylor, Kazuma Kobayashi, Akiko Aizawa, Irene Li
| Challenge: | Existing models that use English and local languages have a multilingual gap . a language-informed co-reasoning framework can be used to improve multilingual reasoning . |
| Approach: | They propose a language-informed co-reasoning framework that elicits parallel English and local-language reasoning and abstracts them into structured concepts. |
| Outcome: | Experiments show that Med-CoReasoner improves multilingual reasoning performance by 5% . the framework produces clinically sound and culturally grounded reasoning traces . |
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning (2023.findings-emnlp)
Copied to clipboard
Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar
| Challenge: | Existing methods for image-to-text generation store all knowledge within parameters, thus requiring computational-expensive fine-tuning. |
| Approach: | They propose a Retrieval-augmented Visual Language Model that stores all the knowledge within parameters and can be used to retrieve it from the external database. |
| Outcome: | The proposed model significantly boosts performance for image-to-text generation tasks with 4x less parameters compared with baseline methods. |
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schuetze, Volker Tresp, Yunpu Ma
| Challenge: | Large Language Models (LLMs) are stateless and limited by a finite context window, preventing them from maintaining knowledge across long conversations or evolving tasks. |
| Approach: | They propose a reinforcement learning framework that empowers LLMs to actively manage external memory through two specialized agents. |
| Outcome: | The proposed framework outperforms baselines and benchmarks across diverse question types, three benchmarks, and multiple model scales. |
Investigating the Multilingual Calibration Effects of Language Model Instruction Tuning (2026.eacl-short)
Copied to clipboard
Jerry Huang, Peng Lu, Qiuhao Zeng, Yusuke Iwasawa, Yutaka Matsuo, Sarath Chandar, Edison Marrese-Taylor, Irene Li
| Challenge: | despite advances in foundation model research, the relationship between large language models and their calibration remains an open area of research. |
| Approach: | They examine a gap in the calibration of large language models within multilingual settings to better understand how data scarcity can potentially lead to different calibration effects. |
| Outcome: | The proposed calibration gap is found in two multilingual benchmarks over 29 and 42 languages. |
SocialBench: Sociality Evaluation of Role-Playing Conversational Agents (2024.findings-acl)
Copied to clipboard
Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang
| Challenge: | Existing studies on role-playing agents have focused on enhancing their conversational capability, role-specific knowledge and style, but there has been a gap in assessing their social intelligence. |
| Approach: | They propose a benchmark to evaluate the sociality of role-playing agents using LLMs. |
| Outcome: | The proposed benchmark is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. |
Relation-Aware Question Answering for Heterogeneous Knowledge Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing retrieval-based approaches to solve multihop Knowledge Base Question Answering (KBQA) fail to utilize information from head-tail entities and the semantic connection between relations to enhance the information capturing of relations in KGs. |
| Approach: | They propose to use a dual relation graph to find the answer entity in a knowledge graph . they use primal entity graph reasoning, dual relation grafitment and interaction . |
| Outcome: | The proposed approach achieves significant performance gain over the prior state-of-the-art on two public datasets, WebQSP and CWQ. |
Red Teaming Language Models for Processing Contradictory Dialogues (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that language models are prone to self-contradiction during dialogues. |
| Approach: | They propose a red teaming framework that detects and attempts to explain dialogues, then modifies existing contradictory content using the explanation. |
| Outcome: | The proposed task improves the ability to detect contradictory dialogues and provides valid explanations. |
AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework (2024.lrec-main)
Copied to clipboard
| Challenge: | Currently, ML&DL methods fail to provide reasons for stock trend predictions, lacking interpretability and reasoning processes. large language models (LLMs) suffer from hallucinations and are unable to keep up with the latest information. |
| Approach: | They develop a method to train large language models to handle financial analysis tasks . they use AlphaFin datasets to compare performance with traditional methods . |
| Outcome: | The proposed method improves stock trend prediction and financial question answering tasks. |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have remarkable capabilities, but unreliability remains a barrier to deployment in high-stakes domains. |
| Approach: | They propose to transform uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior. |
| Outcome: | The proposed model evolution from passive diagnostic metric to active control signal is critical for high-stakes applications. |
Generative Text-to-Image Retrieval via Hierarchical Identifiers and Semantic Internalization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing text-to-image retrieval methods suffer from limited semantic discriminability, alignment bias, and closed-set restrictions. |
| Approach: | They propose a framework for semantic internalization for Generative Multimodal Alignment . they construct multi-granularity hierarchical identifiers to ensure unique, semantically consistent image representations . |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks on Flickr30K and MS-COCO datasets . it achieves average Recall@1, Recall @5, and Recall_10 improvements of 10.65%, 8.50%, and 7.00% . |
Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent research indicates that Large Reasoning Models suffer from a strategic bottleneck at reasoning path planning. |
| Approach: | They propose a framework that reformulates reasoning as a dynamic search for the optimal thinking strategy. |
| Outcome: | The proposed framework improves accuracy and computational cost while reducing generation length by over 22%. |
LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting (2022.coling-1)
Copied to clipboard
Xiang Chen, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang
| Challenge: | Existing approaches for Named Entity Recognition (NER) use extensive labeled data for model training, which struggles in low-resource scenarios. |
| Approach: | They propose a lightweight tuning paradigm for low-resource NER via pluggable prompting . they construct a learnable verbalizer of entity categories without any label-specific classifiers . |
| Outcome: | The proposed model outperforms baselines and class transfer models in low-resource scenarios. |
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024.emnlp-industry)
Copied to clipboard
Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, Meishan Zhang, Wenjie Li, Min Zhang
| Challenge: | Existing models for text retrieval are based on a multi-stage process that involves retrieving documents from a large corpus. |
| Approach: | They propose to build a multilingual text representation model and a cross-encoder reranker from scratch for text retrieval. |
| Outcome: | The proposed models outperform the state-of-the-art models on long-context retrieval benchmarks. |
A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work has questioned the robustness of unsupervised bilingual dictionary induction methods on distant language pairs. |
| Approach: | They propose an iterative dimension reduction method to bridge this gap . they propose a method that initializes and self-learning and inducing a dictionary . |
| Outcome: | The proposed method achieves 13.64 55.53% accuracy between English and four distant languages. |
GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Computer-aided translation (CAT) is a form of software that assists a human translator in the translation process. |
| Approach: | They propose to use computer-aided translation (CAT) to assist a human translator in the translation process. |
| Outcome: | The proposed method can give significantly more accurate predictions than baseline methods on CAT datasets. |
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts (2025.acl-long)
Copied to clipboard
Ziwei Huang, Wanggui He, Quanyu Long, Yandi Wang, Haoyuan Li, Zhelun Yu, Fangxun Shu, Weilong Dai, Hao Jiang, Fei Wu, Leilei Gan
| Challenge: | Existing studies on text-to-image (T2I) models focus on text alignment, image quality, and object composition capabilities. |
| Approach: | They propose a T2I-FactualBench benchmark to evaluate the factuality of knowledge-intensive concept generation. |
| Outcome: | The proposed framework evaluates the factuality of knowledge-intensive concept generation tasks. |
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been recognized for their impressive capabilities in natural language processing (NLP). |
| Approach: | They propose a method to enhance the multilingual performance of Large Language Models by aggregating knowledge from diverse languages. |
| Outcome: | The proposed method reduces the performance disparity across languages and offers valuable insights for further exploration. |
Attention-Guided Answer Distillation for Machine Reading Comprehension (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to reading comprehension systems are vulnerable to adversarial attacks. |
| Approach: | They propose to use knowledge distillation to transfer knowledge from an ensemble to a single model. |
| Outcome: | The proposed methods outperform the teacher on adversarial datasets and NarrativeQA benchmarks. |
KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | General pre-trained language models (PLMs) leverage relation triples from knowledge graphs (KGs) and integrate external data sources into language models via self-supervised learning. |
| Approach: | They propose to learn Knowledge-Enhanced language representations with Hierarchical Reinforcement Learning (KEHRL) to detect positions for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge. |
| Outcome: | The proposed model can detect essential positions in texts for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge. |
Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction (2022.findings-naacl)
Copied to clipboard
Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen
| Challenge: | Existing approaches for named entity recognition and relation extraction suffer from error sensitivity when irrelevant object images are incorporated in texts. |
| Approach: | They propose a hierarchical visual prefix fusion NeTwork for visual-enhanced entity and relation extraction using pluggable visual prefixed visual features. |
| Outcome: | The proposed method achieves state-of-the-art on three benchmark datasets. |
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Event schemas encode knowledge of stereotypical structures of events and their connections . previous work on event schema induction focuses on atomic events or linear temporal sequences . |
| Approach: | They propose a Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. |
| Outcome: | The proposed model outperforms existing models on HITS@1 by 17.8%. |
ToolRM: Towards Agentic Tool-Use Reward Modeling (2026.findings-acl)
Copied to clipboard
Renhao Li, Jianhong Tu, Yang Su, Yantao Liu, Fei Huang, Hamid Alinejad-Rokny, Derek F. Wong, Junyang Lin, Min Yang
| Challenge: | lack of reliable reward models for tool-use tasks has limited progress toward agentic AI . recent advances in agentic artificial intelligence are driven by tool-using capabilities of large language models. |
| Approach: | They propose a pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling to build lightweight reward models. |
| Outcome: | The proposed model outperforms existing models on tool calling tasks with higher accuracy. |
Revisiting and Advancing Chinese Natural Language Understanding with Accelerated Heterogeneous Knowledge Pre-training (2022.emnlp-industry)
Copied to clipboard
Taolin Zhang, Junwei Dong, Jianing Wang, Chengyu Wang, Ang Wang, Yinghui Liu, Jun Huang, Yong Li, Xiaofeng He
| Challenge: | Existing knowledge-enhanced pre-trained language models (KEPLMs) can capture internal knowledge, but can't understand external background knowledge. |
| Approach: | They propose to use Chinese knowledge-enhanced pre-trained language models to improve context-aware representations via learning from structured relations in knowledge bases. |
| Outcome: | Experiments show that Chinese knowledge-enhanced pre-trained language models outperform strong baselines over various benchmark NLP tasks and in different model sizes. |
Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)
Copied to clipboard
Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang
| Challenge: | Recent studies have focused on a single pass of lyrics generation with little human intervention. |
| Approach: | They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes. |
| Outcome: | The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly. |
Advancing Collaborative Debates with Role Differentiation through Multi-Agent Reinforcement Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-agent collaborative tasks exhibit exceptional capabilities in natural language applications and generation. |
| Approach: | They propose a multi-LLM Cooperation framework with automatic role assignment capabilities that allows multiple agents to embed roles in turn-based speaking. |
| Outcome: | The proposed framework improves collaboration and expertise among agents and teams by enabling them to share roles and develop complementary strengths from the optimization level. |
CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset (2023.findings-acl)
Copied to clipboard
| Challenge: | a cross-domain text-to-SQL task aims to parse user questions into SQL on complete unseen databases . a single-domain task evaluates the performance on identical databases based on the same domain . |
| Approach: | They propose a cross-domain text-to-SQL task that parses user questions into SQL on unseen databases. |
| Outcome: | The proposed system can parse user questions into SQL on complete unseen databases. |
Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation (2025.findings-acl)
Copied to clipboard
Hongzhe Huang, Jiang Liu, Zhewen Yu, Li Cai, Dian Jiao, Wenqiao Zhang, Siliang Tang, Juncheng Li, Hao Jiang, Haoyuan Li, Yueting Zhuang
| Challenge: | Recent advances in Multi-modal Large Language Models (MLLMs) introduce significant variability in data quality. |
| Approach: | They propose to use human and LLM preference alignment to compress large corpus of machine-generated multimodal instructions into a compact and high-quality form. |
| Outcome: | The proposed algorithm outperforms LLaVA-series models in MLLM benchmarks by 90% . it uses human and LLM preference alignment to compress a large dataset . |
On the Reliability of Psychological Scales on Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has focused on examining Large Language Models’ characteristics from a psychological standpoint, acknowledging the necessity of understanding their behavioral characteristics. |
| Approach: | They propose to examine the reliability of personality tests to LLMs by using psychological scales. |
| Outcome: | The proposed model can represent diverse personalities with specific prompt instructions. |
TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Games (2025.emnlp-main)
Copied to clipboard
| Challenge: | evaluating large language models' reasoning abilities via detective stories is often infeasible due to the large answer space and diverse reasoning types presented by its questions. |
| Approach: | They propose a framework and dataset for evaluating the deductive reasoning abilities of Large Language Models (LLMs) by leveraging the interactive gameplay of detective games Ace Attorney and Danganronpa. |
| Outcome: | The proposed framework and dataset are based on the detective games Ace Attorney and Danganronpa and show that they are more efficient than current strategies for enhancing deductive reasoning. |
Understanding Secret Leakage Risks in Code LLMs: A Tokenization Perspective (2026.findings-acl)
Copied to clipboard
| Challenge: | Code Large Language Models (CLLMs) are reshaping how software is built, maintained, and evolved. |
| Approach: | They propose to use BPE tokenization to inadvertently leak code secrets . they propose to mitigate the gibberish bias by using a newer tokenizer . |
| Outcome: | The proposed model is based on a novel method that can be used to detect and mitigate gibberish bias in CLLMs. |
Multilingual Agreement for Multilingual Neural Machine Translation (2021.acl-short)
Copied to clipboard
| Challenge: | Existing models that only use auxiliary languages to encourage multilingual agreement ignore the relationships between different language pairs. |
| Approach: | They propose a multilingual agreement-based method which explicitly models the agreement between different translation directions by randomly substituting some fragments of the source language with their counterpart translations of auxiliary languages. |
| Outcome: | The proposed method improves on the multilingual translation task of 10 language pairs. |
DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale (2025.findings-acl)
Copied to clipboard
Linghao Zhang, Junhao Wang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Jiaheng Wen, Chengxing Xie, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Existing studies highlight that dependency-related issues cause over 40% of observed runtime errors on the generated repository. |
| Approach: | They propose a large-scale benchmark and evaluation framework specifically designed to assess LLMs’ capability on dependency inference. |
| Outcome: | The proposed model achieves only a 48% execution pass rate on Python, indicating room for improvement. |
TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Long-context Document Visual Question Answering (DocVQA) methods struggle with visual semantics or handling finite context windows. |
| Approach: | They propose a new approach to longcontext document visual question answering that transforms retrieval into adaptive evidence chain construction using a Bi-Layered Graph. |
| Outcome: | The proposed approach achieves an average accuracy improvement of 14.07% on M5BookVQA and exhibits robust generalization with a 13.38% gain across four established benchmarks. |
Be Helpful but Don’t Talk too Much - Enhancing Helpfulness in Conversations through Relevance in Multi-Turn Emotional Support (2024.emnlp-main)
Copied to clipboard
| Challenge: | a helpful speaker should maintain an "effect-effort" tradeoff for a conversation to help and support . a study aimed to cultivate the awareness of "optimal relevance" into the cognitive process of conversation agents . |
| Approach: | They integrate the "Cognitive Relevance Principle" into emotional support agents . they found that the "relevance principle" is effective in generating human-like, helpful, harmless conversations . |
| Outcome: | The proposed method improves human-likedness and support in multi-turn conversations . the source code will be available at https://github.com/CN-Eyetk/VLESA-ORL.git . |
TableBank: Table Benchmark for Image-based Table Detection and Recognition (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing techniques for table detection and recognition are limited to document types and layouts. |
| Approach: | They propose to build a table detection and recognition dataset with weak supervision from Word and Latex documents on the internet. |
| Outcome: | The proposed dataset contains 417K high quality labeled tables and is publicly available. |
Layer-wise Fusion with Modality Independence Modeling for Multi-modal Emotion Recognition (2023.acl-long)
Copied to clipboard
Jun Sun, Shoukang Han, Yu-Ping Ruan, Xiaoning Zhang, Shu-Kai Zheng, Yulong Liu, Yuxin Huang, Taihao Li
| Challenge: | Existing studies focus on developing models that exploit the unification of multiple modalities. |
| Approach: | They propose to maintain modality independence by using a multi-modal transformer model that fuses all modalities. |
| Outcome: | The proposed model outperforms state-of-the-art models in multi-modal emotion recognition. |
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models require a more expressive vocabulary to represent all languages . however, increasing the vocabulary size significantly slows down the pre-training speed . |
| Approach: | They propose an algorithm VoCap to determine the desired vocabulary capacity of each language. |
| Outcome: | The proposed algorithm improves cross-lingual model pre-training while reducing side effects of increasing vocabulary size. |
Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Despite promising progress, vision-language models still exhibit significant challenges in understanding visio-linguistic concepts beyond object terms. |
| Approach: | They propose a framework that encourages the model to pay greater attention to composition words denoting relationships and attributes within the text. |
| Outcome: | The proposed framework improves the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements. |
Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (2024.acl-long)
Copied to clipboard
| Challenge: | Existing detectors for AI-generated text lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text. |
| Approach: | They propose a siamese calibration technique to train the model to make equally confident predictions under different noise, which improves the model’s robustness against adversarial perturbations. |
| Outcome: | The proposed detector outperforms baseline methods on four datasets and is more generalizable in cross-domain, cross-genre, and mixed-source scenarios. |
Better LLM Reasoning via Dual-Play (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR) however, external supervision remains a bottleneck for tasks and domains for which supervised data are scarce or non-existent. |
| Approach: | They propose a novel dual-play framework that adversarially trains two models initialized from the same base model. |
| Outcome: | The proposed framework improves the math reasoning performance of large language models. |
ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors (2024.findings-emnlp)
Copied to clipboard
Zhexin Zhang, Yida Lu, Jingyuan Ma, Di Zhang, Rui Li, Pei Ke, Hao Sun, Lei Sha, Zhifang Sui, Hongning Wang, Minlie Huang
| Challenge: | Existing tools for detecting safety issues in LLMs are expensive and inefficient. |
| Approach: | They propose an LLM-based safety detector which annotates the safety of queries and provides explanations for its decisions. |
| Outcome: | The proposed detector outperforms baselines on four sets of query-response pairs and is effective as a safety evaluator for advanced LLMs. |
Unifying Inference-Time Planning Language Generation (2026.findings-acl)
Copied to clipboard
Prabhu Prakash Kagitha, Bo Sun, Ishan Desai, Andrew Zhu, Cassie Huang, Manling Li, Ziyang Li, Li Zhang
| Challenge: | Large language models (LLMs) are used to generate a formal representation of a plan in a planning language. |
| Approach: | They propose a unifying organizational framework based on intermediate representations to unify the inference-time LLM-as-formalizer methodology for classical planning. |
| Outcome: | The proposed framework subsumes most existing work and proposes new ones that involve syntactically similar but high-resource intermediate languages. |
Can Monolingual Pretrained Models Help Cross-Lingual Classification? (2020.aacl-main)
Copied to clipboard
| Challenge: | Multilingual pretrained language models have shown impressive results for cross-lingual transfer, but due to the constant model capacity, multilingual pre-training usually lags behind the monolingual competitors. |
| Approach: | They propose to transfer the knowledge from monolingual pretrained models to multilingual ones to improve zero-shot cross-lingual classification by using machine translation systems. |
| Outcome: | The proposed methods outperform vanilla multilingual fine-tuning on two cross-lingual classification benchmarks. |
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)
Copied to clipboard
Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang
| Challenge: | Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability. |
| Approach: | They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs . |
| Outcome: | The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks. |
HiSVD: Principled Low-Rank Approximation of LLMs via Hierarchical Modeling of Information Capacity and Spectral Structure (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating layer importance ignore the fine-grained influence of spectral distribution shape. |
| Approach: | They propose a hierarchical rank allocation framework with two stages to address this gap . they propose SVD-based lowrank approximation that exploits spectral heterogeneity . |
| Outcome: | Experiments show that HiSVD outperforms state-of-the-art methods on LLMs . |
Meta-Reflection: A Feedback-Free Reflection Learning Framework (2025.acl-long)
Copied to clipboard
Yaoke Wang, Yun Zhu, XintongBao XintongBao, Wenqiao Zhang, Suyang Dai, Kehan Chen, Wenqiang Li, Gang Huang, Siliang Tang, Yueting Zhuang
| Challenge: | Existing approaches to improve large language models' ability to understand and reason are limited by external feedback. |
| Approach: | They propose a feedback-free reflection mechanism that requires only a single inference pass without external feedback. |
| Outcome: | The proposed method is based on an industrial e-commerce benchmark and public datasets. |
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space (2025.emnlp-main)
Copied to clipboard
Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang
| Challenge: | Embodied Question Answering (EQA) tasks are primarily focused on indoor environments, leaving the complexities of urban settings unexplored. |
| Approach: | They propose a task where an embodied agent answers open-vocabulary questions in dynamic city spaces. |
| Outcome: | The proposed agent achieves 60.7% of human-level answering accuracy compared to baselines . the proposed agent outperforms existing agents in open-ended city spaces . |
From Noise to Clarity: Filtering Real and LLM-Generated Samples for Enhanced Intent Detection (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using large language models for generating synthetic samples for data augmentation can cause problems with the generalization ability of classification models. |
| Approach: | They propose an interpretable Sample Filter by Topic Modeling framework that allows for filtering by topic and a 'sampler by topic' framework. |
| Outcome: | The proposed framework reduces the quantity of real and synthetic samples while improving the performance of the classification models. |
DDGIP: Radiology Report Generation Through Disease Description Graph and Informed Prompting (2025.findings-naacl)
Copied to clipboard
| Challenge: | Automatic radiology report generation is challenging due to inherent biases in medical imaging data. |
| Approach: | They propose a disease description graph that encapsulates comprehensive and pertinent disease information. |
| Outcome: | The proposed model outperforms state-of-the-art models on two widely-used datasets . the proposed model is based on a three-layer decoder and improves on existing models . |
Ciron: a New Benchmark Dataset for Chinese Irony Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | Automatic Chinese irony detection often lacks labeled benchmark datasets . despite its pervasive nature, irony is a trope whose actual meaning differs from what is literally enunciated. |
| Approach: | They propose to use a Chinese benchmark dataset for automatic Chinese irony detection to provide a benchmark for machine learning models. |
| Outcome: | The proposed dataset includes more than 8.7K posts, collected from Weibo, a micro blogging platform. |
LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning. |
| Approach: | They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion . |
| Outcome: | The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action. |
R2F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference (2022.emnlp-main)
Copied to clipboard
| Challenge: | Document-level natural language inference (DOCNLI) is a new task in natural language processing. |
| Approach: | They propose a document-level natural language inference framework that fuses sentence-level tasks into a set of sentence-based tasks. |
| Outcome: | The proposed framework improves interpretability and performance with evidence. |
ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems with opaque architectures are limiting deep search capabilities for web-augmented large language models. |
| Approach: | They propose a transparent and modular multi-agent framework to democratize deep search for LLMs. |
| Outcome: | The proposed framework outperforms open-source systems in deep reasoning tasks. |
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)
Copied to clipboard
Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao
| Challenge: | Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions. |
| Approach: | They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models. |
| Outcome: | The proposed benchmarks show that the models perform better in open-ended conversations. |
Explicit Semantic Decomposition for Definition Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing definition generation methods rely on decoding to extract semantic components of words. |
| Approach: | They propose a method which explicitly decomposes meaning of words into semantic components and models them with discrete latent variables for definition generation. |
| Outcome: | The proposed method outperforms existing methods on WordNet and Oxford benchmarks. |
GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | a funder name refers to an agency, organization, or program providing financial support for the research. |
| Approach: | They propose a funding sentence classifier and a relation extraction framework to extract grant information from scientific articles. |
| Outcome: | The proposed framework outperforms state-of-the-art BERT-based RE baselines against the PubMed Central and arXiv test sets. |
Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks and evaluation protocols focus on surface-level factual recall. |
| Approach: | They propose a benchmark for assessing cognitive memory under cue–trigger semantic disconnect. |
| Outcome: | The proposed framework reveals failures not captured by existing benchmarks. |
LJPCheck: Functional Tests for Legal Judgment Prediction (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing LJP models fail to evaluate specific aspects of their performance, such as legal fairness and judicial fairness. |
| Approach: | They propose a suite of functional tests for LJP models to comprehend LJp models’ behaviors and offer diagnostic insights. |
| Outcome: | Extensive tests reveal weaknesses in LJP models and provide diagnostic insights. |
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)
Copied to clipboard
Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang
| Challenge: | Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand. |
| Approach: | They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages. |
| Outcome: | Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages. |
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale generative models like DeepSeek-R1 and OpenAI-O1 benefit substantially from chain-of-thought reasoning, yet pushing their performance typically requires vast data, large model sizes, and full-parameter fine-tuning. |
| Approach: | They propose a dual-system LoRA framework that partitions data and parameters by System 1 or System 2 demands and adopts a two-stage fine-tuning strategy to enhance knowledge and intuition. |
| Outcome: | The proposed framework partitions data and parameters by System 1 or System 2 demands, using fewer yet more focused parameters for each task. |
AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models (2024.findings-emnlp)
Copied to clipboard
Xiyang Wu, Tianrui Guan, Dianqi Li, Shuaiyi Huang, Xiaoyu Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Boyd-Graber, Tianyi Zhou, Dinesh Manocha
| Challenge: | Large vision-language models are prone to hallucinations, where contextual cues in an image can trigger the language module to produce overconfident and incorrect reasoning about abnormal or hypothetical objects. |
| Approach: | They propose to automate the generation of hallucination-related questions using images . they propose to use three image manipulation strategies to induce hallucinosity . |
| Outcome: | The proposed approach reduces human bias in crafting such examples and improves accuracy. |
Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)
Copied to clipboard
Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation. |
| Approach: | They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior. |
| Outcome: | Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function. |
Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning (2026.acl-long)
Copied to clipboard
Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu, Weizhou Shen, Peng Li, Ming Yan, Fei Huang, Ya-Qin Zhang, Yang Liu
| Challenge: | Recent advances in Large Language Models (LLMs) have enabled strong performance in long-form writing, but current training paradigms remain limited. |
| Approach: | They propose an Adaptive Curriculum Reinforcement Learning framework to advance long-form writing capabilities beyond SFT. |
| Outcome: | Experiments on 7B-scale writer models show that Writing-RL improves long-form writing performance over strong SFT baselines. |
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks (2026.acl-long)
Copied to clipboard
Tianyi Wang, Yixia Li, Long Li, Yibiao Chen, Shaohan Huang, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
| Challenge: | Proximal Policy Optimization (PPO) is central to aligning Large Language Models with verifiable rewards. |
| Approach: | They propose a scalable algorithm that harmonizes sample efficiency with stability of outcome-based updates. |
| Outcome: | The proposed algorithm outperforms standard PPO and matches the performance of computation-heavy group-based methods. |
Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs. |
| Approach: | They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them. |
| Outcome: | The proposed method reduces hallucinations by reducing false activation and enhancing correct ones. |
Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)
Copied to clipboard
Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang
| Challenge: | Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability. |
| Approach: | They propose an off-policy influence estimation method that approximates data influence using offline trajectories. |
| Outcome: | The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency. |
Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to retrieve hard negative sentences are limited in the scale of the dataset thus fail to identify negative samples of high difficulty for every image. |
| Approach: | They propose to use a model to generate synthetic negative sentences with higher difficulty by masking and refilling the images and performing word discrimination and word correction tasks to improve retrieval and generation. |
| Outcome: | The proposed model generates synthetic negative sentences with higher difficulty on MS-COCO and Flickr30K and is robust and faithful to state-of-the-art training. |
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)
Copied to clipboard
Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang
| Challenge: | Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph . |
| Approach: | They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm. |
| Outcome: | The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy. |
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs (2021.emnlp-main)
Copied to clipboard
Zewen Chi, Li Dong, Shuming Ma, Shaohan Huang, Saksham Singhal, Xian-Ling Mao, Heyan Huang, Xia Song, Furu Wei
| Challenge: | Multilingual T5 pretrains a sequence-to-sequence model on monolingual texts, but it has shown promising results on many cross-lingual tasks. |
| Approach: | They propose a partially non-autoregressive objective for text-to-text pre-training and propose mT6 to improve cross-lingual transferability over multilingual T5. |
| Outcome: | The proposed model improves cross-lingual transferability over existing models. |
Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)
Copied to clipboard
Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou
| Challenge: | Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments. |
| Approach: | They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts. |
| Outcome: | Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability. |
NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies on Chinese grammatical error correction focus on learning essays. |
| Approach: | They propose a Chinese grammatical error correction dataset that annotates multiple references for 12,500 sentences from three native domains. |
| Outcome: | The proposed dataset can be used to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains. |
Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)
Copied to clipboard
Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi
| Challenge: | Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance. |
| Approach: | They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation. |
| Outcome: | The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities. |
FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)
Copied to clipboard
Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang
| Challenge: | Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation. |
| Approach: | a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 . |
| Outcome: | a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 . |
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)
Copied to clipboard
Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke
| Challenge: | Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis. |
| Approach: | They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis. |
| Outcome: | SciAssess evaluates 11 LLMs on multiple tasks across scientific fields. |
Integrating Data Validation with Large Language Models for Regulation-Guided Tabular Anomaly Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing tabular anomaly detection methods focus on detecting anomalies based on data distribution without considering regulatory compliance. |
| Approach: | They propose a task that leverages regulations to detect anomalies in tabular data . they also develop three new datasets to address this task . |
| Outcome: | The proposed method outperforms baselines on three new datasets. |
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)
Copied to clipboard
Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
| Challenge: | Existing approaches to program repair are based on correctness alone. |
| Approach: | They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits. |
| Outcome: | The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing. |
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can replicate insecure patterns from training data. |
| Approach: | They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module. |
| Outcome: | Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines. |
When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost. |
| Approach: | They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations. |
| Outcome: | The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations. |
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)
Copied to clipboard
Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang
| Challenge: | a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling . |
| Approach: | They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution. |
| Outcome: | The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data. |
OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety (2024.acl-demos)
Copied to clipboard
Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin, Yufei Huang, Ling Shi, Junhui Zhang, Xinmeng Ji, Tingting Cui, Liutao Liutao, Jinwang Song, Hongying Zan, Sun Li, Deyi Xiong
| Challenge: | a rapid development of Chinese large language models poses big challenges for efficient LLM evaluation. |
| Approach: | They propose an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. |
| Outcome: | The evaluation platform OpenEval benchmarks Chinese LLMs across capability, alignment and safety. |
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing metrics for video captioning are based on text-based comparisons with ground-truth references. |
| Approach: | They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research . |
| Outcome: | The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics . |
ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained Exploration (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models face intrinsic limitations in coding with unseen APIs in training corpora. |
| Approach: | They propose a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by planning a complex problem into several API invocation subtasks and experimenting with correct API usage at intermediate steps. |
| Outcome: | The proposed framework significantly improves performance for models lacking prior API knowledge, achieving 11.99% over retrieval-based approaches and 17.28% over pretraining-based methods in pass@10. |
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)
Copied to clipboard
Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Deli Zhao, Wenbing Huang, Tingyang Xu, Qifeng Bai, Yu Rong
| Challenge: | Existing medical reasoning datasets are limited in scale and typically rely on incomplete data. |
| Approach: | They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline. |
| Outcome: | The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%. |
Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)
Copied to clipboard
| Challenge: | Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. |
| Approach: | They propose to generate sentences from disentangled syntactic and semantic spaces by using the linearized tree sequence. |
| Outcome: | The proposed method achieves similar or better performance in various tasks compared with state-of-the-art models. |
Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)
Copied to clipboard
Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone. |
| Approach: | They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs. |
| Outcome: | The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively. |
Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Documents contain various structures that hinder the ability of machines to comprehend . user information needs are often underspecified, and the nature of heterogeneous documents poses challenges. |
| Approach: | They propose a dataset for building machines that help users seek information via conversations . their dataset contains over 100,000 turns based on Chinese documents from five domains . |
| Outcome: | The proposed tasks are challenging and worthy of further research. |
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination (2026.acl-industry)
Copied to clipboard
Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit, Jiaxin Zhang, Vaibhav Vats, Yu Li, Xiangyu Peng, Chien-Sheng Wu
| Challenge: | Enterprise deep research systems fail to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. |
| Approach: | They propose a scalable Enterprise Deep Research (EDR) architecture that decomposes requests into coverage-driven objectives via outline generation with reflection and localizes context with dependency-guided execution and explicit information sharing. |
| Outcome: | The proposed system achieves the strongest overall performance compared with competitive deep-research baselines on internal sales enablement tasks and the public DeepResearch Bench benchmark. |
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Fine-tuning-as-a-service exposes models to harmful fine-tuneing attacks . however, inherent general adaptability of LLMs allows them to bypass selective unlearning by rapidly relearning or repurposing their general capabilities for harmful tasks. |
| Approach: | They propose a paradigm shift that inducing model collapse instead of selective removal by relearning or repurposing general capabilities for harmful tasks. |
| Outcome: | The proposed model collapse mechanism neutralizes the very general capabilities that attackers exploit, tackling the core issue unaddressed by selective unlearning. |
AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation (2024.emnlp-main)
Copied to clipboard
Wenhao Huang, Zhouhong Gu, Chenghao Peng, Jiaqing Liang, Zhixu Li, Yanghua Xiao, Liqian Wen, Zulong Chen
| Challenge: | Existing methods for web scraping suffer from limited adaptability and scalability when faced with a new website. |
| Approach: | They propose a framework that generates web scrapers with large language models and a new executability metric to measure the performance of web scraper generation tasks. |
| Outcome: | The proposed framework can handle diverse web environments more efficiently. |
MemeQA: Holistic Evaluation for Meme Understanding (2025.acl-long)
Copied to clipboard
Khoi P. N. Nguyen, Terrence Li, Derek Lou Zhou, Gabriel Xiong, Pranav Balu, Nandhan Alahari, Alan Huang, Tanush Chauhan, Harshavardhan Bala, Emre Guzelordu, Affan Kashfi, Aaron Xu, Suyesh Shrestha, Megan Vu, Jerry Wang, Vincent Ng
| Challenge: | Existing benchmarks for meme understanding only concern narrow aspects of meme semantics. |
| Approach: | They propose to use multiple-choice questions to evaluate meme comprehension . they use a dataset of over 9,000 multiple-question questions to assess meme comprehension. |
| Outcome: | The proposed model outperforms existing models on meme comprehension . the model makes many errors on memes where proper understanding requires going beyond sentiment . |
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)
Copied to clipboard
Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun, Wei Wang
| Challenge: | Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities. |
| Approach: | They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations. |
| Outcome: | Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well. |
Few-Shot Named Entity Recognition: An Empirical Baseline Study (2021.emnlp-main)
Copied to clipboard
Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han
| Challenge: | Existing methods to build named entity recognition systems with limited labeled data are lacking. |
| Approach: | They propose three orthogonal schemes to build named entity recognition systems when labeled data is limited. |
| Outcome: | The proposed NER systems outperform existing methods on few-shot and training-free settings. |
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing techniques for natural language understanding and generation use autoencoding and/or autoregressive objectives to train models. |
| Approach: | They propose a self-supervised pre-training scheme that pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus for generating new text conditioned on context. |
| Outcome: | The proposed scheme achieves state-of-the-art results on a variety of language generation benchmarks covering generative question answering, abstractive summarization and conversational response generation. |
LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey (2026.findings-acl)
Copied to clipboard
Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu, Jizhou Guo, Yankai Chen, Chunyu Miao, Hoang H Nguyen, Yue Zhou, Weizhi Zhang, Liancheng Fang, Hanrong Zhang, Fangxin Wang, Pengfei Zhang, Langzhou He, Yangning Li, Dongyuan Li, Renhe Jiang, Philip S. Yu
| Challenge: | Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. |
| Approach: | They propose to integrate human-provided information, feedback, or control into the agent system to enhance system performance, reliability, and safety. |
| Outcome: | The proposed systems improve system performance, reliability, and safety by integrating human-provided information, feedback, or control into the agent system. |
Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking (2021.acl-short)
Copied to clipboard
| Challenge: | Existing dialog state tracking models neglect rich structural information in a dataset. |
| Approach: | They propose to use curriculum learning to leverage dialog state tracking data . they propose a model-agnostic framework that pre-trains a DST model with schema information . |
| Outcome: | The proposed framework improves performance over a transformer-based and RNN-based model on WOZ2.0 and MultiWOZ2.1. |
Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to generate intelligent open-domain dialogue agents only consider auxiliary commonsense stored in pure text, ignoring grounding information from the external visual world. |
| Approach: | They propose a VIsual Commonsense enhanced dialogue generaTOR that exploits auxiliary commonsense from images related to context to generate coherent and informative responses. |
| Outcome: | The proposed method outperforms the latest competitive methods in terms of coherence and diversity on two public datasets. |
VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Despite the impressive capabilities of large multi-modal models, their effectiveness in handling complex tasks has been limited by the prevailing singlestep reasoning paradigm. |
| Approach: | They propose a visuallygrounded object-centric Chain-of-Thought reasoning framework for LMMs that is based on a multi-modal interleaved and aligned representation of object concepts. |
| Outcome: | The proposed model outperforms SOTA models in CLEVR and EmbSpatial benchmarks. |
Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for dialog routing are mostly heuristic and cannot achieve high-quality performance. |
| Approach: | They propose a multi-task learning framework with a dialog encoder and two tailored gated mechanism modules to solve this problem. |
| Outcome: | The proposed model can play the role of hierarchical information filtering and is non-invasive to existing dialog systems. |
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)
Copied to clipboard
Damai Dai, Chengqi Deng, Chenggang Zhao, R.x. Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y. Wu, Zhenda Xie, Y.k. Li, Panpan Huang, Fuli Luo, Chong Ruan, Zhifang Sui, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs. |
| Approach: | They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them. |
| Outcome: | The proposed architecture achieves comparable performance with GShard with 2B parameters and computation. |
Fine-Tuning Language Models with Reward Learning on Policy (2024.naacl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is an effective approach to align large language models (LLMs) to human preferences. |
| Approach: | They propose a framework that refines a reward model using policy samples to keep it on-distribution. |
| Outcome: | The proposed framework outperforms the state-of-the-art on three benchmark datasets showing that it can learn robust representations of policy samples. |
Parameter Efficient Multi-task Fine-tuning by Learning to Transfer Token-wise Prompts (2023.findings-emnlp)
Copied to clipboard
Muling Wu, Wenhao Liu, Jianhan Xu, Changze Lv, Zixuan Ling, Tianlong Li, Longtao Huang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Prompt tuning has been proven to be successful on various tasks by incorporating a small number of trainable parameters while freezing large pre-trained language models. |
| Approach: | They propose a token-wise prompt tuning method that uses a bank of finer-grained soft prompt tokens to generate an instance-dependent prompt. |
| Outcome: | The proposed method performs far better than full parameter fine-tuned models and achieves state-of-the-art by tuning only 0.035% parameters on 14 datasets. |
Evaluating Explanation Methods for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has seen great success during recent years. |
| Approach: | They propose a metric that measures the fidelity of explanation methods on translation tasks . they use an efficient approximation to evaluate several explanation methods . |
| Outcome: | The proposed metric is efficient and can be used on translation tasks. |
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator (2023.acl-long)
Copied to clipboard
Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li
| Challenge: | Existing pre-training methods underutilize the benefits of language understanding for generation. |
| Approach: | They propose a GAN-style model for encoder-decoder pre-training with an auxiliary discriminator. |
| Outcome: | The proposed model outperforms existing pre-trained models and achieves state-of-the-art performance. |
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)
Copied to clipboard
Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov
| Challenge: | Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps. |
| Approach: | They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels . |
| Outcome: | The proposed benchmark aims to bridge symbolic reasoning and factual verification. |
Through the Valley: Path to Effective Long CoT Training for Small Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Long chain-of-thought (CoT) supervision is effective for large language models . but small models trained on limited long CoT data experience performance degradation . |
| Approach: | They identify a phenomenon called Long CoT Degradation in small language models . long CoT data can be used to generate long chain-of-thought (CoT) responses . |
| Outcome: | The results show that models trained on 8k long CoT examples lose up to 75% of their original performance before fine-tuning. |
Learning Preference Model for LLMs via Automatic Preference Data Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing training methods for large language models rely on human-annotated data. |
| Approach: | They propose to learn the preference model for LLMs via automatic preference data generation (AutoPM) using HHH-guided preference data, they show reliability and potential . |
| Outcome: | The proposed approach enables LLMs to learn human preferences and align with human values. |
DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check (2025.acl-long)
Copied to clipboard
Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang
| Challenge: | Chinese spelling check (CSC) tasks require that incorrect characters are usually similar to the correct ones in either phonetics or glyph. |
| Approach: | They propose a plug-and-play decoding intervention with similarity of characters module for Chinese spelling check (CSC) they propose to incorporate phonetic and glyph similarities only during the inference phase. |
| Outcome: | The proposed method significantly improves Chinese spelling check models on benchmarks and on benchmark datasets. |
WESR: A Benchmark and Strong Baseline for Word-level Event-Speech Recognition (2026.findings-acl)
Copied to clipboard
Chenchen Yang, Kexin Huang, Liwei Fan, Qian Tu, Botian Jiang, Dong Zhang, Linqi Yin, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
| Challenge: | aaron carroll: the precise localization of non-verbal vocal events remains a critical yet under-explored challenge. carroll says current methods suffer from insufficient task definitions with limited category coverage. carrol: knowing exactly where an event occurred is not enough; knowing exactly what it happened is. |
| Approach: | They propose a taxonomy of 21 vocal events with a new categorization into discrete versus continuous types. |
| Outcome: | The proposed model disentangles ASR errors from event detection while maintaining ASR quality. |
Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun
| Challenge: | Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence. |
| Approach: | They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary. |
| Outcome: | Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training. |
CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. |
| Approach: | They propose an unsupervised reference-free metric which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks. |
| Outcome: | The proposed metric has higher correlations with human judgments while obtaining better generalization of evaluating generated texts from different models and with different qualities. |
On the Branching Bias of Syntax Extracted from Pre-trained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for extracting constituency trees from language models suffer from branching bias. |
| Approach: | They propose to measure the branching bias by comparing the performance gap on a language and its reversed language. |
| Outcome: | The proposed method is agnostic to language models and extracting methods, and it can be implemented with three factors to introduce the branching bias. |
ToM-Synth: Scaling Robust Theory of Mind in LLMs via 6,912 Structured Social Units (2026.findings-acl)
Copied to clipboard
Guiyang Hou, Xiang Huang, Shangke Lyu, Yuchuan Wu, Weiyao Luo, Xinyu Mei, Yongliang Shen, Weiming Lu, Yongbin Li
| Challenge: | Existing methods endowing LLMs with Theory of Mind fail to internalize the augmented ToM into the LLM. |
| Approach: | They propose a factorial combinatorial synthesis framework that enables systematic synthesis of ToM data and uses it for RL fine-tuning. |
| Outcome: | The proposed framework yields a training dataset of 27,648 instances. |
PRIM: Towards Practical In-Image Multilingual Machine Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current research on in-image machine translation focuses on synthetic data with simple background, single font, fixed text position, and bilingual translation. |
| Approach: | They propose an end-to-end model to handle the challenge of practical conditions in PRIM . they annotate a real-world one-line text image with complex background, fonts, diverse text positions . |
| Outcome: | The proposed model improves translation quality and visual effect compared to other models. |
Teaching Large Language Models to Translate on Low-resource Languages with Textbook Prompting (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive results in Machine Translation by following instructions, even without training on parallel data. |
| Approach: | They propose a Translate After LEarNing Textbook approach which aims to enhance LLMs’ ability to translate low-resource languages by learning from a textbook. |
| Outcome: | The proposed approach improves translation performance by 14.8% using 112 low-resource languages from FLORES-200 with two LLMs: ChatGPT and BLOOMZ. |
MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)
Copied to clipboard
Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li
| Challenge: | In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming. |
| Approach: | They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space. |
| Outcome: | The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis. |
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck. |
| Approach: | They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed. |
| Outcome: | The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance. |
Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)
Copied to clipboard
Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang
| Challenge: | Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process. |
| Approach: | They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors. |
| Outcome: | The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs. |
Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models (2026.findings-acl)
Copied to clipboard
Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li
| Challenge: | Existing training paradigms rely on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. |
| Approach: | They propose a framework that integrates large reasoning models with retrieval-augmented generation to improve reasoning fidelity and verification rigor. |
| Outcome: | Experiments on multiple benchmarks demonstrate the effectiveness of the proposed framework. |
CEM: Machine-Human Chatting Handoff via Causal-Enhance Module (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to predict chatbot failure ignore causal variables, resulting in cost increasement and prediction bias. |
| Approach: | They propose a machine-human chatting handoff module that predicts chatbot failure . they use user state and labor cost to correct the prediction bias . |
| Outcome: | The proposed method improves the performance of existing methods without any elaborate model crafting. |
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing (2022.findings-emnlp)
Copied to clipboard
Zefeng Cai, Xiangyu Li, Binyuan Hui, Min Yang, Bowen Li, Binhua Li, Zheng Cao, Weijie Li, Fei Huang, Luo Si, Yongbin Li
| Challenge: | Extensive experiments show that STAR outperforms previous pre-training methods and ranks first on the leaderboard . text-to-SQL parsing aims to translate natural language (NL) questions into executable SQL queries . |
| Approach: | They propose a SQL guided pre-training framework STAR for context-dependent text-to-SQL parsing . they propose two objectives that explore context-dependence of NL utterances and SQL queries . |
| Outcome: | The proposed framework outperforms existing methods on two downstream benchmarks and ranks first on the leaderboard. |
Modeling Evolution of Message Interaction for Rumor Resolution (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for rumor resolution ignore local interactions during the message diffusion which is important for the identification of rumors. |
| Approach: | They propose to model confrontation and reciprocity between message pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. |
| Outcome: | Experiments on a PHEME dataset show that the proposed model achieves higher accuracy than existing methods. |
DocMEdit: Towards Document-Level Model Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models only output short phrases or sentences, raising doubts about their practical usability. |
| Approach: | They propose a dataset focused on document-level model editing that aims to correct errors and outdated knowledge in Large language models (LLMs) they propose to use document-based model editing to improve model capabilities in real-world scenarios. |
| Outcome: | The proposed model editing task improves model capabilities in real-world scenarios and reduces the cost of retraining. |
AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness (2025.acl-long)
Copied to clipboard
| Challenge: | Existing models that assess mLLMs on harmful meme understanding are inaccurate and lack accuracy. |
| Approach: | They propose a framework that adaptively probes the reasoning capabilities of mLLMs . their framework systematically reveals the varying performance of different target mllms a . |
| Outcome: | The proposed framework systematically reveals the performance of different target mLLMs. |
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)
Copied to clipboard
Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng
| Challenge: | Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity. |
| Approach: | They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging. |
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning (2021.acl-long)
Copied to clipboard
| Challenge: | Existing vision-language pre-training methods use a two-step training procedure to learn visual features from image-text pairs. |
| Approach: | They propose a vision-language pre-trained model for V+L understanding and generation using a unified Transformer framework. |
| Outcome: | The proposed model can learn visual representation and semantic alignments between image and text on visual-text pairs and on visual processing tasks. |
A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)
Copied to clipboard
Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin
| Challenge: | Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities. |
| Approach: | They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning. |
| Outcome: | The proposed model achieves superior performance and strong practical value in an industrial search engine. |
Reasoning-Guided Exploration for Online DPO (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work has aimed to enhance reasoning capabilities of language models, but these methods are limited to domains with objectively verifiable answers. |
| Approach: | They propose a self-play framework to improve reasoning on general-domain data. |
| Outcome: | Experiments show that the proposed framework improves reasoning performance on general-domain data while maintaining competitive performance on verifiable academic benchmarks. |
Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating concepts from different perspectives lack a unified formalization. |
| Approach: | They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks. |
| Outcome: | Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures. |
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning (D19-1)
Copied to clipboard
| Challenge: | Existing studies on video captioning focus on the association relationships between multiple modalities. |
| Approach: | They propose a video captioning model with high-order cross-modal attention (HOCA) they propose low-rank HOCA which adopts tensor decomposition to reduce the space requirement . |
| Outcome: | The proposed model captures cross-modal interaction of different modalities and reduces space requirement. |
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)
Copied to clipboard
Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie, Junda Wu, Xintong Li, Ryan Aponte, Hanjia Lyu, Joe Barrow, Hongjie Chen, Franck Dernoncourt, Branislav Kveton, Tong Yu, Ruiyi Zhang, Jiuxiang Gu, Nesreen K. Ahmed, Yu Wang, Xiang Chen, Hanieh Deilamsalehy, Sungchul Kim, Zhengmian Hu, Yue Zhao, Nedim Lipka, Seunghyun Yoon, Ting-Hao Kenneth Huang, Zichao Wang, Puneet Mathur, Soumyabrata Pal, Koyel Mukherjee, Zhehao Zhang, Namyong Park, Thien Huu Nguyen, Jiebo Luo, Ryan A. Rossi, Julian McAuley
| Challenge: | Large Language Models (LLMs) have been used for selection and training of data for active learning. |
| Approach: | They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop. |
| Outcome: | The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances. |
A Survey of RAG-Reasoning Systems in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Weizhi Zhang, Yuyao Yang, Wei-Chieh Huang, Yaozu Wu, Junyu Luo, Yuanchen Bei, Henry Peng Zou, Xiao Luo, Yusheng Zhao, Chunkit Chan, Yankai Chen, Zhongfen Deng, Yinghui Li, Hai-Tao Zheng, Dongyuan Li, Renhe Jiang, Ming Zhang, Yangqiu Song, Philip S. Yu
| Challenge: | a survey of RAG-based reasoning-based approaches shows that it is not effective for multi-step inferences. |
| Approach: | They map how advanced reasoning optimizes each stage of RAG . they show how retrieved knowledge supply missing premises and expand context for complex inference . |
| Outcome: | The proposed frameworks achieve state-of-the-art across knowledge-intensive benchmarks. |
Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-lingual sequence labeling require bilingual resources and require linguistic knowledge. |
| Approach: | They propose a multilingual language model with deep semantic Alignment to generate language-independent representations for cross-lingual sequence labeling. |
| Outcome: | The proposed model achieves state-of-the-art NER and POS performance across European languages and on distant language pairs such as English and Chinese. |
Planning-Guided Tutoring with Assessment-Driven Memory for Pedagogical LLM Tutors (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to simulate tutor behaviors or preferences fail to sustain high-quality pedagogical conversations that provide explicit stepwise scaffolding and adapt to learners’ evolving cognitive states. |
| Approach: | They propose a planning-guided tutoring framework with an assessment-driven memory for multi-turn math dialogue tutoring. |
| Outcome: | Experiments on multi-turn math tutoring benchmarks show that ScaffoldLM significantly improves pedagogical tutoring quality over strong baselines. |
How to Contextualize Empirical Data for Risk Analysis with LLMs: A Case Study of Power Outages (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly being considered for high-stakes decision-making, yet their application in statistical risk analysis remains largely underexplored. |
| Approach: | They propose a method for extracting key information from raw data and translating it into structured contextual input within the LLM prompt. |
| Outcome: | The proposed approach significantly improves the LLM’s performance in risk assessment tasks. |
A Copy-Augmented Generative Model for Open-Domain Question Answering (2022.acl-short)
Copied to clipboard
| Challenge: | Existing open-domain question answering approaches follow a two-stage paradigm retriever then reader. |
| Approach: | They propose a novel reader-based generative approach that incorporates extractive and generative readers. |
| Outcome: | The proposed model improves on two benchmark datasets, Natural Questions and TriviaQA. |
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex (2023.eacl-main)
Copied to clipboard
Terry Yue Zhuo, Zhuang Li, Yujin Huang, Fatemeh Shiri, Weiqing Wang, Gholamreza Haffari, Yuan-Fang Li
| Challenge: | Existing techniques for parsing natural-language utterances are vulnerable to adversarial attacks, requiring large amounts of labelled data and expensive human annotation. |
| Approach: | They propose to enhance the adversarial robustness of a prompt-based semantic parser based on a language model trained on code by constructing a set of demonstration examples. |
| Outcome: | The proposed method can be enhanced without significant amounts of labelled data or expensive human annotations on in-domain semantic parsing data. |
Social Bot-Aware Graph Neural Network for Early Rumor Detection (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models do not distinguish genuine users from social bots, and their failure in identifying rumors timely. |
| Approach: | They propose to account for social bots’ behavior and construct a Social Bot-Aware Graph Neural Network to model early propagation of posts and then use it to detect rumors. |
| Outcome: | The proposed method achieves significant improvements over baselines and identifies rumors within 3 hours while maintaining more than 90% accuracy. |
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)
Copied to clipboard
Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang
| Challenge: | Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation. |
| Approach: | They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward. |
| Outcome: | The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench. |
Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to ground large language models in external knowledge are limited by hallucinations and a lack of granular medical context. |
| Approach: | They propose a framework that replaces external retrieval with internal, key-based knowledge access by encoding clinical information directly into the model’s parameter space. |
| Outcome: | The proposed framework achieves state-of-the-art performance across four benchmark healthcare outcome prediction datasets. |
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)
Copied to clipboard
Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu
| Challenge: | Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios. |
| Approach: | They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity. |
| Outcome: | The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues. |
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for usergenerated text in Chinese. |
| Approach: | They propose a Chinese spell checker that leverages multimodal Chinese characters' information to predict the correct output. |
| Outcome: | The proposed model outperforms strong baselines on the SIGHAN benchmarks by a large margin. |
Context-aware Embedding for Targeted Aspect-based Sentiment Analysis (P19-1)
Copied to clipboard
| Challenge: | Existing methods do not specifically pre-train reasonable embeddings for targets and aspects in TABSA. |
| Approach: | They propose to refine the embeddings of targets and aspects using a sparse coefficient vector . this allows the embeds to be refined from highly correlative words instead of context-independent vectors . |
| Outcome: | Experiments show that the proposed method improves on two benchmark datasets. |
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking (2024.eacl-long)
Copied to clipboard
| Challenge: | Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates. |
| Approach: | They propose a framework to integrate Chinese geographic semantics into re-ranking pipelines. |
| Outcome: | The proposed framework improves on two Chinese benchmark datasets. |
A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks. |
| Approach: | They propose to decompose Chinese Spelling Check into detection, reasoning, and searching subtasks and to train a module that is compatible with existing CSC models. |
| Outcome: | The proposed module can be trained for one model and benefit other models. |
ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)
Copied to clipboard
Xianming Hu, Jingyang Chen, Bin Tang, Yihe Liu, Yihong Huang, Hongbo Zhao, Nuoyi Chen, Jie Zhang, Ping Li, Kai Zhang
| Challenge: | retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures . |
| Approach: | They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents. |
| Outcome: | The proposed method reduces offline indexing costs and accelerates retrieval. |
Which Sense Dominates Multisensory Semantic Understanding? A Brain Decoding Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Decoding semantic meanings from brain activity is open to multisensory stimulation, as word meanings can be delivered by both auditory and visual inputs. |
| Approach: | They aim to develop a computational model to probing what information from the act of language understanding is represented in human brain. |
| Outcome: | The proposed model dissociates multisensory integration of word understanding into written text, spoken text and image perception respectively, exploring the decoding efficiency and reliability of unisensory information in the brain representation. |
FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading (2025.findings-acl)
Copied to clipboard
Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie
| Challenge: | Large language models (LLMs) have impressive reasoning capabilities in financial tasks, but struggle with multi-step, goal-oriented scenarios in interactive financial markets. |
| Approach: | They propose a framework that integrates large language models with gradient-driven reinforcement learning (RL) policy optimization. |
| Outcome: | The proposed framework improves performance in trading and other financial domain tasks. |
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data. |
| Approach: | They propose a method that uses a dynamic graph to organize auxiliary languages in prompts to improve LRL translations. |
| Outcome: | The proposed method improves translation accuracy in low-resource languages (LRLs) using auxiliary language pairs and synthetic pseudo-parallel data. |
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models fail to generate singing voices rich in stylistic nuances for unseen singers due to multifaceted nature of singing styles. |
| Approach: | They propose a zero-shot SVS model for style transfer across cross-lingual speech and singing styles and multi-level style control. |
| Outcome: | Experimental results show that TCSinger outperforms baseline models in synthesis quality, singer similarity, and style controllability. |
On the Limit of Language Models as Planning Formalizers (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models can create plans that are neither executable nor verifiable in grounded environments. |
| Approach: | They use Large Language Models to generate a formal representation of the planning domain in some language, such as Planning Domain Definition Language (PDDL). |
| Outcome: | The proposed model outperforms the models directly generating plans while being robust to lexical perturbation. |
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)
Copied to clipboard
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang
| Challenge: | Simultaneous translation is notoriously dif- ficult due to word-order differences. |
| Approach: | They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model. |
| Outcome: | The proposed framework achieves low latency and reasonable qual- ity on 4 directions. |
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality (2025.emnlp-main)
Copied to clipboard
| Challenge: | Privacy-sensitive users require deploying large language models within their own infrastructure (on-premises) vulnerabilities in local environments can lead to unauthorized access and potential model theft. |
| Approach: | They propose a framework that secures a few bottom layers in a secure environment . they propose metric to optimize trade-off between protection and customization flexibility . |
| Outcome: | The proposed framework outperforms baselines on five models with 1.3B to 70B parameters. |
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)
Copied to clipboard
Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
| Challenge: | Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures. |
| Approach: | They propose a toolkit that supports pre-training models of different modalities. |
| Outcome: | The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks. |
KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs (2025.coling-main)
Copied to clipboard
Zelin Zhou, Simone Conia, Daniel Lee, Min Li, Shenglei Huang, Umar Farooq Minhas, Saloni Potdar, Henry Xiao, Yunyao Li
| Challenge: | Existing studies have shown that combining information from KGs in different languages aids knowledge Graph Completion and Knowledge Graph Enhancement. |
| Approach: | They propose a sequence-to-sequence framework that unifies tasks of textual and relational information completion for multilingual knowledge graphs. |
| Outcome: | The proposed framework unifies tasks of KGC and KGE into a single framework. |
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)
Copied to clipboard
Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li
| Challenge: | Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences. |
| Approach: | They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks. |
| Outcome: | The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge. |
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems. |
| Approach: | They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. |
| Outcome: | The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning. |
Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for OOD intent detection are limited to single dialogue turns. |
| Approach: | They propose a context-aware OOD intent detection framework to model multi-turn contexts in OOD context detection tasks using unlabeled data. |
| Outcome: | The proposed framework improves the F1-OOD score by 29% on multi-turn OOD detection tasks compared to the previous best method. |
The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for zero-shot video captioning focus on one key aspect of the scene and ignore the rest of the visual input. |
| Approach: | They propose a novel textual prompting strategy for zero-shot video captioning that uses a category-aware retrieval mechanism to promote prompt diversity while ensuring visual relevance. |
| Outcome: | The proposed method outperforms existing methods on in-domain and cross-domain settings. |
Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification (2020.coling-main)
Copied to clipboard
| Challenge: | inessential words are unintentionally misjudged as attention-worthy words and assigned heavier attention weights than should be. |
| Approach: | They propose a penalty-based method to regulate the attention learning process by integrating penalty coefficients into the computation of loss by means of overstability of attention weight distributions. |
| Outcome: | The proposed method improves on the Penn Discourse TreeBank corpus and is competitive compared to the state-of-the-art methods. |
MMDEND: Dendrite-Inspired Multi-Branch Multi-Compartment Parallel Spiking Neuron for Sequence Modeling (2025.acl-long)
Copied to clipboard
Kexin Wang, Yuhong Chou, Di Shang, Shijie Mei, Jiahong Zhang, Yanbin Huang, Man Yao, Bo Xu, Guoqi Li
| Challenge: | Vanilla spiking neurons are simplified from complex biological neurons with dendrites, soma, and synapses into single somatic compartments. |
| Approach: | They propose a multi-branch, multi-compartment parallel spiking dendritic neuron with a proportion-adjustable multi-branched structure that enables long-term temporal dependencies. |
| Outcome: | The proposed model achieves better long-sequence modeling capability with fewer parameters and lower energy consumption. |
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)
Copied to clipboard
Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang
| Challenge: | Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. |
| Approach: | AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. |
| Outcome: | Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% . |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma
| Challenge: | Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation. |
| Approach: | They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset. |
| Outcome: | The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations. |
Improving Question Generation with Multi-level Content Planning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies suggest key phrase selection is essential for question generation, yet it is difficult to connect disjointed phrases into meaningful questions, especially for long context. |
| Approach: | They propose a QG framework that uses multi-level content planning to generate questions from a given context and an answer. |
| Outcome: | The proposed framework outperforms baselines on two popular QG datasets. |
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang
| Challenge: | Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge. |
| Approach: | They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy. |
| Outcome: | The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities. |
SIFT: Grounding LLM Reasoning in Contexts via Stickers (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using a new approach, we can improve the pass@1 accuracy of LLM reasoning in large language models. |
| Approach: | They propose a method that leverages increasing inference-time compute to ground LLM reasoning in contexts. |
| Outcome: | The proposed approach improves pass@1 accuracy of DeepSeek-R1 on AIME2024 from 78.33% to **85.67%** and that on Aime2025 from 69.8% to **77.33%**. |
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel (2025.findings-acl)
Copied to clipboard
Yijiong Yu, Huiqiang Jiang, Xufang Luo, Qianhui Wu, Chin-Yew Lin, Dongsheng Li, Yuqing Yang, Yongfeng Huang, Lili Qiu
| Challenge: | Long-context language models exhibit position bias, also known as "lost in the middle" research shows that even long-contemporary LLMs fail to utilize all context information effectively . |
| Approach: | They propose a method to mitigate position bias by scaling positional hidden states . they propose to use a channel of hidden states to modify positional Hidden states a LCLM's positional bias . |
| Outcome: | The proposed method can improve performance by 15.2% in a "lost in the middle" benchmark. |
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang
| Challenge: | Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question . |
| Approach: | They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance . |
| Outcome: | The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered . |
Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains. |
| Approach: | They propose several strategies for deploying RAG that balance performance and efficiency. |
| Outcome: | The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy. |
Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)
Copied to clipboard
Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li
| Challenge: | Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints. |
| Approach: | They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream. |
| Outcome: | The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods. |
VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild (2024.acl-long)
Copied to clipboard
| Challenge: | VoiceCraft is a token-infilling neural codec language model for speech editing and zero-shot text-to-speech evaluation. |
| Approach: | They introduce a token infilling neural codec language model that performs on speech editing and zero-shot text-to-speech tasks. |
| Outcome: | The proposed model outperforms previous models on speech editing and zero-shot text-to-speech tasks. |
Context-aware Stand-alone Neural Spelling Correction (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. |
| Approach: | They propose a stand-alone spelling correction problem that corrects the spelling of tokens without additional token insertion or deletion. |
| Outcome: | The proposed solution outperforms the state-of-the-art spelling correction model by 12.8% absolute F0.5 score. |
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory. |
| Approach: | a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities . |
| Outcome: | Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory . |
IgSEG: Image-guided Story Ending Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing tasks such as story ending generation generate text-based story endings, but visual storytelling generates photo-streams-based stories. |
| Approach: | They propose a task called Image-guided Story Ending Generation (IgSEG) given a multi-sentence story plot and an ending-related image, they propose MGCL to solve these challenges. |
| Outcome: | The proposed model outperforms baselines on automatic and human evaluation. |
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models (2024.findings-acl)
Copied to clipboard
Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong
| Challenge: | Multimodal reasoning is a key capability for large vision-language models . however, the vanilla Chain-of-Thought method fails to address critical steps in multi-step reasoning tasks. |
| Approach: | They propose a bi-modal Behavioral Alignment method to augment multimodal reasoning . they use domain-specific language to integrate multimodal information into a precise alternative form . |
| Outcome: | The proposed method significantly improves GPT-4V(ision) on geometry problem solving, chess positional advantage prediction and molecular property prediction. |
Theory-optimal Quantization Based on Flatness (2026.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to quantization of Large Language Models (LLMs) have been widely adopted due to activation outliers, which degrade model performance especially at lower bit precision. |
| Approach: | They propose a new metric for quantization that strategically distributes outlier magnitudes across matrix dimensions via optimized diagonal operations. |
| Outcome: | The proposed framework achieves less than 1% accuracy drop in W4A4 quantization on the LLaMA-3-8B model and reduces the performance gap by 39.1% on the more challenging W2A4KV16 model. |
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis (2025.acl-long)
Copied to clipboard
Zhiliang Tian, Jingyuan Huang, Zejiang He, Zhen Huang, Menglong Lu, Linbo Qiao, Songzhu Mei, Yijie Wang, Dongsheng Li
| Challenge: | Existing methods for rumor detection on social media are limited by limited modeling capacity and insufficient training corpora. |
| Approach: | They propose an SFT-based rumor detection model with Influence guided Sample selection and Game-based multi-perspective analysis to address these issues. |
| Outcome: | The proposed model outperforms existing SOTA on three datasets. |
Uncertainty in Language Models: Assessment through Rank-Calibration (2024.emnlp-main)
Copied to clipboard
Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
| Challenge: | Language Models (LMs) have shown promising performance in natural language generation . however, it is crucial to correctly quantify their level of uncertainty in responding to inputs. |
| Approach: | They propose a framework to quantify uncertainty and confidence for Large Language Models . they use a Rank-calibration framework to measure uncertainty and confident responses . |
| Outcome: | The proposed framework assesses uncertainty and confidence measures for LMs. |
CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)
Copied to clipboard
Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin
| Challenge: | Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination. |
| Approach: | They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns. |
| Outcome: | The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages. |
Multi-Stage LLM Fine-Tuning with a Continual Learning Setting (2025.findings-naacl)
Copied to clipboard
Changhao Guan, Chao Huang, Hongliang Li, You Li, Ning Cheng, Zihe Liu, Yufeng Chen, Jinan Xu, Jian Liu
| Challenge: | Large language models (LLMs) have made significant progress in knowledge-intensive applications, but they may face a multi-stage continuous learning scenario. |
| Approach: | They propose a multi-stage continuous learning paradigm that includes a preference-based learning bias to identify potential knowledge conflicts and a self-distillation-based data augmentation strategy to expand and enrich the training corpus. |
| Outcome: | The proposed learning paradigm achieves a significant improvement in accuracy after 7 stages of fine-tuning compared to previous methods while preserving general knowledge. |
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent (2025.acl-long)
Copied to clipboard
Haohang Li, Yupeng Cao, Yangyang Yu, Shashidhar Reddy Javaji, Zhiyang Deng, Yueru He, Yuechen Jiang, Zining Zhu, K.p. Subbalakshmi, Jimin Huang, Lingfei Qian, Xueqing Peng, Jordan W. Suchow, Qianqian Xie
| Challenge: | Recent advances have underscored the potential of large language model (LLM)-based agents in financial decision-making. |
| Approach: | They propose to evaluate LLM agents using 13 different LLMs as backbone models across various market environments and tasks. |
| Outcome: | The proposed framework assesses the reasoning and decision-making capabilities of 13 different LLMs across various market environments and tasks. |
OntoED: Low-resource Event Detection with Ontology Embedding (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to ED rely on training instances and ignore correlation of event types. |
| Approach: | They propose a process of event ontology population linking event instances to pre-defined event types in event ontoology and ontological embedding to address these problems. |
| Outcome: | The proposed framework can be applied to new unseen event types by establishing linkages to existing ones. |
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)
Copied to clipboard
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu
| Challenge: | Existing slot filling models memorize inherent patterns of entities and contexts from training data. |
| Approach: | They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution . |
| Outcome: | The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts. |
ExpanRL: Hierarchical Reinforcement Learning for Course Concept Expansion in MOOCs (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for concept expansion in MOOCs are inefficient because of the diversity of MOOC courses and rapid updates. |
| Approach: | They propose an end-to-end hierarchical reinforcement learning (HRL) model for concept expansion in MOOCs that employs a two-level mechanism of seed selection and concept expansion. |
| Outcome: | The proposed model improves on nine real MOOC datasets and maintains competitive performance under different settings. |
ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reasoning-augmented systems that handle complex queries are lacking . we present a framework that enhances LLM-based recommendation assistants . |
| Approach: | They propose a reinforcement fine-tuning framework that enhances LLM-based recommendation . they use a dual-graph Enhanced Reward Shaping framework to integrate recommendation metrics . |
| Outcome: | The proposed framework outperforms state-of-the-art recommendations and preserves core abilities. |
MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction (2025.emnlp-industry)
Copied to clipboard
Peng Xing, Yinghui Li, Shirong Ma, Xinnian Liang, Haojing Huang, Yangning Li, Shu-Yu Guo, Hai-Tao Zheng, Wenhao Jiang, Ying Shen
| Challenge: | Chinese Spelling Correction (CSC) is a model that detects and corrects spelling errors in given sentences. |
| Approach: | They propose a model-agnostic model with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain rather than focusing solely on new domain knowledge. |
| Outcome: | The proposed model-agnostic framework is based on an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge. |
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (2026.acl-long)
Copied to clipboard
Rui Qian, Chuanhang Deng, Qiang Huang, Jian Xiong, Mingxuan Li, Yingbo Zhou, Wei Zhai, Jintao Chen, Dejing Dou
| Challenge: | Existing models rely on a single segmentation token whose hidden state implicitly encodes both semantic reasoning and spatial localization . Existing methods rely only on SEG>, which encodes semantic reasoning, limiting the model's ability to explicitly disentangle what to segment from where to segment. |
| Approach: | They propose a method which reformulates reasoning segmentation as a structured conditional generation process over image tokens conditioned on language grounded query banks. |
| Outcome: | The proposed model bridges token-level predictions and pixel-level supervision by decoupling spatial grounding from semantic reasoning through structured language grounded query banks. |
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)
Copied to clipboard
Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu
| Challenge: | Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning. |
| Approach: | They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
| Outcome: | The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
Aligning Translation-Specific Understanding to General Understanding in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language models (LLMs) have remarkable abilities in understanding complex texts . however, understanding misalignment leads to LLMs mistakenly translating complex concepts . |
| Approach: | They propose a translation process that aligns the translation-specific understanding with the general understanding to improve translation quality and reduce translation literalness. |
| Outcome: | The proposed translation process improves translation quality and reduces translation literalness by -25% -51%. |
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current LLMs are achieving better performance on various benchmarks, but their performance in practical applications does not always match their benchmark results. |
| Approach: | They propose to detect and rewrite leaked benchmarks without altering their difficulties by using Inference-Time Decontamination (ITD) to mitigate performance inflation caused by memorizing leaked samples. |
| Outcome: | The proposed method reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU. |
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems. |
| Approach: | They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction. |
| Outcome: | The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets. |
How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that In-Context Learning (ICA) can align Large Language Models (LLMs) with human preferences without requiring parameter adjustments. |
| Approach: | They investigate the effectiveness of each part in enabling ICA to function effectively and examine how variants in these parts impact alignment performance. |
| Outcome: | The proposed model can comprehend human instructions without parameter adjustments. |
PRAM: An End-to-end Prototype-based Representation Alignment Model for Zero-resource Cross-lingual Named Entity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to address the named entity recognition problem are limited and lack explicit optimization specific to the task. |
| Approach: | They propose a prototype-based representation alignment model for a cross-lingual named entity recognition task using labeled source language data. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods in some challenging scenarios. |
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang
| Challenge: | Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks. |
| Approach: | They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations. |
| Outcome: | The proposed pipeline can be used to study tool use under three scenarios. |
Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)
Copied to clipboard
Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu
| Challenge: | Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions. |
| Approach: | They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics. |
| Outcome: | The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively. |
EDDA: An Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing text or data are limited by lack of logical connections between generated texts and training data. |
| Approach: | They propose an encoder-decoder data augmentation framework that combines large language models and chain-of-thought prompting to summarize texts into target-specific if-then rationales, establishing logical relationships. |
| Outcome: | The proposed framework significantly improves over state-of-the-art methods on benchmark datasets while enabling interpretable rationale-based learning. |
Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)
Copied to clipboard
Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing LI, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Liefeng Bo
| Challenge: | Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. |
| Approach: | They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark. |
| Outcome: | The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness. |
Using Contextually Aligned Online Reviews to Measure LLMs’ Performance Disparities Across Language Varieties (2025.naacl-short)
Copied to clipboard
| Challenge: | Of the world's 7,000 languages, sixty (60) million people speak British English, 23 million speak Taiwan Mandarin, and 10 million speak European Portuguese. |
| Approach: | They propose a contextually aligned dataset that captures comments in different languages from real-world scenarios. |
| Outcome: | The proposed approach shows that large language models underperform in Taiwan Mandarin in a sentiment analysis task. |
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Evidence-Augmented Policy Optimization (EAPO) improves long-context reasoning performance . Xu et al., 2025): large language models are a critical part of NLP . |
| Approach: | They propose an Evidence-Augmented Reasoning paradigm that uses a group-relative reward to improve evidence quality. |
| Outcome: | EAPO significantly improves long-context reasoning performance compared to baselines. |
From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on correcting the output but overlook the ability of LLMs to detect and correct misleading content in the input itself. |
| Approach: | They propose a three-stage fine-tuning method that improves LLMs' ability to detect and correct misleading information in input queries. |
| Outcome: | The proposed method improves accuracy and factuality of LLM responses while also reducing hallucinations. |
Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)
Copied to clipboard
Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li
| Challenge: | Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization . |
| Approach: | They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume. |
| Outcome: | Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency. |
Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Mis- and disinformation online are a major source of harms of different kinds . out-of-context information is where different pieces of information are falsely associated . past studies have attempted to defend against OOC mis- and deinformation through external evidence, but they disregard the role of different pieces with different stances. |
| Approach: | They propose a stance extraction network that can extract stances of different pieces of evidence in a single framework. |
| Outcome: | The proposed model outperforms the state-of-the-art models on a public large-scale dataset with a performance gain of 3.2% in accuracy. |
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)
Copied to clipboard
Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang
| Challenge: | Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. |
| Approach: | They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants. |
| Outcome: | The proposed approach improves performance across benchmarks and representation space. |
Unified Language Representation for Question Answering over Text, Tables, and Images (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to answer complex questions are limited to text or structured data. |
| Approach: | They propose a paradigm that transforms images and tables into unified language representations to simplify QA problems. |
| Outcome: | The proposed framework outperforms existing methods on two datasets and the WebQA leaderboard. |
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)
Copied to clipboard
Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu
| Challenge: | In the evolving landscape of large language models, the predominant focus has been on English and Chinese. |
| Approach: | They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding. |
| Outcome: | The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks. |
Exploring and Adapting Chinese GPT to Pinyin Input Method (2022.acl-long)
Copied to clipboard
| Challenge: | a frozen GPT can generate state-of-the-art performance on perfect pinyin, but performance drops when input includes abbreviated pinyan, which links to even larger number of Chinese characters. |
| Approach: | They propose to use Chinese GPT to generate fluent sentences using abbreviated pinyin. |
| Outcome: | The proposed approach improves on abbreviated pinyin across all domains. |
MultiSQL: A Schema-Integrated Context-Dependent Text2SQL Dataset with Diverse SQL Operations (2024.findings-acl)
Copied to clipboard
| Challenge: | Text2SQL is a task that translates natural language into SQL statements. |
| Approach: | They propose a task that translates natural language into SQL statements. |
| Outcome: | The proposed task enables users to convert natural language into SQL statements. |
Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing Large Language Models suffer from "Reasoning Collapse" on mathematical reasoning tasks where stochastic sampling produces lexical variations of the same erroneous logic rather than genuine semantic exploration. |
| Approach: | They propose a geometric inference framework that uses a spectral orthogonal probe to introduce semantically heterogeneous reasoning signals into the teacher's orthogonale complement of its dominant subspace. |
| Outcome: | The proposed framework improves accuracy and sampling efficiency over baseline methods on logic and code generation benchmarks. |
Decoder Tuning: Efficient Language Understanding as Decoding (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to adapt pre-trained models with parameters frozen are based on input-side adaptation, which requires thousands of API queries. |
| Approach: | They propose to train a model-as-a-service (MaaS) setting to provide only the inference APIs for users . they argue that input-side adaptation could be arduous due to the lack of gradient signals . |
| Outcome: | The proposed model outperforms state-of-the-art algorithms with a 200x speed-up. |
Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Song translation requires both translation of lyrics and alignment of music notes . human translators of songs need to have a mastery of cultural traditions and the poetic usage of both source and target languages . |
| Approach: | They propose a model that can model lyric translation and lyrics-melody alignment . they use an encoder-decoder framework that can translate lyrics and determine number of aligned notes . |
| Outcome: | The proposed framework can translate lyrics and determine the number of aligned notes at each decoding step. |
PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit reasonable multilingual abilities, despite predominantly English-centric pretraining. |
| Approach: | They propose a framework that establishes multilingual alignment prior to language model pretraining and preserves this alignment using a code-switching strategy during pretraining. |
| Outcome: | Experiments in a synthetic English to English-Clone setting show that PreAlign outperforms standard multilingual joint training in language modeling, zero-shot cross-lingual transfer, and cross-linguistic knowledge application. |
Segment-Level and Category-Oriented Network for Knowledge-Based Referring Expression Comprehension (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods employ sentence-level retrieval and fusion methods, which may lead to similarity bias and interference from irrelevant information in unstructured knowledge sentences. |
| Approach: | They propose a segment-level and category-oriented network to solve similarity bias problem by segmenting and prompting knowledge retrieval methods and a category-based grounding method. |
| Outcome: | The proposed model eliminates similarity bias and improves the overall performance of the KB-REC task. |
Extracting Financial Events from Raw Texts via Matrix Chunking (2024.lrec-main)
Copied to clipboard
| Challenge: | Event Extraction (EE) is widely used in the Chinese financial field to provide valuable structured information. |
| Approach: | They propose a task which extracts financial events from raw texts and an efficient method called MACK. |
| Outcome: | The proposed method is fault-tolerant and can visualize interactions among text components. |
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)
Copied to clipboard
Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang
| Challenge: | Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information. |
| Approach: | They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format. |
| Outcome: | The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios (2025.findings-acl)
Copied to clipboard
JinYang Huang, Xiachong Feng, Qiguang Chen, Hanjie Zhao, Zihui Cheng, Jiesong Bai, Jingxuan Zhou, Min Li, Libo Qin
| Challenge: | MLDebugging is a benchmark designed to assess debugging challenges within multi-library Python code. |
| Approach: | They propose to introduce a benchmark to assess debugging challenges within multi-library Python code using 126 Python libraries. |
| Outcome: | The proposed benchmark covers 126 Python libraries and a wide range of multi-library code issues. |
A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Conventional knowledge Graph Reasoning models learn the embeddings of KG components over the structure of a KG. |
| Approach: | They propose a pipeline to integrate knowledge from LLMs into KGs without fine-tuning . they propose knowledge alignment, KG reasoning and entity reranking to enhance conventional models . |
| Outcome: | The proposed pipeline can enhance the performance of conventional KGR models in incomplete and general situations. |
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)
Copied to clipboard
Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance. |
| Approach: | They propose to use data diversity to measure instruction tuning of large language models. |
| Outcome: | The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning. |
Training Language Model to Critique for Better Refinement (2025.findings-acl)
Copied to clipboard
Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang
| Challenge: | Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. |
| Approach: | They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses. |
| Outcome: | The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes. |
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for Named Entity Recognition (NER) use a similarity metric to measure semantic similarity between test samples and referents, but their performance is limited due to the label scarcity. |
| Approach: | They propose a novel approach to learn a similarity metric for measuring the semantic similarity between test samples and referents, where each referent represents an entity class. |
| Outcome: | The proposed approach outperforms state-of-the-art models with a significant margin in most cases. |
VLSBench: Unveiling Visual Leakage in Multimodal Safety (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that textual unlearning does not achieve comparable safety performance with image-text alignment. |
| Approach: | They propose to use textual unlearning to align MLLMs with image-text pairs to explain this problem . they construct a visual leakless safety bench with 2.2k image- text pairs to test this problem. |
| Outcome: | The proposed model can refuse image-text pairs according to textual queries, leading to unreliable safety evaluations. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang
| Challenge: | Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). |
| Approach: | a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance. |
| Outcome: | a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models . |
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)
Copied to clipboard
Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan
| Challenge: | Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference. |
| Approach: | They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks. |
| Outcome: | The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities. |
Speculating LLMs’ Chinese Training Data Pollution from Their Tokens (2025.emnlp-main)
Copied to clipboard
Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu, Qi Li, Minlie Huang, Hewu Li, Han Qiu
| Challenge: | Experiments on GPT and other 23 LLMs indicate that tokens widely exist while GPT’s vocabulary behaves the worst: more than 23% long Chinese tokens (i.e., a token with more than two Chinese characters) are either porn or online gambling. |
| Approach: | They propose to locate Polluted Chinese (PoC) tokens in LLMs and build a PoC token detector to label them in vocabularies by considering each token’s semantics and related contents from the search engines. |
| Outcome: | The proposed method predicts that the ratio of “*” related webpages in GPT-4o's training data is around 0.5%. |
RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts. |
| Approach: | They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases. |
| Outcome: | The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions. |
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)
Copied to clipboard
Yixia Li, Yaqing Shi, Zhiwen Ruan, Dongdong Zhang, Lingjie Jiang, Shaohan Huang, Yun Chen, Guanhua Chen, Furu Wei
| Challenge: | Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision. |
| Approach: | They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone. |
| Outcome: | The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data. |
Analyzing the Intensity of Complaints on Social Media (2022.findings-naacl)
Copied to clipboard
| Challenge: | Prior studies on identifying the existence or the type of complaints focus on building automatic classification models for identifying complaints. |
| Approach: | They propose to measure the intensity of complaints from text using Best-Worst Scaling method to estimate the popularity of posts on social media. |
| Outcome: | The proposed model can estimate the popularity of complaints on social media with best-worst scaling (BWS) method. |
Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (2026.acl-long)
Copied to clipboard
| Challenge: | a contrastive learning approach for vision-language models is needed to capture compositional information. |
| Approach: | They propose a framework that masks compositional concepts in one modality and reconstructs them conditioned on full contextual information from the other . |
| Outcome: | The proposed framework enhances compositionality in visual language models and improves their ability to capture syntactic structure and linguistic information. |
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking (2025.acl-long)
Copied to clipboard
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun
| Challenge: | Existing studies in retrieval-augmented generation (RAG) do not sufficiently address the design of complex engineering solutions. |
| Approach: | They propose a retrieval-augmented generation system that leverages tree-based exploration and bi-point thinking mechanism to generate reliable solutions. |
| Outcome: | Experiments show that the proposed system achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications. |
Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction (2025.acl-industry)
Copied to clipboard
Yinghui Li, Shang Qin, Jingheng Ye, Haojing Huang, Yangning Li, Shu-Yu Guo, Libo Qin, Xuming Hu, Wenhao Jiang, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Recent studies have shown that Large Language Models’ performance as correctors on Chinese Grammatical Error Correction (CGEC) remains unsatisfactory due to the challenging nature of the task. |
| Approach: | They propose a training framework EXAM that uses LLMs as explainers to enhance CGEC small models and a novel evaluation method SEE that utilizes LLM as evaluators to bring more reasonable evaluations. |
| Outcome: | The proposed methods improve the performance of LLMs on Chinese Grammatical Error Correction (CGEC) task. |
Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models (2024.acl-long)
Copied to clipboard
Weihong Zhong, Xiaocheng Feng, Liang Zhao, Qiming Li, Lei Huang, Yuxuan Gu, Weitao Ma, Yuan Xu, Bing Qin
| Challenge: | Large Vision-Language Models (LVLMs) suffer from multimodal hallucinations . however, the generated hallucines could influence the models’ subsequent generation . |
| Approach: | They propose a framework to evaluate LVLMs' behaviors when encountering generated hallucinations and a method to revise the output distribution of LVLs with the one derived from the residual visual input. |
| Outcome: | The proposed framework reduces the performance of open-source LVLMs by 31%, indicating that they are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions. |
MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on unstructured retrieval or coarse abstractions, which lead to temporal conflicts, brittle reasoning, and limited traceability. |
| Approach: | They propose a unified memory framework that consolidates long-term agent experiences into three interconnected components that combine structured knowledge and evidence to construct compact yet information-dense contexts for reasoning. |
| Outcome: | The proposed framework significantly improves multi-hop and temporal reasoning accuracy while reducing input context length by over 95% compared to long-context baselines. |
Diagram-Driven Course Questions Generation (2025.emnlp-main)
Copied to clipboard
Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, Jun Liu
| Challenge: | Visual Question Generation (VQG) research focuses on natural images while neglecting diagrams, a critical component of educational materials. |
| Approach: | They propose a diagram-driven course questions generation task to generate diagram-relevant questions for specific courses. |
| Outcome: | The proposed framework outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets. |
Probing the Safety Robustness of LLMs in Latent Space (2026.acl-long)
Copied to clipboard
Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Xin Wang, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang
| Challenge: | Despite substantial progress in safety alignment techniques, aligned large language models can still produce unsafe responses under minor internal perturbations. |
| Approach: | They introduce Activation Steering Attack (ASA) and leverage the Negative Log-Likelihood (NLL) as a diagnostic signal to probe the local sensitivity of safety behaviors in latent space. |
| Outcome: | The proposed method is model-agnostic and supervision-free, enabling a general and reproducible diagnostic metric for analyzing safety robustness. |
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms for large language model (LLM) agents use memory construction and retrieval-augmented generation. |
| Approach: | They propose a framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization. |
| Outcome: | Experiments show that CoM outperforms baselines with accuracy gains of 7.5%–10.4% while reducing computational overhead to approximately 2.7% of token consumption and 6.0% of latency compared to complex memory architectures. |
MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints (2026.findings-acl)
Copied to clipboard
Kangyang Luo, Shuzheng Si, Yuzhuo Bai, Cheng Gao, Zhitong Wang, Cheng Huang, Yingli Shen, Yufeng Han, Wenhao Li, Cunliang Kong, Maosong Sun
| Challenge: | Existing supervised neural methods are underexplored for coreference resolution, especially in incremental clustering. |
| Approach: | They propose a dual-threshold incremental clustering approach based on a lightweight Transformer. |
| Outcome: | Experiments on common benchmarks show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints. |
SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)
Copied to clipboard
Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu
| Challenge: | Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios. |
| Approach: | They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage. |
| Outcome: | The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method. |
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)
Copied to clipboard
Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang, Hui Xue, Yongliang Shen, Weiming Lu, Yueting Zhuang
| Challenge: | Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon . |
| Approach: | They propose a routing-guided intervention method that enhances domain expert activation. |
| Outcome: | The proposed method achieves consistent improvements on visual reasoning tasks. |
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li
| Challenge: | Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams. |
| Approach: | They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids . |
| Outcome: | The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct . |
Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment (2023.acl-long)
Copied to clipboard
Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, Yongbin Li
| Challenge: | Existing speech-text pre-training methods are limited to one or two specific tasks, despite their success in speech-language processing tasks. |
| Approach: | They propose a temporal position prediction task to capture the speech-text alignment . they use a textual dialog pre-training task to generalize a response selection task . |
| Outcome: | The proposed model is superior in learning speech-text alignment and multi-turn dialog context. |
CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)
Copied to clipboard
Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu
| Challenge: | a recent study shows that large language models have limited generalization in low-resource languages like Chinese. |
| Approach: | They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private . |
| Outcome: | The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language. |
Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing relevance models rely on query-keyword pairs but keywords are usually short texts with scarce semantic information, which may not accurately reflect the underlying advertising purposes. |
| Approach: | They propose a bidding-graph augmented triple-based relevance model with three towers to deeply fuse the bidding graphs and semantic textual data. |
| Outcome: | The proposed model outperforms existing models on a large industry dataset and consistently outperformed existing models. |
Tensor Product Generation Networks for Deep NLP Modeling (N18-1)
Copied to clipboard
| Challenge: | Using Tensor Product Representations (TPRs) we propose a new architecture for natural language processing based on the principle that hypothesis space for learning includes network hypotheses that are independently known to be suitable for performing the target task. |
| Approach: | They propose a Tensor Product Generation Network (TPGN) which is capable of carrying out TPR computation but uses unconstrained deep learning to design its internal representations. |
| Outcome: | The proposed architecture outperforms baselines on the COCO dataset and can interpret internal representations and operations. |
Continual Learning for Multilingual Neural Machine Translation via Dual Importance-based Model Division (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods focus on preventing catastrophic forgetting by making compromises between the original and new language pairs, leading to sub-optimal performance on both translation tasks. |
| Approach: | They propose a dual importance-based model division method to divide the model parameters into two parts and separate the translation of the original and new tasks. |
| Outcome: | The proposed method outperforms strong baselines under different incremental translation scenarios. |
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu
| Challenge: | Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains. |
| Approach: | They propose a training framework that operationalizes this principle through coarse-to-fine budgeting. |
| Outcome: | Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines. |
Rethinking Document-level Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence . |
| Approach: | They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly . |
| Outcome: | The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages. |
Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance (2024.acl-long)
Copied to clipboard
Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Junqi Dai, Qinyuan Cheng, Xuanjing Huang, Xipeng Qiu
| Challenge: | Extensive experiments across various reasoning tasks demonstrate that UAG not only enhances the reasoning abilities of LLMs but consistently outperforms several strong baselines with minimal computational overhead. |
| Approach: | They propose an approach to guide LLMs onto an accurate and reliable trajectory by identifying and adjusting uncertainty signals within each step of the reasoning chain. |
| Outcome: | The proposed approach outperforms strong baselines and outperformed strong models with minimal computational overhead. |
Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Definition bias is a negative phenomenon that can mislead models. |
| Approach: | They propose a framework that measures definition bias, bias-aware fine-tuning and task-specific bias mitigation to mitigate definition bias in information extraction. |
| Outcome: | The proposed framework mitigates definition bias in information extraction tasks by measuring definition bias, bias-aware fine-tuning, and task-specific bias mitigation. |
DependEval: Benchmarking LLMs for Repository Dependency Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | a benchmark is designed to evaluate the repository-level dependency understanding of large language models (LLMs) based on 2683 repositories from real-world websites. |
| Approach: | They propose a benchmark to evaluate repository dependency understanding for large language models . DEPENDEVAL evaluates models on three core tasks across 8 programming languages . |
| Outcome: | The benchmark evaluates models on three core tasks across 8 programming languages from real-world repositories. |
IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models for fact extraction and verification fail to utilize multi-view contextual information. |
| Approach: | They propose to integrate multi-view contextual information (IMCI) for fact extraction and verification by combining contextual information with inter-document context. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the open-domain Wikipedia task with a winning FEVER score of 73.96% and label accuracy of 77.25% on the online blind test set. |
BCL: Bayesian In-Context Learning Framework for Information Extraction (2026.findings-acl)
Copied to clipboard
Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li
| Challenge: | Existing information extraction (IE) tasks rely on in-context learning with large language models. |
| Approach: | They propose a Bayesian-based in-context learning framework that refines label representations across IE tasks using particle filtering and Bayes updates. |
| Outcome: | The proposed framework improves performance over existing methods (up to 30%) it underperforms one-shot prompting by a substantial margin on NER tasks and CodeIE fails on RE tasks with near-zero micro-F1. |
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)
Copied to clipboard
Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu
| Challenge: | Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling. |
| Approach: | They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space. |
| Outcome: | The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks. |
Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)
Copied to clipboard
Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie
| Challenge: | Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores. |
| Approach: | They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs. |
| Outcome: | The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values. |
Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2025.findings-emnlp)
Copied to clipboard
Hao Zhang, Bo Huang, Zhenjia Li, Xi Xiao, Hui Yi Leong, Zumeng Zhang, Xinwei Long, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) is a promising approach to adapting LLMs to specialized tasks . existing rank allocation techniques remain computationally inefficient and unstable . |
| Approach: | They propose a low-rank adapted model that approximates model weight updates using low-ranked decomposition. |
| Outcome: | The proposed method is limited by its uniform rank allocation to each incremental matrix . it leverages the second-order derivatives of the loss function to capture weight sensitivity . |
AMA: Adaptive Memory via Multi-Agent Collaboration (2026.findings-acl)
Copied to clipboard
Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin
| Challenge: | Existing approaches to longterm memory rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. |
| Approach: | They propose a framework that leverages coordinated agents to manage memory across multiple granularities. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks while reducing token consumption by approximately 80%. |
Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to describe differences between two images are highly challenging due to distractors such as illumination and viewpoint changes. |
| Approach: | They propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors. |
| Outcome: | The proposed method outperforms existing methods on CLEVR-Change, CLE VR-DC and Spot-the-Diff datasets and achieves state-of-the art performance. |
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check (2021.acl-long)
Copied to clipboard
| Challenge: | False gram and phonological errors make Chinese spelling check difficult . a novel end-to-end trainable model outperforms existing methods . |
| Approach: | They propose a trainable Chinese spelling check model that integrates phonological and visual information into a pre-trained language model. |
| Outcome: | The proposed model outperforms existing state-of-the-art models on three benchmarks. |
Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)
Copied to clipboard
Jiawei Li, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, 林一冠 林一冠, Bin Xu, Ren Bowen, Chong Feng, Yang Gao, Heyan Huang
| Challenge: | Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications. |
| Approach: | They propose a reliable strategy for domains to choose more robust LLMs for real-world applications. |
| Outcome: | The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications. |
AlignSTS: Speech-to-Singing Conversion via Cross-Modal Alignment (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to speech-to-singing voice conversion are difficult to learn in text-free situations. |
| Approach: | They propose an STS model which views speech variance as different modalities . it uses a novel rhythm adaptor to predict the target rhythm representation . they also use the predicted rhythm representation to re-align the content . |
| Outcome: | The proposed model achieves superior performance in terms of objective and subjective metrics. |
Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models (2025.findings-naacl)
Copied to clipboard
Siyin Wang, Xingsong Ye, Qinyuan Cheng, Junwen Duan, Shimin Li, Jinlan Fu, Xipeng Qiu, Xuanjing Huang
| Challenge: | Recent studies focus on single-modality threats, but this approach fails to address cross-modal safety alignment. |
| Approach: | They propose a safety alignment challenge to evaluate cross-modality safety alignment . they propose 'Safe Inputs but Unsafe Output' to consider safety of single modalities . |
| Outcome: | The proposed safety alignment challenge examines cases where modalities are safe independently but could lead to unsafe outputs when combined. |
U-CORE: A Unified Deep Cluster-wise Contrastive Framework for Open Relation Extraction (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing methods for Relation Extraction (RE) are limited due to the overlap between predefined and undefined relations. |
| Approach: | They propose a unified framework for both Zero-shot and Unsupervised Relation Extraction tasks by leveraging techniques from Contrastive Learning and Clustering. |
| Outcome: | The proposed framework improves on three well-known datasets showing an average improvement of 7.35% ARI on Zero-shot ORE tasks and 15.24% ARI for Unsupervised ORE. |
Breaking Language Preference in Multilingual RAG via Language-Controllable Retrieval and Language-Agnostic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval accuracy and generation quality of large language models suffer from language preference. |
| Approach: | They propose a framework that explicitly disentangles multilingual RAG into language-controllable retrieval and language-agnostic reasoning. |
| Outcome: | Experimental results show that the proposed approach outperforms baselines across multilingual benchmarks. |
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences (2026.acl-long)
Copied to clipboard
Zizhen Li, Chuanhao Li, Yibin Wang, Jianwen Sun, Yukang Feng, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Yifei Huang, Kaipeng Zhang
| Challenge: | Recent advances in large language models have expanded the role of board games as creative co-designers . however, current systems lack the capacity to offer constructive critique grounded in the emergent user experience . |
| Approach: | They propose a large language model that internalizes persona-specific reasoning patterns to accurately simulate the subjective feedback of diverse player archetypes. |
| Outcome: | The proposed model outperforms commercial models in community alignment and critique quality. |
Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understanding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that our approach can significantly improve the parsing accuracy of all baseline models, leading to new state-of-the-art results. |
| Approach: | They propose a deep hierarchical syntax understanding approach to improve the cross-lingual semantic memory capability of large language models by implicitly aligning linguistic knowledge between source and target languages. |
| Outcome: | The proposed approach improves the cross-lingual semantic memory capability of large language models by combining implicit multi-task fine-tuning and explicit label bank guiding. |
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models (2021.acl-short)
Copied to clipboard
| Challenge: | Experimental results show that a sequence-to-sequence learning framework with neural networks can be effective for Chinese Spelling Correction (CSC) |
| Approach: | They propose a sequence-to-sequence learning framework with neural networks that generates more valuable training instances and adds task-specific examples to enhance the model. |
| Outcome: | The proposed method improves generalization and robustness of multiple CSC models across three datasets. |
GroundingGPT: Language Enhanced Multi-modal Grounding Model (2024.acl-long)
Copied to clipboard
Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, YiQing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Vu Tu, Zhida Huang, Tao Wang
| Challenge: | Existing multi-modal large language models focus on capturing global information while neglecting the fine-grained local information in multimodal inputs. |
| Approach: | They propose an end-to-end language enhanced multi-modal grounding model that performs fine-grained grounding tasks for image, video and audio. |
| Outcome: | The proposed model achieves impressive fine-grained understanding of multi-modal inputs while maintaining or improving its global comprehension capabilities. |
LongMP-Bench: A Benchmark for Multimodal Persona Understanding in Long-Term Dialogues (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets suffer from limited persona diversity and static, overly simplified settings, making them insufficient for capturing the complexity of real-world interactions. |
| Approach: | They propose a benchmark to evaluate models' ability to understand evolving user personas within long-term multimodal dialogues by using a dataset that contains long conversations from 150 users. |
| Outcome: | The proposed benchmark aims to assess models' ability to track persona evolution, integrate visual and textual inputs, and apply persona understanding in realistic dialogue scenarios. |
Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021.acl-short)
Copied to clipboard
| Challenge: | Recent work focuses on question answering based on machine reading comprehension . current approaches treat QA as extracting a consecutive piece of text to a given question. |
| Approach: | They propose a generative QA model that incorporates an extractive mechanism into a model. |
| Outcome: | The proposed model improves quality and semantic accuracy over baseline models. |
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)
Copied to clipboard
Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
| Challenge: | Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training . |
| Approach: | They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens. |
| Outcome: | The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates. |
Can LLMs be Good Graph Judge for Knowledge Graph Construction? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for converting unstructured text into structured Knowledge Graphs (KGs) have limitations such as large amount of noise, inaccurate knowledge, and hallucination . |
| Approach: | They propose a GraphJudge framework to reduce noise in real-world documents . they propose Graphjudge to fine-tune a LLM as a graph judge to enhance quality . |
| Outcome: | The proposed framework eliminates noise in real-world documents and improves the quality of generated KGs. |
Lifelong Knowledge Editing for LLMs with Retrieval-Augmented Continuous Prompt Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to correct outdated or erroneous knowledge in large language models (LLMs) are slow and cumbersome, resulting in catastrophic knowledge forgetting and degradation of model performance. |
| Approach: | They propose a RetriEval-augmented ContInuous Prompt lEarning method that converts knowledge statements into short and informative continuous prompts, prefixed to the LLM’s input query embedding. |
| Outcome: | The proposed method improves the performance of large language models (LLMs) while maintaining the overall performance of the model. |
Measuring Meaning Composition in the Human Brain with Composition Scores from Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing computational metric to quantify extent of meaning composition is lacking . despite extensive neurolinguistic research, understanding how meaning is constructed is difficult . |
| Approach: | They propose a computational metric to quantify the degree of meaning composition . they use key-value memory interpretation of transformer feed-forward network blocks to study meaning composition. |
| Outcome: | Experimental results show that the metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting multifaceted nature of meaning composition during human sentence comprehension. |
CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent techniques such as Generation-Augmented Retrieval (GAR) and Generative Document Retrieleval (GDR) leverage LLMs to enhance retrieval performance but face key challenges: GAR’s generated content may not always align with the target document corpus, while GDR limits the generative capacity of LLM. |
| Approach: | They propose a Context-Aware Generation-Augmented Retrieval approach which integrates corpus information into their generation process. |
| Outcome: | Experimental results show that CA-GAR outperforms existing methods on seven tasks and four non-English languages. |
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored. |
| Approach: | They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction. |
| Outcome: | The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios. |
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Sentence embedding is essential for many NLP tasks, but reliance on manual labels limits scalability. |
| Approach: | They propose a method for controlling the generation direction of large language models in the latent space by integrating ranking information and semantic information. |
| Outcome: | The proposed method achieves new SOTA performance with a modest cost in ranking sentence synthesis. |
VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . advanced proprietary models show promise, but struggle with increasing task complexity . |
| Approach: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to enhance output quality. |
| Outcome: | VisualEDU is a benchmark to evaluate VLMs' ability to produce coherent video from text . it integrates meta-prompt learning, visual and code feedback, and a drawing toolkit to improve output quality. |
Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing methods to translate spoken utterances from one language to another are unable to preserve speaker timbre of source speech. |
| Approach: | They propose a pipeline with style-transfer capability on the basis of self-supervised speech representations and codec units. |
| Outcome: | The proposed model achieves zero-shot cross-lingual style transfer on previously unseen source languages. |
An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Multi-aspect controllable text generation has attracted increasing attention . but the mutual interference of multiple prefixes limits its extensibility to training-time unseen combinations. |
| Approach: | They propose to use trainable gates to normalize the intervention of prefixes to restrain the interference. |
| Outcome: | The proposed approach outperforms baselines on constraint accuracy, text quality, and extensibility. |
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application. |
| Approach: | They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model. |
| Outcome: | The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity. |
Specialization through Collaboration: Understanding Expert Interaction in Mixture-of-Expert Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based large language models are popular for multitasking . however, whether each expert can specialize to a task remains unclear . |
| Approach: | They propose to use a dictionary learning approach to analyze expert collaboration mechanisms in MoE LLMs. |
| Outcome: | The proposed model outperforms existing methods by 2.5% while enabling 50% expert reduction. |
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering (2025.acl-long)
Copied to clipboard
Ruisheng Cao, Hanchong Zhang, Tiancheng Huang, Zhangyi Kang, Yuxin Zhang, Liangtai Sun, Hanqi Li, Yuxun Miao, Shuai Fan, Lu Chen, Kai Yu
| Challenge: | Existing approaches to retrieval augmented generation neglect PDF structure and layout . individual PDFs often exceed prompt limits and user queries may span multiple documents. |
| Approach: | They propose a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. |
| Outcome: | The proposed framework organizes semi-structured PDF content into relational database and vectorstore . it defeats both RAG and structured baselines on three PDF-based QA datasets . |
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu
| Challenge: | Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos . |
| Approach: | They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. |
| Outcome: | The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss. |
SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (2022.coling-1)
Copied to clipboard
Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li
| Challenge: | Existing methods that learn from multiple semantically-equivalent questions are limited to one-to-one mapping . |
| Approach: | They propose a constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions and learn robust feature representations with reduced spurious associations. |
| Outcome: | The proposed method outperforms strong competitors and achieves state-of-the-art results on five benchmark datasets. |
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts (2023.acl-long)
Copied to clipboard
| Challenge: | Existing research on multi-modal dialogue pre-training is limited due to limited availability of multi-dimensional data . a recent emergence of chatGPT 1 has increased confidence in the potential for this goal . |
| Approach: | They propose a framework for multi-modal dialogue pre-training that integrates experts to accommodate multi-faceted tasks. |
| Outcome: | The proposed framework achieves state-of-the-art on eight multi-modal dialog benchmarks. |
A Structure-Aware Argument Encoder for Literature Discourse Analysis (2022.coling-1)
Copied to clipboard
Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu
| Challenge: | Existing research for argument representation learning treats tokens in sentences equally and ignores the implied structure information of argumentative context. |
| Approach: | They propose to separate tokens into two groups to capture structural information of arguments and to incorporate paragraph-level position information into the model. |
| Outcome: | The proposed model captures structural information of arguments and is able to identify arguments automatically. |
CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain? (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multimodal large language models cannot generate executable procedures . authors propose a new benchmark to assess procedural competence in multimodal models . |
| Approach: | They propose a new benchmark to assess procedural competence in multimodal large language models . they use a CrochetPARADE DSL representation to enable structural validation and functional evaluation . |
| Outcome: | The proposed model enables structural validation and functional evaluation via execution. |
Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to aspect-level sentiment classification focus on modeling the relationship between aspect words and their contexts with attention, and ignore the use of elaborate knowledge implicit in the context. |
| Approach: | They exploit syntactic awareness to the model by the graph attention network on the dependency tree structure and external pre-training knowledge by BERT language model, which helps to model the interaction between the context and aspect words better. |
| Outcome: | The proposed model can model the interaction between the context and aspect words better by using syntactic awareness and external pre-training knowledge. |
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to attack Large Language Model (LLM) tool-learning systems are black-box oriented and rely on static commands that cannot adapt flexibly to the changes in user queries and the invocation chain. |
| Approach: | They propose a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems that mimics the familiar by inferring the information utilized by upstream tools. |
| Outcome: | The proposed approach outperforms baselines with +13.2% ASRTheft and can be generalized to new tool-learning systems to expose their information leakage risks. |
SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) struggle with complex semantic and structural correctness required for automated code repair. |
| Approach: | They propose a hybrid neural-symbolic framework that unifies code synthesis with compiler-informed symbolic feedback to improve LLM-based vulnerability repair. |
| Outcome: | The proposed framework improves code repair accuracy and efficiency over strong SFT and RFT training strategies on the FixJS and CodeFlaws benchmarks. |
AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)
Copied to clipboard
Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Guozhi Wang, Dingyu Zhang, Shuai Ren, Hongsheng Li
| Challenge: | a new dataset is being developed to improve the capabilities of mobile GUI-control agents. |
| Approach: | They propose a dataset designed for generalist mobile GUI-control agents . they use screenshots from popular mobile applications to create a detailed GUI-annotated dataset . |
| Outcome: | The Android Multi-annotation EXpo (AMEX) is a large-scale dataset for generalist mobile GUI-control agents . it includes screenshots from popular mobile applications, which are annotated at multiple levels . |
ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent Large Language Models (LLMs) have demonstrated remarkable performance in document reranking tasks. |
| Approach: | They propose a two-stage training approach for document reranking using reinforcement learning and fine-grained score learning. |
| Outcome: | The proposed approach outperforms open-source and proprietary reranking models on BEIR benchmark. |
Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang, Shuo Wang, Hongliang Li, Xu Jinan, Meng Jiang, Jian-Yun Nie, Kaiyu Huang
| Challenge: | Existing approaches to multilingual retrieval-augmented generation (MRAG) use a single-turn retrieval and subsequent optimization to acquire and integrate beneficial external knowledge from multilingual collections. |
| Approach: | They propose a multilingual search-augmented reinforcement learning framework that integrates a language-coupled Group Relative Policy Optimization into the policy and reward models. |
| Outcome: | The proposed framework achieves competitive performance and is appropriate for various practical scenarios such as constrained training data and retrieval over collections encompassing a large number of languages. |
Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak attacks fail against reasoning models enhanced by Chain-of-Thought (CoT) reasoning. |
| Approach: | They propose a jailbreak method that uses Chain-of-Thought reasoning to reduce harmfulness from jailbreaking. |
| Outcome: | The proposed jailbreak method performs well against open AI models and deepseek-R1 reasoning models. |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)
Copied to clipboard
Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu
| Challenge: | Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios . |
| Approach: | They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios. |
| Outcome: | The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm. |
HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)
Copied to clipboard
Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu
| Challenge: | Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers. |
| Approach: | They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters . |
| Outcome: | The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork. |
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) enabled dialogue systems are one of the central modes in human-machine interaction. |
| Approach: | They propose a benchmark task for dialogue element MOdeling and Element Awareness and a new benchmark for dialogue agent interaction that allows the agent to model dialogue elements via imitation learning. |
| Outcome: | The proposed agent performs well in both dialogue element modeling and out-of-domain tasks. |
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning . |
| Approach: | a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path . |
| Outcome: | Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness. |
EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)
Copied to clipboard
Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang
| Challenge: | Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios. |
| Approach: | They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts. |
| Outcome: | The proposed model performs comparable to state-of-the-art large models on the test set. |
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)
Copied to clipboard
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu
| Challenge: | Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models. |
| Approach: | They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. |
| Outcome: | Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. |
ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images. |
| Approach: | They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models. |
| Outcome: | The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts. |
EvolveSearch: An Iterative Self-Evolving Search Agent (2025.emnlp-main)
Copied to clipboard
Ding-Chu Zhang, Yida Zhao, Jialong Wu, Liwen Zhang, Baixuan Li, Wenbiao Yin, Yong Jiang, Yu-Feng Li, Kewei Tu, Pengjun Xie, Fei Huang
| Challenge: | Existing approaches to enabling LLM web search proficiency struggle with data production in open-search domains, while supervised fine-tuning struggles with data utilization efficiency. |
| Approach: | They propose an iterative self-evolution framework that combines SFT and RL to enhance agentic web search capabilities without external human-annotated reasoning data. |
| Outcome: | EvolveSearch achieves 4.7% improvement over current state-of-the-art in seven benchmarks . supervised fine-tuning struggles with data production in open-search domains compared with RL . |
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) LLMs achieve higher performance with fewer active parameters, but are still difficult to deploy due to their immense parameter sizes. |
| Approach: | They propose expert-level sparsification techniques to enhance the deployment efficiency of large language models by introducing plug-and-play expert pruning and skipping techniques. |
| Outcome: | The proposed methods reduce model sizes and increase inference speed while maintaining satisfactory performance across a wide range of tasks. |
Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to target sentiment analysis are limited by huge search space and sentiment inconsistency. |
| Approach: | They propose a span-based extract-then-classify framework to detect opinion targets . they propose pipeline, joint, and collapsed models to classify polarities . |
| Outcome: | The proposed framework outperforms the sequence tagging baseline on three benchmark datasets. |
Data Augmentation for Text Generation Without Any Augmented Data (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for data augmentation need to define or choose proper data mapping functions to create augmented samples. |
| Approach: | They propose to use data mapping functions to augment text samples without using specific mapping functions. |
| Outcome: | The proposed approach can approximate or even surpass popular data augmentation methods on two text generation tasks with a convergence rate guarantee. |
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use (2024.acl-long)
Copied to clipboard
| Challenge: | In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models significantly affects their performance in tasks demanding a high degree of context awareness. |
| Approach: | They propose a method that compensates an attention trough with an attention peak by a process to enhance the model's awareness to various contextual positions. |
| Outcome: | The proposed method improves the performance of a 7B model on the largest tool-use benchmark, comparable to that of GPT-4. |
Domain Incremental Lifelong Learning in an Open World (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to lifelong learning (LL) models require access to task identities in the testing phase or cannot handle samples from unseen tasks. |
| Approach: | They propose a dynamic architecture-based lifelong learning model that tries to learn a sequence of tasks with a prompt-enhanced language model. |
| Outcome: | The proposed model outperforms state-of-the-art models in handling unseen tasks and focuses on task-level prompts to capture knowledge from different granularities. |
Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)
Copied to clipboard
Zhiyuan Zeng, Qipeng Guo, Xiaoran Liu, Zhangyue Yin, Wentao Shu, Mianqiu Huang, Bo Wang, Yunhua Zhou, Linlin Li, Qun Liu, Xipeng Qiu
| Challenge: | Existing methods to optimize LLM for long sequences for long documents are slow and consume memory. |
| Approach: | They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size . |
| Outcome: | The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory. |
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)
Copied to clipboard
| Challenge: | End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it. |
| Approach: | They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency . |
| Outcome: | The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks. |
Don’t Corrupt the Fact: A Trustworthy RAG Watermarking Framework based on Dual Factual Shield (2026.acl-long)
Copied to clipboard
| Challenge: | Existing watermarking methods are fact-agnostic and cause "faithfulness hallucinations" a novel framework to enforce knowledge loyalty is proposed to improve watermarks . |
| Approach: | They propose a new framework that enforces knowledge loyalty by spoofing terms from retrieved contexts and prompt-based semantic guidance to protect against factual corruption. |
| Outcome: | The proposed framework reduces the Knowledge Corruption Rate while maintaining its original high security and robustness. |
Exploring Representation-level Augmentation for Code Search (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent data augmentations for code search are at the raw-data level, which requires additional code analysis and training cost. |
| Approach: | They propose a general format of representation-level augmentation that unifies existing methods. |
| Outcome: | The proposed methods can boost the performance of code search models on a large-scale dataset. |
Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing context window extension methods obstruct scaling external knowledge input. |
| Approach: | They develop a multi-agent framework to overcome two core bottlenecks in existing agent orchestration designs. |
| Outcome: | The proposed framework overcomes two core bottlenecks and improves inference-time knowledge integration without longer-context training. |
MetaASSIST: Robust Dialogue State Tracking with Meta Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing dialogue datasets contain lots of noise in their state annotations. |
| Approach: | They propose a framework to train robust dialogue state tracking models by combining pseudo and vanilla labels by a common weighting parameter. |
| Outcome: | The proposed framework achieves state-of-the-art accuracy of 80.10% on multiWOZ 2.4. |
Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for aligning small language models with human values model preference knowledge from large language models (LLMs) however, this limitation hinders student SLMs from capturing nuanced preferences for multiple responses. |
| Approach: | They propose a framework which models teacher's preference knowledge as a probability distribution over all potential preferences, thereby providing more nuanced supervisory signals. |
| Outcome: | The proposed framework outperforms existing methods on four benchmark tasks and achieves 20% improvement on AlpacaEval 2 and Arena-Hard. |
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)
Copied to clipboard
Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, Bo Zheng
| Challenge: | Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences. |
| Approach: | They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects. |
| Outcome: | The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives. |
Long-Tailed Question Answering in an Open World (2023.acl-long)
Copied to clipboard
| Challenge: | Existing QA approaches require access to seen tasks or do not explicitly model samples from unseen tasks. |
| Approach: | They propose an open-tailed QA model that encourages knowledge sharing between head, tail and unseen tasks and explicitly mines knowledge from a large pre-trained language model. |
| Outcome: | The proposed model outperforms the state-of-the-art on a large-scale dataset. |
Fingerprinting LLMs via Prompt Injection (2026.acl-long)
Copied to clipboard
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Zhenqiang Gong
| Challenge: | Existing provenance detection methods for large language models are infeasible for already published models and compare outputs using hand-crafted or random prompts. |
| Approach: | They propose a detection framework that constructs fingerprints by exploiting LLMs’ inherent vulnerability to prompt injection. |
| Outcome: | The proposed framework achieves high true positive rates while keeping false positive rates near zero. |
Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for ECI rely on causal features and external knowledge, but these methods fail in two dimensions: causal features between events in texts often lack explicit clues and external information may introduce bias. |
| Approach: | They propose a simple and effective Semantic Dependency Inquiry Network for ECI that captures semantic dependencies within the context using a unified encoder and generates a fill-in token based on comprehensive context understanding. |
| Outcome: | Extensive experiments show that SemDI surpasses state-of-the-art methods on three widely used benchmarks. |
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026.acl-long)
Copied to clipboard
Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang
| Challenge: | Existing approaches to formalizing mathematical statements face limitations in accuracy, especially in the context of complex, highlevel problems that involve sophisticated mathematical reasoning. |
| Approach: | They propose a CriticLean framework that elevates the role of the critic from a passive validator to an active learning component and introduce a benchmark to measure models’ ability to distinguish semantically correct from incorrect formalizations. |
| Outcome: | The proposed framework outperforms open- and closed-source benchmarks and shows that it significantly outperformed existing models. |
DocBank: A Benchmark Dataset for Document Layout Analysis (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches for document layout analysis are based on rule-based or machine learning methods that ignore textual information. |
| Approach: | They present a benchmark document layout analysis dataset using a computer vision model . they build strong baselines and manually split train/dev/test sets for evaluation . |
| Outcome: | The proposed model trains on DocBank accurately recognize layout information for a variety of documents. |
StructFact: Reasoning Factual Knowledge from Structured Data with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have made significant strides in natural language processing by leveraging their ability to comprehend and reason with factual knowledge. |
| Approach: | They propose a benchmark to evaluate the ability of large language models to reason with structured data for knowledge-intensive tasks. |
| Outcome: | Extensive tests on 10 common LLMs show that they struggle with heterogeneity of structured data during reasoning. |
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup (2021.emnlp-main)
Copied to clipboard
| Challenge: | Experiments on five text classification benchmarks and five backbone models have shown that our methods reduce the error rate over Mixup variants in a significant margin (up to 31.3%), especially in low-resource conditions (upto 17.5%). |
| Approach: | They propose to add a small adversarial perturbation to the mixing coefficients rather than the examples to relax locally linear constraints. |
| Outcome: | Experiments on five text classification benchmarks and five backbone models show that the proposed methods reduce the error rate over Mixup variants by 31.3%, especially in low-resource conditions. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
Weight Perturbation as Defense against Adversarial Word Substitutions (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existence and pervasiveness of textual adversarial examples have raised serious concerns to security-critical applications. |
| Approach: | They propose to perform weight perturbations in the parameter space rather than the input feature space to improve adversarial robustness of NLP models. |
| Outcome: | The proposed method improves adversarial robustness of models by performing weight perturbations in the parameter space rather than the input feature space. |
Training Language Models to Critique With Multi-agent Feedback (2025.findings-emnlp)
Copied to clipboard
Tian Lan, Wenwei Zhang, Chengqi Lyu, Shuaibin Li, Chen Xu, Heyan Huang, Dahua Lin, Xian-Ling Mao, Kai Chen
| Challenge: | utilizing human annotations can enhance critique ability, but model-generated critiques suffer from inherent flaws due to complexity of critique . a new framework that leverages multi-agent feedback improves critique ability . |
| Approach: | They propose a framework that leverages multi-agent feedback to improve critique ability . they propose to use supervised fine-tuning and reinforcement learning to improve this capability . |
| Outcome: | The proposed framework improves critique ability in both supervised fine-tuning and reinforcement learning stages. |
A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)
Copied to clipboard
Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li
| Challenge: | Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps. |
| Approach: | They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement. |
| Outcome: | The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps. |
Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to integrating graph and language models face two key limitations: achieving robust semantic alignment and ensuring interpretability in outputs. |
| Approach: | They propose a framework to integrate graph and language modalities while enhancing transparency. |
| Outcome: | Extensive experiments on three benchmark datasets show that the proposed framework surpasses existing methods in efficiency and generates outputs that are significantly more interpretable. |
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives (2025.findings-acl)
Copied to clipboard
Zhihu Wang, Shiwan Zhao, Yu Wang, Heyuan Huang, Sitao Xie, Yubo Zhang, Jiaxin Shi, Zhixing Wang, Hongyan Li, Junchi Yan
| Challenge: | Existing approaches to solving complex tasks with large language models (LLMs) fail to decompose tasks accurately or execute subtasks effectively. |
| Approach: | They propose a Chain-of-Learning (CoL) paradigm that highlights task dependencies on specific capability items, further broken down into their constituent knowledge and skill components. |
| Outcome: | The proposed model improves Yi-1.5-9B and Llama3-Chinese-8B for legal tasks by 45.00% and 24.50% on different domains. |
MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction (2022.naacl-main)
Copied to clipboard
| Challenge: | Using a multi-reference multi-source evaluation dataset, Chinese grammatical error correction (CGEC) is relatively scarce. |
| Approach: | They propose a multi-reference multi-source evaluation dataset for Chinese grammar error correction . the dataset contains 7,063 sentences written by Chinese-as-a-Second-Language learners . |
| Outcome: | The proposed dataset can be used to evaluate Chinese grammar errors in Chinese. |
Demystifying Data Organization for Enhanced LLM Training (2026.acl-long)
Copied to clipboard
Yalun Dai, Yangyu Huang, Tongshen Yang, Yonghan Wang, Xin Zhang, Wenshan Wu, Qihao Zhao, Hao Li, Yuanyuan Gao, Kim-Hui Yap, Scarlett Li
| Challenge: | Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation. |
| Approach: | They propose to reuse pre-computed sample-level scores originally generated for data efficiency and introduce two new data ordering methods to improve LLM training. |
| Outcome: | The proposed methods improve the stability and performance of LLM training. |
Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). |
| Approach: | They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations. |
| Outcome: | The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts. |
One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)
Copied to clipboard
Weitao Ma, Xiyuan Du, Xiaocheng Feng, Lei Huang, Yichong Huang, Huiyi Zhang, Xiaoliang Yang, Baohang Li, Xiachong Feng, Ting Liu, Bing Qin
| Challenge: | Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations. |
| Approach: | They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness. |
| Outcome: | The proposed approach outperforms existing methods while achieving superior editing efficiency. |
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)
Copied to clipboard
Kaibo Liu, Zhenpeng Chen, Yiyang Liu, Jie M. Zhang, Mark Harman, Yudong Han, Yun Ma, Yihong Dong, Ge Li, Gang Huang
| Challenge: | TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites . |
| Approach: | They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs . |
| Outcome: | The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification . |
Moon IME: Neural-based Chinese Pinyin Aided Input Method with Customizable Association (P18-4)
Copied to clipboard
| Challenge: | a pinyin input method engine (IME) allows users to input Chinese into a computer by typing pinyan through the common keyboard. |
| Approach: | They present a pinyin IME that integrates neural machine translation and IR to offer amusive and customizable association ability. |
| Outcome: | The Moon IME integrates neural machine translation and IR to offer amusive association ability. |
EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning (2025.acl-long)
Copied to clipboard
Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang
| Challenge: | Existing methods for strategic reasoning face challenges in adaptability, scalability, and transferring strategies to new contexts. |
| Approach: | They propose an explicit policy optimization model that provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior. |
| Outcome: | The proposed model provides strategies in open-ended action space and can be plugged into arbitrary LLM agents to motivate goal-directed behavior. |
ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent controllable zero-shot text-to-speech systems can synthesize speech for unseen speakers from a short reference audio clip, but they also inherit the speaking style present in the reference. |
| Approach: | They propose a framework that enables continuous and reference-relative style control in zero-shot text-to-speech systems by combining style-specific LoRAs with Orthogonal LoRA Fusion. |
| Outcome: | The proposed framework reduces the model's dependence on reference style while preserving text fidelity while maintaining intelligibility and speaker timbre. |
Discrete Argument Representation Learning for Interactive Argument Pair Identification (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing research on monological argumentation covers claims generation, argument structure prediction, and essay scoring. |
| Approach: | They propose to identify argument pairs from two posts with opposite stances to a certain topic. |
| Outcome: | The proposed framework outperforms competing models on a large-scale dataset . it also proves that it is useful for analyzing argument pairs from two posts . |
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)
Copied to clipboard
Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao
| Challenge: | Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs . |
| Approach: | They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained . |
| Outcome: | The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency. |
On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models (2024.acl-short)
Copied to clipboard
Dongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, Jun Huang
| Challenge: | Existing RAG methods focus on improving the task performance, without fine-grained process of knowledge. |
| Approach: | They propose a method that detects long-tail knowledge in large language models by analyzing retrieved documents and enhancing queries indiscriminately with retrieved information. |
| Outcome: | The proposed method achieves over 4x speedup in average inference time and consistent performance improvement in downstream tasks compared to existing pipelines. |
Privacy Implications of Retrieval-Based Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | a study of retrieval-based language models shows improved interpretability, factuality, and adaptability compared to parametric counterparts . kNN-LMs are more susceptible to leaking private information from their private datastore than parametric models . |
| Approach: | They present the first study of privacy risks in retrieval-based language models . they aim to strike a balance between utility and privacy in domains where privacy is of concern . |
| Outcome: | The proposed methods improve interpretability, factuality, and adaptability compared to parametric models . the study finds that kNN-LMs are more susceptible to leaking private data than parametric ones . |
GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)
Copied to clipboard
Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun
| Challenge: | Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically. |
| Approach: | They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance. |
| Outcome: | The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models (2023.emnlp-demo)
Copied to clipboard
Chenliang Li, He Chen, Ming Yan, Weizhou Shen, Haiyang Xu, Zhikai Wu, Zhicheng Zhang, Wenmeng Zhou, Yingda Chen, Chen Cheng, Hongzhu Shi, Ji Zhang, Fei Huang, Jingren Zhou
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. |
| Approach: | They propose a framework that equips large language models with tool-use capabilities . they propose LLaMA and Chat-GLM as controllers, and a model-based agent framework . |
| Outcome: | The proposed framework equips open-source LLMs with tool-use capabilities . it provides a user-friendly system library with a customizable engine design . |
One-Shot Learning as Instruction Data Prospector for Large Language Models (2024.acl-long)
Copied to clipboard
Yunshui Li, Binyuan Hui, Xiaobo Xia, Jiaxi Yang, Min Yang, Lei Zhang, Shuzheng Si, Ling-Hao Chen, Junhao Liu, Tongliang Liu, Fei Huang, Yongbin Li
| Challenge: | Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality. |
| Approach: | They propose a method that leverages one-shot learning to discern and select high-quality instruction data from extensive datasets. |
| Outcome: | Nuggets outperforms existing methods on MT-Bench and Alpaca-Eval benchmarks. |
Simplify-Pro: A Two-level and Progressive LLM-based Framework for Auto Long Text Simplification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on lexical- and sentence-level simplification, leaving long text simplification comparatively unexplored . |
| Approach: | They propose a two-level and progressive LLM-based framework that establishes an effective paradigm for automatic long text simplification under diverse test scenarios. |
| Outcome: | The proposed framework outperforms advanced and proprietary LLMs in in-domain and out-of-domain simplification tasks and matches or outperformed existing LLM frameworks. |
Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation (2025.acl-long)
Copied to clipboard
Luyao Cheng, Hui Wang, Chong Deng, Siqi Zheng, Yafeng Chen, Rongjie Huang, Qinglin Zhang, Qian Chen, Xihao Li, Wen Wang
| Challenge: | Mainstream speaker diarization systems rely only on acoustic information, making it challenging in complex aural environments. |
| Approach: | They propose a multimodal approach that integrates audio, visual, and semantic cues to enhance speaker diarization. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on multi-party conversations . it integrates audio-visual-semantic cues into the clustering process for acoustic speaker embeddings . |
MindAgent: Emergent Gaming Interaction (2024.findings-naacl)
Copied to clipboard
Ran Gong, Qiuyuan Huang, Xiaojian Ma, Yusuke Noda, Zane Durante, Zilong Zheng, Demetri Terzopoulos, Li Fei-Fei, Jianfeng Gao, Hoi Vo
| Challenge: | Large foundation models (LFMs) can perform complex scheduling in a multi-agent system and can coordinate agents to complete complex tasks that require extensive collaboration. |
| Approach: | They propose a gaming-based infrastructure that evaluates LFMs' planning and coordination capabilities in the context of gaming interaction. |
| Outcome: | The proposed infrastructure can be deployed in a customized VR version of Cuisineworld and adapted in the “Minecraft” domain. |
OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Wenbo Li, Amirali Amini, Bo Sun, Yakov Bart, Weimin Lyu, Jiri Gesi, Tian Wang, Jing Huang, Yu Su, Upol Ehsan, Malihe Alikhani, Toby Jia-Jun Li, Lydia Chilton, Dakuo Wang
| Challenge: | evaluating LLMs' ability to mimic real user behavior remains an open challenge due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual user. |
| Approach: | They propose a dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. |
| Outcome: | The proposed dataset is the first to evaluate how well current LLMs can accurately simulate the next web action of a specific user. |
The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Sparse attention is a promising strategy to extend long-context capabilities in LLMs . but its efficiency–accuracy trade-offs remain unclear due to the lack of comprehensive evaluation . |
| Approach: | They evaluate sparse attention methods across multiple model families and sizes . they find larger sparser models outperform smaller dense ones at equivalent cost . |
| Outcome: | The proposed methods outperform smaller sparse models at equivalent cost and improve the Pareto frontier. |
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation (2025.acl-long)
Copied to clipboard
Wei Li, Xin Zhang, Zhongxin Guo, Shaoguang Mao, Wen Luo, Guangyue Peng, Yangyu Huang, Houfeng Wang, Scarlett Li
| Challenge: | Existing benchmarks focus on standalone programming problems, such as HumanEval, MBPP, and LiveCodeBench. |
| Approach: | They propose to use large language models to evaluate their ability to perform incremental development within code repositories by collecting pull requests from 83 GitHub repositorias and using rule-based and intent-based filtering to construct task instances focused on new feature development. |
| Outcome: | The proposed benchmarks show that large language models perform significantly worse in the FEA-Bench, highlighting considerable challenges in repository-level incremental code development. |
THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption (2022.findings-acl)
Copied to clipboard
Tianyu Chen, Hangbo Bao, Shaohan Huang, Li Dong, Binxing Jiao, Daxin Jiang, Haoyi Zhou, Jianxin Li, Furu Wei
| Challenge: | enabling pre-trained models inference on ciphertext data is difficult due to the complex computations in transformer blocks. |
| Approach: | They propose an approximation approach for transformers which enables inference on ciphertext data. |
| Outcome: | The proposed approach can infer pre-trained models on encrypted data with negligible performance drop but enjoy theory-guaranteed privacy-preserving advantage. |
Towards Higher Pareto Frontier in Multilingual Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing Pareto optimization approaches are limited by the long-tailed distribution of multilingual corpora. |
| Approach: | They propose a Pareto mutual distillation framework that pushes the Paret frontier outwards rather than making trade-offs. |
| Outcome: | The proposed framework pushes the Pareto frontier outwards rather than making trade-offs, the authors show. |
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal in-context learning (ICL) is a key mechanism for harnessing the capabilities of large vision–language models. |
| Approach: | They propose a transformer-based model with task-aware attention that dynamically configures ICL sequences. |
| Outcome: | Experiments on five LVLMs and nine datasets show that TACO surpasses baselines across diverse ICL tasks. |
ATG: Benchmarking Automated Theorem Generation for Generative Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing generative language models (LMs) can generate new or reusable theorems, but their ability to generate new theorels is under-explored. |
| Approach: | They propose to use Metamath library to generate new theorems that can be saved as reusable knowledge for future theoretical proving. |
| Outcome: | The proposed benchmark evaluates whether an agent can generate valuable (and possibly brand new) theorems that are applicable for downstream theoretic proving as reusable knowledge. |
A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using an LLM for Chinese spelling correction tasks is completely different from previous approaches . given a Chinese character, there may exist many others with the same or similar pronunciations, or with similar shapes. |
| Approach: | They propose a training-free prompt-free approach to leverage large language models for Chinese spelling correction task. |
| Outcome: | The proposed model significantly improves performance on five public datasets, enabling them to compete with state-of-the-art domain-general CSC models. |
Language Model as Planner and Formalizer under Constraints (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been widely used in planning but lack interpretability and control. |
| Approach: | They propose to augment widely used planning benchmarks with manually annotated, fine-grained, and rich natural language constraints spanning four formally defined categories. |
| Outcome: | The proposed model outperforms existing models in 4 state-of-the-art reasoning LLMs, 4 formal languages, and 4 datasets. |
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages (2024.acl-long)
Copied to clipboard
Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang, Songyang Gao, Yilong Wu, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing research focuses on enhancing LLMs capabilities through tool utilization. |
| Approach: | They propose a framework to investigate safety issues in large language models in tool learning . they propose malicious queries and jailbreak attacks in the input stage . |
| Outcome: | The proposed framework investigates six safety scenarios for LLMs in tool learning . the data will be released upon acceptance of the proposed framework . |
Scaling Laws for Code: A More Data-Hungry Regime (2026.acl-long)
Copied to clipboard
Xianzhen Luo, Wenzhen Zheng, Qingfu Zhu, Rongyi Zhang, Houyi Li, Siming Huang, YuanTao Fan, Wanxiang Che
| Challenge: | Code Large Language Models (LLMs) are revolutionizing software engineering, but scaling laws are primarily analyzed on Natural Language (NL). |
| Approach: | They fit Chinchilla law and Farsser law to test scaling laws for code . they find code is more data-hungry and requires higher data-to-parameter ratio . |
| Outcome: | The proposed scaling laws show that the more expressive Farsser law offers greater accuracy and scales with model size. |
Adaptive Zooming via Relevance-Informed Positional Resource Allocation for Training-free LLM Context Extension (2026.findings-acl)
Copied to clipboard
Hongbo Zhao, Huibin Wang, Bin Tang, Xianming Hu, Yihong Huang, Yijun Shen, Nuoyi Chen, Ping Li, Kai Zhang
| Challenge: | Existing training-free methods for extrapolating beyond training context lengths are semantics-agnostic . Existing methods that focus on relative token distances can indiscriminately blur semantically relevant and irrelevant tokens . |
| Approach: | They propose an adaptive positional zooming method that uses semantic relevance to extrapolate beyond training context lengths. |
| Outcome: | Experiments show that RiPRA outperforms existing training-free extrapolation methods . relevant tokens get higher positional resolution, while irrelevant tokens are compressed . |
EasyNLP: A Comprehensive and Easy-to-use Toolkit for Natural Language Processing (2022.emnlp-demos)
Copied to clipboard
Chengyu Wang, Minghui Qiu, Taolin Zhang, Tingting Liu, Lei Li, Jianing Wang, Ming Wang, Jun Huang, Wei Lin
| Challenge: | Pre-Trained Models (PTMs) have reshaped the development of natural language processing (NLP) but it is not easy to obtain high-performing PTMs without a large amount of labeled training data and deploy them online with fast inference speed. |
| Approach: | They propose to make it easy to build NLP applications with knowledge-enhanced pre-training and knowledge distillation. |
| Outcome: | EasyNLP supports a comprehensive suite of NLP algorithms and features knowledge-enhanced pre-training, knowledge distillation and few-shot learning functionalities. |
Understanding the Dark Side of LLMs’ Intrinsic Self-Correction (2025.acl-long)
Copied to clipboard
Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang, Ke Xu, Hewu Li, Liu Yan, Han Qiu
| Challenge: | Recent studies show that LLMs’ intrinsic self-correction fails without oracle labels as feedback. |
| Approach: | They propose to use one simple task and three complex tasks with state-of-the-art LLMs like ChatGPT, Llama, and DeepSeek to interpret LLM's intrinsic self-correction. |
| Outcome: | The proposed methods reveal the dark side of LLMs’ intrinsic self-correction for different tasks, especially for those failure cases. |
Pre-training Multi-party Dialogue Models with Latent Discourse Inference (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies have failed to scale up the pre-training process by putting aside unlabeled data . et al., 2019: multi-party dialogues are more difficult for models to understand since they involve multiple interlocutors resulting in interweaving reply-to relations and information flows. |
| Approach: | They propose to treat discourse structures as latent variables and jointly infer them to pre-train a model that understands the discourse structure of multi-party dialogues. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art results on multiple downstream tasks. |
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)
Copied to clipboard
Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu
| Challenge: | Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says . |
| Approach: | They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions. |
| Outcome: | a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures . |
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)
Copied to clipboard
Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing methods for retrieving historical messages are based on similarity-based mechanisms. |
| Approach: | They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. |
| Outcome: | The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S. |
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark (2025.acl-long)
Copied to clipboard
Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei
| Challenge: | Multiple-choice question datasets like Massive Multitask Language Understanding (MMLU) have inevitably led to benchmark contamination, resulting in unreliable evaluation. |
| Approach: | They propose a contamination-free MCQ benchmark called MMLU-CF which reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination. |
| Outcome: | The proposed MMLU-CF reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination. |
AIR: Complex Instruction Generation via Automatic Iterative Refinement (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for generating complex instructions are resource-intensive and lack diversity. |
| Approach: | They propose a framework to generate complex instructions with constraints using a document-generated initial instruction and an iterative refinement framework to incorporate LLM-as-judge guidance. |
| Outcome: | The proposed framework significantly outperforms existing methods for generating complex instructions, and outperformed existing methods. |
Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for pre-trained language models rely on noisy data, which can be expensive if all parameters are updated. |
| Approach: | They propose a self-training framework that incorporates Monte Carlo dropouts into the model and judiciously selects reliable pseudo-labeled examples based on confidence and certainty. |
| Outcome: | The proposed framework improves performance and efficiency over multiple tasks over multiple datasets. |
InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)
Copied to clipboard
Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao
| Challenge: | Existing methods focus on knowledge and linguistic patterns of characters. |
| Approach: | They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits. |
| Outcome: | The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits. |
Event-Content-Oriented Dialogue Generation in Short Video (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing multi-modal dialogue models are limited to incapacity of reading visual information and multi-dimensional interactions. |
| Approach: | They propose a novel event-oriented video-dialogue dataset called SportsVD to overcome these challenges by generating human-like response according to event contents in the video and related external knowledge. |
| Outcome: | The proposed method outperforms existing methods on SportsVD and other baselines under several automatic metrics. |
Guiding Variational Response Generator to Exploit Persona (2020.acl-main)
Copied to clipboard
Bowen Wu, MengYuan Li, Zongsheng Wang, Yifu Chen, Derek F. Wong, Qihang Feng, Junhong Huang, Baoxun Wang
| Challenge: | Neural Response Generators (NRGs) use persona information of users to perform personalized conversations . current studies focus on incorporating explicit meta-data of user profiles or character descriptions to generate persona-aware responses. |
| Approach: | They propose to use persona information of users in Neural Response Generators to perform personalized conversations. |
| Outcome: | The proposed method improves persona-aware response generation and the metrics are reasonable to evaluate them. |
Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics (2022.findings-acl)
Copied to clipboard
| Challenge: | Current evaluation methods focus on one dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task. |
| Approach: | They propose to use a single dataset to evaluate the performance of automatic translation metrics. |
| Outcome: | The results show that the rankings of metrics vary when the evaluation is conducted on different datasets. |
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)
Copied to clipboard
Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni
| Challenge: | MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture. |
| Approach: | They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content. |
| Outcome: | The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context. |
Adaptive Token-level Cross-lingual Feature Mixing for Multilingual Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual neural machine translation models can translate multiple language pairs in a single model but lacks ability to capture language-specific features. |
| Approach: | They propose a token-level feature mixing method that captures different features and dynamically determines feature sharing across languages. |
| Outcome: | The proposed method outperforms baselines and can be extended to zero-shot translation. |
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)
Copied to clipboard
Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li
| Challenge: | Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains . |
| Approach: | They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions . |
| Outcome: | The proposed model excels in a teacher-student framework adaptable to evolving domains. |
Accelerating BERT Inference for Sequence Labeling via Early-Exit (2021.acl-long)
Copied to clipboard
| Challenge: | Existing early-exit mechanisms are designed for sequence-level tasks, rather than sequence labeling. |
| Approach: | They propose to extend sentence-level early-exit to accelerate inference of PTMs . they propose a token-level mechanism that allows partial tokens to exit early at different layers . |
| Outcome: | The proposed approach can save up to 66%75% inference cost with minimal performance degradation. |
Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | a novel generalization framework for visual temporal-aligned translation is proposed to transfer recognition skills to unseen performers . ambiguity in the visual sequence can hinder current methods for visual language translation . |
| Approach: | They propose a generalizable framework to transfer recognition skills to unseen performers . they use visual temporal-aligned translation to generate multiple words autoregressively . |
| Outcome: | The proposed framework is generalized to transfer recognition skills to unseen performers . it is compared with existing methods on lipreading and fingerspelling datasets . |
Learning Inter-Entity-Interaction for Few-Shot Knowledge Graph Completion (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent FKGC studies focus on learning semantic representations of entity pairs by separately encoding the neighborhoods of head and tail entities. |
| Approach: | They propose a model to learn semantic representations of entity pairs by separately encoding the neighborhoods of head and tail entities. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two public datasets. |
M-TRACE: Detecting and Mitigating Time-Anchor Drift via Step-wise Conflict Checking in Temporal Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that M-TRACE effectively reduces time-anchor drift . external knowledge may be inaccurate while internal knowledge can become outdated . |
| Approach: | They propose a multi-agent reasoning framework for temporal knowledge conflicts . they propose 'TimeConfQA' which guides conflict-aware final reasoning . |
| Outcome: | Experimental results show that M-TRACE reduces time-anchor drift and improves performance on complex temporal question answering tasks. |
PAD: A Robustness Enhancement Ensemble Method via Promoting Attention Diversity (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to enhance robustness of deep neural networks focus on perturbation . weak robustness is a problem for many types of adversarial attacks, authors say . |
| Approach: | They propose a lightweight framework for enhancing robustness by perturbing parameters of a model and diversifying adversarial example distributions among different models. |
| Outcome: | The proposed method can improve robustness against adversarial attacks while maintaining accuracy on clean data. |
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)
Copied to clipboard
Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen
| Challenge: | Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content. |
| Approach: | They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question . |
| Outcome: | The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types. |
LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases in the real world. |
| Approach: | They propose to train different MMT models to support translations between different languages. |
| Outcome: | The proposed model is able to handle the above issues by providing a shared semantic space for multiple languages. |
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)
Copied to clipboard
Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu
| Challenge: | Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery. |
| Approach: | They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions. |
| Outcome: | The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency. |
GeoAgent: To Empower LLMs using Geospatial Tools for Address Standardization (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to address address standardization are lacking in the current field. |
| Approach: | They propose a framework that incorporates spatial knowledge into address texts and achieves efficient address standardization. |
| Outcome: | The proposed framework incorporates spatial knowledge into address texts and achieves efficient address standardization. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large vision-language models exhibit an imbalance in multilingual capabilities . |
| Approach: | They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning. |
| Outcome: | The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers. |
Improving Factual Consistency of News Summarization by Contrastive Preference Optimization (2024.findings-emnlp)
Copied to clipboard
Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma
| Challenge: | Recent advances in news summarization have created problems with “hallucinations” that are factually inconsistent with the source text. |
| Approach: | They propose to disentangle LLMs’ propensities to generate faithful and fake content by adopting a probing-based specific training method to improve their capacity of distinguishing two types of propensity. |
| Outcome: | The proposed method disentangles LLMs’ propensities to generate faithful and fake content and improves their ability to distinguish between two types of propensity. |
MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)
Copied to clipboard
Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang
| Challenge: | Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture. |
| Approach: | They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition. |
| Outcome: | The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module. |
CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Comparative Policy Optimization (CPO) redefines the reward evaluation paradigm by shifting from sample-wise scoring to comparative group-wise score. |
| Approach: | They propose a method to optimize subjective tasks by shifting from sample-wise to comparative group-wise scoring. |
| Outcome: | The proposed framework shifts from sample-wise scoring to comparative group-wise score . it minimizes contextual bias and enables more robust and fair performance evaluation. |
Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-enhanced pre-trained language models (PLMs) introduce redundant factual knowledge from knowledge bases and require complex modules. |
| Approach: | They propose a knowledge prompting-based PLM framework that incorporates factual knowledge into PLMs. |
| Outcome: | The proposed framework can be flexibly combined with existing mainstream PLMs. |
Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-Context Models (2024.emnlp-main)
Copied to clipboard
Xinyu Liu, Runsong Zhao, Pengcheng Huang, Chunyang Xiao, Bei Li, Jingang Wang, Tong Xiao, JingBo Zhu
| Challenge: | Existing methods, tasks and benchmarks to measure model’s effective memory length are limited. |
| Approach: | They propose a method called forgetting curve to measure the memorization capability of long-context models. |
| Outcome: | The proposed method is robust to the tested corpus and experimental settings, and can be applied to any model size. |
S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)
Copied to clipboard
Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu
| Challenge: | Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks. |
| Approach: | They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents . |
| Outcome: | The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%. |
RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)
Copied to clipboard
Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu
| Challenge: | Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning. |
| Approach: | They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step. |
| Outcome: | The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings. |
SDPO: Segment-Level Direct Preference Optimization for Social Agents (2025.acl-long)
Copied to clipboard
Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li, Yuchuan Wu, Ke Wang, Xiaoqian Liu, Qicheng Li, Yong Qin, Fei Huang
| Challenge: | Direct Preference Optimization (DPO) has proven effective in aligning LLM behavior with human preferences across various tasks, but is limited in multi-turn social interactions. |
| Approach: | They propose a method which dynamically selects key segments within interactions to optimize multi-turn agent behavior. |
| Outcome: | The proposed methods outperform existing methods and proprietary LLMs on the SOTOPIA benchmark and show that they can improve social intelligence. |
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding (2023.acl-long)
Copied to clipboard
Ziheng Li, Shaohan Huang, Zihan Zhang, Zhi-Hong Deng, Qiang Lou, Haizhen Huang, Jian Jiao, Furu Wei, Weiwei Deng, Qi Zhang
| Challenge: | Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. |
| Approach: | They propose a dual-alignment pre-training framework that incorporates both sentence-level and token-level alignment. |
| Outcome: | The proposed framework improves cross-lingual sentence embedding on three cross-linguistic benchmarks. |
DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference (2025.findings-acl)
Copied to clipboard
Juhua Zhang, Zhiliang Tian, Minghang Zhu, Yiping Song, Taishu Sheng, Siyi Yang, Qiunan Du, Xinwang Liu, Minlie Huang, Dongsheng Li
| Challenge: | Existing methods to protect privacy of sensitive data are differential privacy (DP) and DP is used to protect users from privacy leakage. |
| Approach: | They propose an LDP-based Dynamic Text sanitization for privacy-preserving LLM inference that dynamically constructs semantic-aware adjacency lists of sensitive tokens to sample non-sensitive tokens for perturbation. |
| Outcome: | The proposed model excels on three datasets. |
ATLAS: Agent Tuning via Learning Critical Steps (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing agent tuning approaches employ supervised finetuning on entire expert trajectories, but behavior-cloning of full traitories introduces expert bias and weakens generalization to states not covered by the expert data. |
| Approach: | They propose a method that finetunes LLMs on critical steps in expert trajectories and identifies and finetuns them on these steps with reduced costs. |
| Outcome: | The proposed method outperforms existing methods and open-source LLM agents on only 30% critical steps in extensive experiments. |
Towards Emotional Support Dialog Systems (2021.acl-long)
Copied to clipboard
| Challenge: | Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. |
| Approach: | They propose an Emotional Support Conversation task and an ESC Framework to train emotional support into dialog systems. |
| Outcome: | The proposed framework provides an example of an Emotional Support Conversation task and shows that it is more effective than existing models. |
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation (2026.acl-long)
Copied to clipboard
Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng
| Challenge: | Existing evaluation benchmarks for text-to-audio-video (T2AV) generation are largely designed for human-recorded videos or single-speaker settings. |
| Approach: | They propose a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation. |
| Outcome: | The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression. |
DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to domain adaptation only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. |
| Approach: | They propose a domain adversarial learning enhanced self-training framework that uses meta-learning to estimate the importance of each pseudo instance and a meta constructor to construct the meta-validation set. |
| Outcome: | The proposed framework reduces label noise and preserves hard examples while maintaining accuracy. |
Transforming Visual Scene Graphs to Image Captions (2023.acl-long)
Copied to clipboard
Xu Yang, Jiawei Peng, Zihua Wang, Haiyang Xu, Qinghao Ye, Chenliang Li, Songfang Huang, Fei Huang, Zhangzikang Li, Yu Zhang
| Challenge: | Existing approaches to generate captions using image captioning are based on multi-head attention (MHA) |
| Approach: | They propose to transform scene graphs into more descriptive captions by using multi-head attention to build a Graph Neural Network (GNN) . they construct a Mixture-of-Expert (MOE)-based decoder where each expert is built on MHA for discriminating the graph embeddings to generate different kinds of words. |
| Outcome: | The proposed framework can generate captions from multiple visual features and objects . it is based on a mixture-of-expert (MOE)-based decoder based upon MHA . |
MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)
Copied to clipboard
Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang
| Challenge: | Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences. |
| Approach: | They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner. |
| Outcome: | The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner. |
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)
Copied to clipboard
Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li
| Challenge: | Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values. |
| Approach: | They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent. |
| Outcome: | The proposed method improves on a two-agent game with an adversarial agent and a defensive agent. |
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)
Copied to clipboard
Xize Cheng, Rongjie Huang, Linjun Li, Zehan Wang, Tao Jin, Aoxiong Yin, Chen Feiyang, Xinyu Duan, Baoxing Huai, Zhou Zhao
| Challenge: | Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors. |
| Approach: | They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages. |
| Outcome: | The proposed model can translate audio-visual speech into audio-visual speech in other languages. |
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization (2026.acl-long)
Copied to clipboard
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
| Challenge: | Recent studies have explored fine-tuning Large Language Models with synthetic data to enhance their long-context capabilities. |
| Approach: | They propose a framework that leverages a Multi-Armed Bandit rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse responses. |
| Outcome: | The proposed framework achieves 4% improvement on long-context reasoning benchmarks on Llama and Qwen. |
SAM3-I: Segment Anything with Instructions (2026.acl-long)
Copied to clipboard
Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng
| Challenge: | Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering. |
| Approach: | They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework. |
| Outcome: | Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability. |
ACEBench: A Comprehensive Evaluation of LLM Tool Usage (2025.findings-emnlp)
Copied to clipboard
Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Yuefeng Huang, Xiangcheng Liu, Wang Xinzhi, Wu Liu
| Challenge: | Existing benchmarks for evaluating LLMs’ tool usage face several limitations: limited evaluation scenarios, lacking assessments in real multi-turn dialogue contexts; narrow evaluation dimensions, with insufficient detailed assessments of how LLM use tools; and reliance on LLM or real API executions for evaluation, which introduces significant overhead. |
| Approach: | ACEBench is a benchmark for evaluating tool usage in Large Language Models . it categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
| Outcome: | ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations (2024.acl-long)
Copied to clipboard
| Challenge: | Currently, many benchmarks evaluate the commonsense reasoning of large language models (LLMs), but most are English-based, limiting non-English evaluations. |
| Approach: | They propose to use Chinese commonsense reasoning to evaluate LLMs' commonsensing ability. |
| Outcome: | The proposed benchmark covers both globally known and Chinese-specific commonsense reasoning abilities and can be used as a reference for future research. |
Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Dialogue embeddings are a critical prerequisite for semantically understanding dialogues. |
| Approach: | They propose a self-guided contrastive learning approach called dial2vec that captures interaction patterns between interlocutors and leverages them to guide the learning of the embeddings corresponding to each interlocuter. |
| Outcome: | The proposed approach achieves 8.7, 9.0, and 13.8 points absolute improvements over the strongest baseline on the three evaluation tasks respectively. |
Causal Document-Grounded Dialogue Pre-training (2023.emnlp-main)
Copied to clipboard
Yingxiu Zhao, Bowen Yu, Bowen Li, Haiyang Yu, Jinyang Li, Chao Wang, Fei Huang, Yongbin Li, Nevin Zhang
| Challenge: | Existing methods for document-grounded dialogue (DocGD) rely on general pre-trained language models without a tailored pre-training approach that explicitly captures causal relationships. |
| Approach: | They propose a causally-complete dataset construction strategy for developing million-scale DocGD pre-training corpora and a perturbation-based strategy to capture causality. |
| Outcome: | The proposed strategy yields significant and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings. |
Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly enhanced their performance in various natural language processing tasks. |
| Approach: | They propose a robust and pluggable knowledge rewriter that is optimized for LLM generation by supporting the model's supportiveness. |
| Outcome: | The proposed model can be used to rewrite knowledge in a supervised manner. |
LLM can Achieve Self-Regulation via Hyperparameter Aware Generation (2024.findings-acl)
Copied to clipboard
Siyin Wang, Shimin Li, Tianxiang Sun, Jinlan Fu, Qinyuan Cheng, Jiasheng Ye, Junjie Ye, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing decoding strategies and hyperparameters may not be optimal for each sample. |
| Approach: | They propose a model that auto-regulates decoding strategies and hyperparameters . this approach eliminates the need for extensive manual tuning, they argue . |
| Outcome: | The proposed model eliminates the need for extensive manual tuning, offering a more autonomous, self-regulate model behavior. |
Faster MoE LLM Inference for Extremely Large Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing inference optimizations for coarse-grained Mixture-of-Experts models implicitly assume a fixed activation budget, which is poorly understood. |
| Approach: | They propose a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget. |
| Outcome: | The proposed skipping policy can provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms. |
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai, Xinyue Lou, Yunghwei Lai, Ziyue Wang, Yawen Wang, Kaiyu Huang, Yile Wang, Peng Li, Yang Liu
| Challenge: | Existing multimodal benchmarks overlook linguistic and visual ambiguities, authors say . ambiguity resolution between modalities is lacking in multimodal large language models . |
| Approach: | They propose a benchmark to evaluate multimodal ambiguity resolution across multilingual and cross-modal scenarios. |
| Outcome: | a new benchmark evaluates multimodal ambiguity resolution across multilingual and cross-modal scenarios . the benchmark shows that MLLMs can resolve ambiguities in image-text alignment . however, existing benchmarks often overlook linguistic and visual ambiguties . |
Towards Multi-modal Sarcasm Detection via Disentangled Multi-grained Multi-modal Distilling (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to sarcasm detection focus on textual and intra-modal incongruity . mainstream approaches process input of each modality in a holistic manner, resulting in redundant and unrefined information. |
| Approach: | They propose a framework for multi-modal sarcasm detection that disentangles modality representations into latent spaces and conducts multi-grained knowledge distilling. |
| Outcome: | The proposed framework overpowers existing methods on a common benchmark. |
Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent work on domain adaptation for text summarization fails to account for the huge gap between dialogue and general articles. |
| Approach: | They propose a hypernetwork-assisted encoder-decoder architecture with parameter-efficient fine-tuning to disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain. |
| Outcome: | The proposed model can disentangle domain-invariant knowledge from source domains while learning specific knowledge of the target domain. |
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)
Copied to clipboard
Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li
| Challenge: | Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored. |
| Approach: | They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation. |
| Outcome: | The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs. |
Pre-Training to Learn in Context (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models are not explicitly trained to learn in context. |
| Approach: | They propose a framework to enhance in-context learning by pre-training language models on a large collection of "intrinsic tasks" they evaluate the in-constitution learning performance of the model trained with PICL on seven widely-used text classification datasets and the Super-NaturalInstrctions benchmark . |
| Outcome: | The proposed framework outperforms larger language models with nearly 4x parameters on seven widely-used datasets and the Super-NaturalInstrctions benchmark. |
WSpeller: Robust Word Segmentation for Enhancing Chinese Spelling Check (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Chinese spelling check (CSC) detects and corrects spelling errors in Chinese texts. |
| Approach: | They propose a Chinese spelling check model that takes into account word segmentation and a module that can assist the correction module by predicting correct word segmentations from sentences containing spelling errors. |
| Outcome: | The proposed model outperforms baselines on SIGHAN13, SIGHEN14, and SIGHAN15 and maintains equal performance on SSGHAN14. |
Aligned Dual Channel Graph Convolutional Network for Visual Question Answering (2020.acl-main)
Copied to clipboard
| Challenge: | Existing graph-based methods focus only on relations between objects in an image and neglect the importance of syntactic dependency relations between words. |
| Approach: | They propose a dual channel graph convolutional network to capture relations between objects in an image and syntactic dependency relations between words in a question. |
| Outcome: | The proposed model achieves comparable performance with the state-of-the-art approaches. |
Multilingual Pretraining and Instruction Tuning Improve Cross-Lingual Knowledge Alignment, But Only Shallowly (2024.naacl-long)
Copied to clipboard
| Challenge: | Current large language models show imbalance abilities in different languages . authors propose two approaches to improve cross-lingual knowledge alignment . |
| Approach: | They propose a framework to assess cross-lingual knowledge alignment of large language models . they propose multilingual pretraining and multilingual instruction tuning to address this problem . |
| Outcome: | The proposed framework assesses the cross-lingual knowledge alignment of LLMs in performance, consistency and conductivity levels. |
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Traditional generation methods focus primarily on textual quality, but they fail to meet complex, multifaceted educational requirements. |
| Approach: | They propose a method for automatic generating high-quality mathematical problems that align with educational objectives using a dataset of 16k mathematical questions with multi-dimensional educational objectives. |
| Outcome: | The proposed method improves generating high-quality mathematical questions that meet multi-dimensional educational objectives. |
World Models with Hints of Large Language Models for Goal Achieving (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods address this by adding intrinsic rewards, but they fail to provide meaningful guidance in long-horizon decision-making tasks with large state and action spaces lacking purposeful exploration. |
| Approach: | They propose a multi-modal model-based RL approach that integrates the proposed hinting subgoals into the model rollouts to encourage goal discovery and reaching in challenging tasks. |
| Outcome: | The proposed model outperforms existing methods in challenging, sparse-reward environments such as HomeGrid, Crafter, and Minecraft by 41.8%, 21.1%, and 9.9%. |
Planning and Editing What You Retrieve for Enhanced Tool Learning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for integrating external tools with Large Language Models fall short on effectively shortlisting relevant tools. |
| Approach: | They propose a plan-and-retrieve and edit-and ground paradigms for LLMs that decompose complex queries into actionable tasks. |
| Outcome: | The proposed paradigms significantly improve recall and NDCG in tool retrieval tasks, surpassing current state-of-the-art models. |
MONTROSE: LLM-driven Monte Carlo Tree Search Self-Refinement for Cross-Domain Rumor Detection (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing feature alignment methods are susceptible to task interference during training. |
| Approach: | MONTROSE is a cross-domain rumor detection method that generates high-quality synthetic data for the target domain and a domain-sharpness-aware approach to train models with these synthetic data. |
| Outcome: | Experiments show that MONTROSE improves in cross-domain rumor detection. |
F-Eval: Asssessing Fundamental Abilities with Refined Evaluation Methods (2024.acl-long)
Copied to clipboard
Yu Sun, Keyuchen Keyuchen, Shujie Wang, Peiji Li, Qipeng Guo, Hang Yan, Xipeng Qiu, Xuanjing Huang, Dahua Lin
| Challenge: | Large language models (LLMs) have been evaluated for their instruction-following capabilities but lack references to their fundamental abilities. |
| Approach: | They propose a bilingual evaluation benchmark to evaluate the fundamental abilities of large language models including expression, commonsense and logic. |
| Outcome: | The proposed evaluation methods show higher correlation coefficients and larger distinction than other evaluators. |
TextHide: Tackling Data Privacy in Language Understanding Tasks (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Unsolved privacy challenges in distributed or federated learning are a challenge for many domains including Natural Language Processing. |
| Approach: | They propose a federated learning framework that adds an encryption step to prevent an eavesdropping attacker from recovering private text data. |
| Outcome: | The proposed model can effectively defend against attacks on shared gradients or representations and the averaged accuracy reduction is only 1.9%. |
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation. |
| Approach: | They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement. |
| Outcome: | The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase. |
CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Developing long-context LLMs with robust long-text capabilities is underdeveloped due to a lack of benchmarks. |
| Approach: | They propose a Chinese benchmark for evaluating long-context LLMs with Chinese capabilities. |
| Outcome: | The proposed model is based on 6 open-source LLMs and 2 commercial ones. |
Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing sparse retrieval methods often yield inferior performance in multilingual retrieval, requiring a large amount of paired data, which is costly. |
| Approach: | They propose an Unsupervised Multilingual dense Retriever trained without paired data which iteratively improves performance of multilingual retrievers. |
| Outcome: | The proposed framework outperforms supervised baselines on two benchmark datasets and shows that iterative training improves the performance. |
LIST: Linearly Incremental SQL Translator for Single-Hop Reasoning, Generation and Verification (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing schema linking methods are not able to handle complex SQL queries. |
| Approach: | They propose a new algorithm that transforms SQL queries into grammatically verifiable sub-queries which are arranged sequentially to reflect single-hop reasoning steps. |
| Outcome: | The proposed algorithm achieves significant performance gains on the BIRD dataset and surpasses schema linking methods at comparable or better cost. |
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)
Copied to clipboard
Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu
| Challenge: | Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks . |
| Approach: | They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps. |
| Outcome: | The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios. |
SAMem: State-Aware Memory as a Fine-Grained Memory for LLM Agents in Decision-Making (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing experiential memory approaches rely on task-level memory, but this lacks the situational alignment required for complex multi-step decision-making. |
| Approach: | They propose a new fine-grained memory paradigm that aligns memory retrieval with the current state instead of storing and reusing globally shared experiences. |
| Outcome: | Experiments on complex decision-making benchmarks show that the proposed state-aware memory outperforms existing experiential memory approaches and significantly improves task-solving efficiency. |
GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for controlling the generation of pre-trained language models infuse domain bias into the generation process, making it difficult to generate out-of-domain texts. |
| Approach: | They propose a retrieval-augmented generation framework that uses retrieval to generate fluent sentences with high attribute relevance. |
| Outcome: | The proposed method can generate fluent sentences with high attribute relevance while keeping domain bias out of the model. |
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can reveal toxic or offensive content inadvertently or intentionally. |
| Approach: | They propose to control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their impact. |
| Outcome: | The proposed approach improves the performance of large language models after fine-tuning. |
Visually-Enhanced Phrase Understanding (2023.findings-acl)
Copied to clipboard
| Challenge: | Large-scale vision-language pre-training models generate high-quality textual representations, which often outperform models that are purely text-based, such as BERT. |
| Approach: | They propose to utilize both textual and visual encoders of multi-modal pre-trained models to enhance language understanding tasks by generating an image associated with a textual prompt. |
| Outcome: | The proposed method outperforms models that are purely text-based on visual and textual understanding tasks and significantly improves the entity clustering task. |
Visualizing the Relationship Between Encoded Linguistic Information and Task Performance (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that encoding more syntactic information does not lead to better performance. |
| Approach: | They propose a method to optimize pareto-optimal models by formalizing it as a multi-objective optimization problem. |
| Outcome: | The proposed method is better than a baseline method on two NLP tasks. |
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs (2026.eacl-long)
Copied to clipboard
Yujia Zheng, Tianhao Li, Haotian Huang, Tianyu Zeng, Jingyu Lu, Chuangxin Chu, Yuekai Huang, Ziyou Jiang, Qian Xiong, Yuyao Ge, Mingyang Li
| Challenge: | Existing studies treat prompts as flat text, overlooking their internal structure, and different components within a prompt contribute unequally to robustness. |
| Approach: | They propose a framework that decomposes prompts into functional components and a method that selectively modifies components to expose component-wise vulnerabilities. |
| Outcome: | The proposed framework exposes component-wise vulnerabilities while ensuring linguistic plausibility through perplexity-based filtering. |
EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks focusing on single-task environments with limited constraints lack the complexity required to fully reflect the evolution of large language models (LLMs). |
| Approach: | They propose to use a Segment Policy Optimization algorithm to enhance the LLM's ability to accurately fulfill multi-task workflows. |
| Outcome: | The proposed benchmarks show that existing benchmarks lack the complexity required to fully reflect the evolution of large language models. |
Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conversations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing retrieval-based methods for long-term conversations face challenges in memory database management and accurate memory retrieval, hindering their efficacy in dynamic, real-world interactions. |
| Approach: | They propose a framework that eschews traditional retrieval modules and memory databases and adopts a “One-for-All” approach to manage memory generation, compression, and response generation. |
| Outcome: | The proposed framework produces more nuanced and human-like experiences than retrieval-based methods. |
LegalAgentBench: Evaluating LLM Agents in Legal Domain (2025.acl-long)
Copied to clipboard
Haitao Li, Junjie Chen, Jingli Yang, Qingyao Ai, Wei Jia, Youfeng Liu, Kai Lin, Yueyue Wu, Guozhi Yuan, Yiran Hu, Wuyue Wang, Yiqun Liu, Minlie Huang
| Challenge: | Existing general-domain benchmarks do not capture complexity of real-world judicial cognition and decision-making. |
| Approach: | They propose a benchmark specifically designed to evaluate LLM Agents in the legal domain. |
| Outcome: | The proposed benchmark includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. |
Context-aware Difference Distilling for Multi-change Captioning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multi-change captioning are difficult because it requires a higher level of cognition to reason an arbitrary number of changes. |
| Approach: | They propose a context-aware difference distilling network to capture all genuine changes for yielding sentences. |
| Outcome: | The proposed network captures all genuine changes for yielding sentences on three public datasets. |
Traces in the Brain: Neural Evidence for Syntactic Movement in English and Chinese (2026.findings-acl)
Copied to clipboard
Yuhan Huang, Zhengwu Ma, Yuqi Jin, Beth Chan, Zheng Shen, Jackie Yan-Ki Lai, John T. Hale, Jixing Li
| Challenge: | Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies. |
| Approach: | They annotated every sentence in the audiobook The Little Prince using X-bar style tree annotations. |
| Outcome: | The proposed model shows that deep structure significantly predicts neural responses in English but not in Chinese. |
Multi-Source Probing for Open-Domain Conversational Understanding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models of open-domain dialogue comprehension have limited conversational understanding and response generation. |
| Approach: | They propose a multi-source probing method to probe dialogue comprehension abilities of open-domain dialogue models. |
| Outcome: | The proposed method aggregates features from multiple sources to accomplish diverse task goals and conducts downstream tasks in a generative manner consistent with dialogue model pre-training to leverage model capabilities. |
Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have shown strong abilities to understand natural language, but how these factors affect the models’ language perception is unclear. |
| Approach: | They compare the self-attention of several existing large language models in different sizes to assess the effect of scaling and instruction tuning on language perception. |
| Outcome: | The proposed models are closer to non-native speakers than native speakers in attention, suggesting a sub-optimal language perception of all models. |
Analyzing and Internalizing Complex Policy Documents for LLM Agents (2026.acl-long)
Copied to clipboard
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xiang Li, Chenlei Guo, Xing Fan, Ruhi Sarikaya, Heng Ji
| Challenge: | Large language model agents rely on in-context policy documents to act as effective user assistants. |
| Approach: | They propose an agentic benchmark generator with Controllable Complexity in agent policy across four levels to evaluate agents under increasing complexity. |
| Outcome: | The proposed method outperforms the baseline in data-sparse and high-complexity settings. |
Teaching Your Models to Understand Code via Focal Preference Alignment (2025.emnlp-main)
Copied to clipboard
Jie Wu, Haoling Li, Xin Zhang, Xiao Liu, Yangyu Huang, Jianwen Luo, Yizhen Zhang, Zuchao Li, Ruihang Chu, Yujiu Yang, Scarlett Li
| Challenge: | Existing methods for supervised fine-tuning focus on unit test feedback to construct preference pairs. |
| Approach: | They propose a preference alignment framework that mimics human iterative debugging to refine Code LLMs. |
| Outcome: | Experiments show that Preference Learning improves on BigCodeBench and BigCodeBind tasks. |
LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency. |
| Approach: | They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache. |
| Outcome: | The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache. |
Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)
Copied to clipboard
Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, Jingyu Lu, Rongjie Huang, Ruiyuan Zhang, Zhiqing Hong, Ziyue Jiang, Zhou Zhao
| Challenge: | Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment. |
| Approach: | VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control. |
| Outcome: | Experimental results show that VersBand performs better than baseline models across multiple song generation tasks. |
BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment (2025.findings-emnlp)
Copied to clipboard
Jiaqi Duan, Xiaoda Yang, Kaixuan Luan, Hongshun Qiu, Weicai Yan, Xueyi Zhang, Youliang Zhang, Zhaoyang Li, Donglin Huang, JunYu Lu, Ziyue Jiang, Xifeng Yang
| Challenge: | BrainLoc is a lightweight object detection model guided by fMRI signals. |
| Approach: | They propose a brain-based object detection model guided by fMRI signals . they employ a multi-modal alignment strategy that enhances fmr feature extraction . |
| Outcome: | The proposed model improves fMRI-based object detection accuracy and convenience. |
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention (2026.acl-long)
Copied to clipboard
Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang
| Challenge: | Code Language Models learn attention based on statistical input-output token correlations. |
| Approach: | They propose a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. |
| Outcome: | The proposed model outperforms baselines in three languages, with gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. |
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024.emnlp-main)
Copied to clipboard
Minzheng Wang, Longze Chen, Fu Cheng, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li
| Challenge: | Existing benchmarks for evaluating long-context language models employ irrelevant noise texts to artificially extend the length of test cases, diverging from the real-world scenarios of long-constituency applications. |
| Approach: | They propose a long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) . |
| Outcome: | The proposed model can scale up the context window of large language models to perform in-depth analysis of multiple long documents. |
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks evaluate contextual causal reasoning in fragmented settings, failing to ensure context consistency or cover the full causal hierarchy. |
| Approach: | They use a unified context to benchmark large language models' contextual causal reasoning skills. |
| Outcome: | The proposed benchmarks show that LLMs are susceptible to distraction by irrelevant but factually correct information at lower level of causality. |
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies treat named entity recognition as a sequential labeling problem. |
| Approach: | They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted . |
| Outcome: | The proposed framework outperforms competing models on four benchmark datasets. |
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models (2025.acl-long)
Copied to clipboard
Zhisong Zhang, Yan Wang, Xinting Huang, Tianqing Fang, Hongming Zhang, Chenlong Deng, Shuaiyi Li, Dong Yu
| Challenge: | Large language models have demonstrated remarkable performance across a wide range of language tasks due to their remarkable ability in context modeling. |
| Approach: | They propose to use parallel context encoding to reduce attention entropy by incorporating attention sinks and selective mechanisms to reduce irregular attention . they also propose to incorporate attention sink mechanisms into the parallel encoded context to reduce the irregular attention. |
| Outcome: | The proposed methods lower irregular attention entropy and narrow performance gaps. |
Regularized Context Gates on Transformer for Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation. |
| Approach: | They propose a method to identify source and target contexts and introduce a gate mechanism to control the contributions from source and targets in the advanced Transformer architecture. |
| Outcome: | The proposed model achieves an averaged gain of 1.0 BLEU score over a strong transformer baseline. |
Universal Information Extraction with Meta-Pretrained Self-Retrieval (2023.findings-acl)
Copied to clipboard
Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang
| Challenge: | Existing methods for IE are task-specific, resulting in specialized and isolated approaches for different tasks. |
| Approach: | They propose a method to retrieve task-specific knowledge from pretrained language models to enhance universal IE by using a Meta-Pretraining Algorithm. |
| Outcome: | The proposed method achieves the new state-of-the-art on 4 IE tasks, 12 datasets under fully-supervised, low-resource and few-shot scenarios. |
Diversify Question Generation with Retrieval-Augmented Style Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing question generation systems focus on the internal knowledge within the textual passage or the semantic word space for diverse content planning. Existing solutions focus on relying on the knowledge of the text and the semantic words, but have not considered the potential of external knowledge for expression diversity. |
| Approach: | They propose a framework for Retrieval-Augmented Style Transfer that utilizes the style of diverse templates for question generation. |
| Outcome: | The proposed framework outperforms baselines on diversity while being comparable in terms of consistency scores. |
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)
Copied to clipboard
Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Jian Wang, Liang Dandan, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang
| Challenge: | Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance. |
| Approach: | They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 . |
| Outcome: | The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs. |
ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questions (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Recent advances in conversational information seeking (CIS) suggest a remedy for the lack of interactive clarification when people face unfamiliar domains. |
| Approach: | They propose a fully autonomous conversational information-seeking agent that couples large language models with a set of domain-specific tools to provide product demand clarification. |
| Outcome: | The proposed agent can iterate over 2,000 automatically generated sessions and score high on real-world evaluations without human annotation. |
ResLoRA: Identity Residual Mapping in Low-Rank Adaption (2024.findings-acl)
Copied to clipboard
Shuhua Shi, Shaohan Huang, Minghui Song, Zhoujun Li, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Low-rank adaptation (LoRA) is one of the most popular parameter-efficient fine-tuning methods. |
| Approach: | They propose a low-rank adaptation method that adds residual paths during training and merges them together during inference to achieve better results. |
| Outcome: | The proposed method achieves 2.5x faster convergence speed and improves performance by 14.3% on NLG, NLU, and text-to-image tasks. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)
Copied to clipboard
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
| Challenge: | a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks. |
| Approach: | They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories . |
| Outcome: | The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points. |
New Frontiers of Information Extraction (2022.naacl-tutorials)
Copied to clipboard
| Challenge: | Information extraction (IE) is the process of automatically extracting structural information from unstructured or semi-structured data. |
| Approach: | This tutorial will provide an introduction to recent advances in IE by answering several important research questions. |
| Outcome: | The tutorial will address several important research questions and outline directions for further investigation. |
Adversarial Text Generation by Search and Learning (2023.findings-emnlp)
Copied to clipboard
Guoyi Li, Bingkang Shi, Zongzhen Liu, Dehan Kong, Yulei Wu, Xiaodan Zhang, Longtao Huang, Honglei Lyu
| Challenge: | Existing text generation methods only use heuristic replacement strategies or language models to generate replacement words at the word level. |
| Approach: | They propose a search and learning framework for Adversarial Text Generation by Search and Learning to evaluate the robustness of natural language processing models. |
| Outcome: | The proposed methods are significantly superior to the most advanced methods in terms of attack efficiency and adversarial text quality. |
UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)
Copied to clipboard
Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs). |
| Approach: | They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits. |
| Outcome: | The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion. |
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)
Copied to clipboard
Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao
| Challenge: | Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences. |
| Approach: | They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning. |
| Outcome: | The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks. |
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models have been successful in NLP tasks, but their large size and long inference time limit their deployment in real-time applications. |
| Approach: | They propose a meta-teacher model that captures transferable knowledge across domains and passes it to students. |
| Outcome: | The proposed model can distill large teacher models into small student models with guidance from the meta-teacher. |
Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction (2022.findings-emnlp)
Copied to clipboard
Shirong Ma, Yinghui Li, Rongyi Sun, Qingyu Zhou, Shulin Huang, Ding Zhang, Li Yangning, Ruiyang Liu, Zhongli Li, Yunbo Cao, Haitao Zheng, Ying Shen
| Challenge: | Chinese Grammatical Error Correction (CGEC) is a challenging NLP task and a common application in human daily life. |
| Approach: | They propose a linguistic rules-based approach to construct large-scale CGEC training corpora with automatically generated grammatical errors. |
| Outcome: | The proposed method improves performance of existing CGEC models and the benchmark is excellent resource for further development. |
Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models (2024.acl-long)
Copied to clipboard
Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang
| Challenge: | Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new knowledge into Large Language Models (LLMs). |
| Approach: | They propose to evaluate LLMs with single edit only and parameter-modifying ME with parameter-preserving ME. |
| Outcome: | The proposed method can maintain LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format. |
Foundation Models Meet Embodied Agents (2025.naacl-tutorial)
Copied to clipboard
| Challenge: | This tutorial will present a systematic overview of recent advances in foundation models for embodied agents . |
| Approach: | This tutorial will present a systematic overview of recent advances in foundation models for embodied agents. |
| Outcome: | This tutorial covers three types of foundation models for embodied agents . |
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)
Copied to clipboard
Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin
| Challenge: | Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation. |
| Approach: | They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets. |
| Outcome: | The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark. |
Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes (2025.emnlp-main)
Copied to clipboard
Qiunan Du, Zhiliang Tian, Zhen Huang, Kailun Bian, Tianlun Liu, Zhaoning Zhang, Xinwang Liu, Feng Liu, Dongsheng Li
| Challenge: | Existing studies on in-context learning (ICL) focus on the selection of individual examples and ignore correlations among examples. |
| Approach: | They propose a method to capture positive and negative correlations using the determinantal point process . they optimize the method via kernel decomposition-based MLE to fit a constructed pseudo-labeled dataset . |
| Outcome: | The proposed method outperforms baselines in ICL example selection. |
Interventional Rationalization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for rationalization use spurious correlations in data to compose rationales and make predictions. |
| Approach: | They propose a method to discover the causal rationales by using a structural causal model. |
| Outcome: | The proposed method is based on the causal theory and validates on three real-world datasets. |
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios (2025.coling-main)
Copied to clipboard
Junjie Ye, Guanyu Li, SongYang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing evaluations of tool learning focus on validation of tools for large language models with expected outcomes, but this focus ignores the complex capabilities required for LLMs to effectively use tools. |
| Approach: | They propose a fine-grained system for evaluation of large language models’ tool learning capabilities in authentic scenarios. |
| Outcome: | The proposed system examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning: format alignment, intent comprehension, behavior planning, tool selection, and answer organization. |
LLM-as-a-Coauthor: Can Mixed Human-Written and Machine-Generated Text Be Detected? (2024.findings-naacl)
Copied to clipboard
Qihui Zhang, Chujie Gao, Dongping Chen, Yue Huang, Yixin Huang, Zhenyang Sun, Shilin Zhang, Weiye Li, Zhengyan Fu, Yao Wan, Lichao Sun
| Challenge: | Current research focuses on purely MGT detection without adequately addressing mixed scenarios including AI-revised Human-Written Text (HWT) and human-revealed MGT. |
| Approach: | They define mixtext, a form of mixed text involving both AI and human-generated content, and then use a MixSet dataset to assess their effectiveness. |
| Outcome: | The proposed detectors struggle to identify mixtext, particularly in dealing with subtle modifications and style adaptability. |
Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support Conversation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing strategies focus on planning the next-turn dialogue strategies, while external strategy planners focus on generating empathetic responses. |
| Approach: | They propose a Markov-driven emotion anticipation framework with emotion trajectory-aware retrieval for LLM-based ESC, which anticipates future emotion states to guide strategy planning and achieve sustained emotional support. |
| Outcome: | The proposed framework can anticipate future emotions and achieve sustained emotional support on two datasets with two models. |
Effidit: An Assistant for Improving Writing Efficiency (2023.acl-demo)
Copied to clipboard
Shuming Shi, Enbo Zhao, Wei Bi, Deng Cai, Leyang Cui, Xinting Huang, Haiyun Jiang, Duyu Tang, Kaiqiang Song, Longyue Wang, Chenyan Huang, Guoping Huang, Yan Wang, Piji Li
| Challenge: | Effidit is a digital writing assistant that provides three modules to help users write faster and more efficiently. |
| Approach: | They present Effidit, a digital writing assistant that provides three modules to help users write higher-quality text more efficiently. |
| Outcome: | Effidit expands the capabilities of a typical writing assistant by providing three modules . Effit can help users create their own text faster and more efficiently . |
Understanding Generalization in Role-Playing Models via Information Theory (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to characterize RPM generalization are inadequate . existing methods do not provide a fine-grained diagnosis of distribution shifts . |
| Approach: | They propose a reasoning-based effective mutual information difference (R-EMID) to measure RPM performance degradation in an interpretable way. |
| Outcome: | The proposed model predicts the worst-case generalization performance of RPMs and reveals how shifts contribute to degradation. |
Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for transferring knowledge from BERT into a model with large parameters are not efficient due to their large-scale and high computational cost. |
| Approach: | They propose a sentence representation approximating oriented distillation framework that can distill pre-trained BERT into a simple LSTM based model without specifying tasks. |
| Outcome: | The proposed model outperforms other distillation methods and larger models on multiple NLP tasks with efficiency well-improved. |
DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking. |
| Approach: | They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss. |
| Outcome: | Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity. |
Activating Distributed Visual Region within LLMs for Efficient and Effective Vision-Language Training and Inference (2025.acl-long)
Copied to clipboard
| Challenge: | Existing Large Vision-Language Models (LVLMs) learn visual capacity through visual instruction tuning. |
| Approach: | They propose a method for LVLMs to be trained by selective layers tuning . they propose removing non-critical layers outside the visual region . |
| Outcome: | The proposed approach preserves nearly 99% of visual performance and improves textual task results while reducing training time. |
Robustness Testing of Language Understanding in Task-Oriented Dialog (2021.acl-long)
Copied to clipboard
Jiexi Liu, Ryuichi Takanobu, Jiaxin Wen, Dazhen Wan, Hongguang Li, Weiran Nie, Cheng Li, Wei Peng, Minlie Huang
| Challenge: | a lack of systematic studies on the robustness of language understanding models in task-oriented dialog systems is limiting . authors propose a model-agnostic toolkit LAUG to approximate natural language perturbations . |
| Approach: | They propose a model-agnostic toolkit LAUG to approximate natural language perturbations for testing the robustness of language understanding models in task-oriented dialog systems. |
| Outcome: | The proposed toolkit reveals critical robustness issues in state-of-the-art models. |
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)
Copied to clipboard
Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang
| Challenge: | Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks. |
| Approach: | They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes. |
| Outcome: | The proposed training framework significantly improves upon translation baselines. |
Altogether: Image Captioning via Re-aligning Alt-text (2024.emnlp-main)
Copied to clipboard
Hu Xu, Po-Yao Huang, Xiaoqing Tan, Ching-Feng Yeh, Jacob Kahn, Christine Jou, Gargi Ghosh, Omer Levy, Luke Zettlemoyer, Wen-tau Yih, Shang-Wen Li, Saining Xie, Christoph Feichtenhofer
| Challenge: | Existing captioning models ignore existing alt-text metadata and lack transparency if training data is unknown. |
| Approach: | They propose an approach to edit and re-align alt-texts associated with images using human annotation. |
| Outcome: | The proposed approach improves image captions and improves text-to-image generation and zero-shot image classification tasks. |
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (2025.findings-emnlp)
Copied to clipboard
Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang
| Challenge: | Existing knowledge poisoning attacks against RAG systems require multiple poisoned documents or can only function effectively on simplistic queries. |
| Approach: | They propose a more realistic knowledge poisoning attack that poisons only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. |
| Outcome: | The proposed attack achieves success by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. |
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. |
| Approach: | They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description. |
| Outcome: | The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset. |
Multilingual Collaborative Defense for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing safeguards for Large Language Models are vulnerable to "jailbreaking" harmful queries. |
| Approach: | They propose a learning method that optimizes a continuous soft safety prompt automatically to facilitate multilingual safeguarding of LLMs. |
| Outcome: | The proposed method outperforms previous approaches in multilingual jailbreak defense while exhibiting strong cross-lingual generalization. |
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking (2022.findings-emnlp)
Copied to clipboard
Yinghui Li, Shirong Ma, Qingyu Zhou, Zhongli Li, Li Yangning, Shulin Huang, Ruiyang Liu, Chao Li, Yunbo Cao, Haitao Zheng
| Challenge: | Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors. |
| Approach: | They propose a framework which renders Chinese Spell Checking model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning. |
| Outcome: | The proposed framework renders the CSC model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning. |
A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning (D19-1)
Copied to clipboard
| Challenge: | Existing models for reading comprehension and question answering do not support discrete reasoning abilities. |
| Approach: | They propose a reading comprehension model that uses a multi-type answer predictor and a multiple-span extraction method to produce one or multiple text spans. |
| Outcome: | The proposed model achieves 79.9 F1 on the DROP hidden test set, creating new state-of-the-art results. |
LogiGraph: Logical Reasoning with Contrastive Learning and Lightweight Graph Networks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods emphasize contextual semantics while others pay more attention to explicit logical features. Existing models utilize graph convolutional networks (GCN) for node updates, still exhibiting some shortcomings. |
| Approach: | They propose a logical reasoning method with contrastive learning and lightweight graph networks (LogiGraph) they employ conjunction and punctuation marks as two types of edges to construct a dual graph. |
| Outcome: | The proposed method improves the GCN and employs conjunction and punctuation marks as two types of edges to construct a dual graph. |
Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) training with Mixture-of-Experts policies remains fragile and prone to reward collapse. |
| Approach: | They propose a router shift-based policy optimization method that computes a per-token router-shift ratio conditioned on the previously activated experts and applies stop-gradient and a lower-bound floor. |
| Outcome: | The proposed method achieves better performance and greater stability than previous methods. |
Rethinking Denoised Auto-Encoding in Language Pre-Training (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained models such as BERT have achieved success in learning sequence representations, but they tend to learn representations that are covariant with the noise of pre-training. |
| Approach: | They propose to train self-trained models to learn noise invariant sequence representations . they encourage consistency between original sequence and corrupted version via unsupervised instance-wise training signals. |
| Outcome: | The proposed model improves on 11 natural language understanding and cross-modal tasks and achieves 0.6% gain on GLUE benchmarks and 0.8% increment on NLVR2 . |
Refiner: Restructure Retrieved Content Efficiently to Advance Question-Answering Capabilities (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. |
| Approach: | They propose an end-to-end extract-and-restructure paradigm that leverages a single decoder-only LLM to adaptively extract query-relevant contents verbatim along with the necessary context. |
| Outcome: | Experiments show that a trained Refiner outperforms state-of-the-art RAG and compressing approaches in multiple tasks. |
"Newspaper Eat" Means "Not Tasty": A Taxonomy and Benchmark for Coded Language in Real-World Chinese Online Reviews (2026.acl-long)
Copied to clipboard
| Challenge: | Current language models handle coded language poorly, with limited real-world datasets and clear taxonomies. |
| Approach: | They propose a taxonomy that captures common encoding strategies including phonetic, orthographic, and cross-lingual substitutions. |
| Outcome: | The proposed model fails to detect or understand coded language in Chinese reviews . negative reviews can expose users to social pressure, retaliation, or reduced visibility . |
FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE Pipelining (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training LLMs with Mixture-of-Experts (MoE) architecture on long sequences are limited by the insufficient computation. |
| Approach: | They propose a MoE training system that enables token-level overlapping across entire Transformer blocks through novel attention-MoE pipelining. |
| Outcome: | The proposed system achieves 1.49x and 2.72x speedup over state-of-the-art token-level overlapping and non-overlapping baselines on GPT-MoE models with sequences up to 32K tokens. |
New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to digitize ancient Chinese texts and extract information from them are shallow and inconsistent with modern realities. |
| Approach: | They propose to expand ancient Chinese datasets using large language model . they focus on Great Compendium of Myriad Flowers, an ancient plants dataset . |
| Outcome: | The proposed model can extract plant-related information from classical Chinese poetry and prose. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)
Copied to clipboard
Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. |
| Approach: | They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer. |
| Outcome: | The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA. |
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning? (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable progress in reasoning, but are resource-intensive and require large curated datasets. |
| Approach: | They propose a framework that leverages the behavioral divergence between a stronger expert model and a weaker amateur model. |
| Outcome: | The proposed framework improves accuracy by up to 28.1% while reducing time consumption by 90% and tuning token usage by 99%. |
Towards Generalizable and Robust Text-to-SQL Parsing (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Text-to-SQL parsers must be generalizable and robust against input perturbations. |
| Approach: | They propose a novel framework to learn text-to-SQL parsing in stages to improve parser's ability to acquire general SQL knowledge instead of capturing spurious patterns. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the Spider, SParC, and CoSQL datasets. |
Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt (2024.naacl-long)
Copied to clipboard
Yongqi Wang, Ruofan Hu, Rongjie Huang, Zhiqing Hong, Ruiqi Li, Wenrui Liu, Fuming You, Tao Jin, Zhou Zhao
| Challenge: | Recent singing-voice-synthesis methods lack ability to control style attributes of synthesized singing. |
| Approach: | They propose a singing-voice-synthesis method that enables attribute controlling on singer gender, vocal range and volume with natural language. |
| Outcome: | The proposed method achieves favorable control ability and audio quality. |
GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level (D19-1)
Copied to clipboard
| Challenge: | SQA is an emerging application of NLP in the medical, geography, and legal domains. |
| Approach: | They propose a dataset of 1,981 scenarios and 4,110 multiple-choice questions in geography domain at high school level. |
| Outcome: | The proposed dataset consists of 1,981 scenarios and 4,110 multiple-choice questions in the geography domain at high school level. |
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
| Challenge: | Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data. |
| Approach: | They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs. |
| Outcome: | The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback. |
MGPO: Thinking with Images via Multi-Turn Grounding-Based Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art large multimodal models face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. |
| Approach: | They propose a multi-turn grounding-based policy optimization framework that enables LMMs to iteratively focus on key visual regions by automatically cropping sub-images based on model-predicted grounding coordinates within a multiple-turn conversation framework. |
| Outcome: | The proposed framework improves on Qwen2.5-VL-7B with 21K samples and surpasses OpenAI’s o1 and GPT-4o models on the out-of-distribution (OOD) V* Bench. |
Evidence Retrieval is almost All You Need for Fact Verification (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evidence retrieval methods adopt a trivial retrieval strategy, resulting in task-irrelevant evidence and undesirable performance. |
| Approach: | They propose a framework for evidence retrieval and joint fact verification that integrates two modules. |
| Outcome: | The proposed framework improves evidence retrieval and claims verification on a FEVER dataset. |
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)
Copied to clipboard
Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li
| Challenge: | Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences. |
| Approach: | They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses. |
| Outcome: | The proposed framework outperforms baseline methods in real-time and in real applications. |
Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored . |
| Approach: | They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries. |
| Outcome: | The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries . |
Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)
Copied to clipboard
Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang
| Challenge: | Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well. |
| Approach: | They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet. |
| Outcome: | The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future. |
MOA: Multi-Objective Alignment for Role-Playing Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work on role-playing agents relies on supervised fine-tuning or reinforcement learning with scalarized rewards, but these approaches do not address the coordination of multiple reward dimensions during optimization. |
| Approach: | They propose a reinforcement-learning framework that enables multi-dimensional, fine-grained rubric optimization for general RPAs. |
| Outcome: | Experiments on PersonaGym and RoleMRC show that MOA improves multi-dimensional role-playing performance over supervised and standard RL baselines. |
Co-Evolving LLMs and Embedding Models via Density-Guided Preference Optimization for Text Clustering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for text clustering use static pseudo-oracles, i.e., unidirectionally querying them for similarity assessment or data augmentation. |
| Approach: | They propose a training framework that enables bidirectional refinement between LLMs and embedding models by using task-aware prompts to guide the LLM in generating interpretations for the input texts. |
| Outcome: | Experiments on 14 benchmark datasets across 5 tasks demonstrate the effectiveness of the proposed training framework. |
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)
Copied to clipboard
Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin
| Challenge: | Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain . |
| Approach: | They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora. |
| Outcome: | The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions. |
Fast and Accurate Neural Machine Translation with Translation Memory (2021.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge demonstrates the superiority of TM-based neural machine translation only on TM specialized tasks . |
| Approach: | They propose a translation memory-based approach to machine translation using a single bilingual sentence as its TM. |
| Outcome: | The proposed approach surpasses baselines on two general tasks and improves on the TM-specialized translation tasks. |
S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering (2023.acl-short)
Copied to clipboard
| Challenge: | Existing question answering systems use a retriever-reader framework to answer multi-hop questions . existing models lack retrieval, selector, and reasoner capabilities . |
| Approach: | They propose a three-stage text tableQA framework which comprises of retriever, selector, and reasoner. |
| Outcome: | The proposed framework outperforms baseline methods in the few-shot setting and ranks first on the HybridQA leaderboard. |
Supervised Optimism Correction: Be Confident When LLMs Are Sure (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated remarkable success across diverse tasks such as instruction following, code generation, and medical diagnosis. |
| Approach: | They propose a supervised fine-tuning-based auxiliary loss for Q-value estimations during supervised refinement. |
| Outcome: | The proposed method outperforms beam search on GSM8K, MATH, and GAOKAO on reasoning benchmarks. |
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (2024.emnlp-main)
Copied to clipboard
Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Current research emphasizes LLMs’ capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. |
| Approach: | They propose a multi-level benchmark to evaluate the robustness of large language models in tool learning by establishing five external environments with varying levels of noise. |
| Outcome: | The proposed model outperforms the GPT-4 model in tool learning in three critical phases: tool selection, parameter identification, and content filling. |
Two-Stage Parameter Alignment for Multi-LoRA Merging in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Current general model merging methods are prone to parameter interference problems . a novel two-stage parameter alignment framework is proposed to address this problem . |
| Approach: | They propose a two-stage parameter alignment framework that integrates low-rank LoRAs . they propose to reduce the computational complexity of existing methods by preserving fine-grained functions . |
| Outcome: | The proposed framework exhibits greater robustness than other methods in high-rank and high-interference scenarios while preserving fine-grained functions. |
Improving Seq2Seq Grammatical Error Correction via Decoding Interventions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to grammatical error correction (GEC) are sequence-to-sequence and sequence-edit. |
| Approach: | They propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally. |
| Outcome: | The proposed framework outperforms baselines and state-of-the-art methods on English and Chinese datasets. |
CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Asynchronous psychological counseling (APC) is a crucial mental health service modality that transcends temporal and spatial constraints. |
| Approach: | They propose a self-optimizing multi-agent framework for counseling dialogue generation, CFlowPsy, which utilizes real anonymized counseling cases as seed data to synthesize diverse problem-solving-oriented APC conversations through large language models. |
| Outcome: | The proposed framework synthesizes diverse problem-solving-oriented APC conversations through large language models. |
LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hierarchical transducers suffer from negative transfer and unstable target-language generation, while training separate models for each direction is computationally prohibitive. |
| Approach: | They propose a hierarchical transducer with language-conditional Mixture-of-Experts adapters to improve multilingual joint automatic speech recognition and speech translation. |
| Outcome: | Experiments on Europarl-ST (9 languages, 72 directions) show that LCMA-SRT improves both ASR and ST within a single joint model, reducing average WER and improving BLEU and COMET over strong hierarchical transducer baselines. |
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning (2026.findings-acl)
Copied to clipboard
Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang
| Challenge: | Large Language Models (LLMs) exhibit severe hallucinations, which undermine reliability of automated scientific document understanding systems. |
| Approach: | They propose a framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization. |
| Outcome: | The proposed framework significantly reduces hallucination rates and improves overall accuracy on the MeasEval benchmark. |
The Proxy Presumption: From Semantic Embeddings to Valid Social Measures (2026.acl-long)
Copied to clipboard
| Challenge: | Natural Language Processing is evolving into a primary instrument for Computational Social Science . but, this transition faces a validity challenge: the “Proxy Presumption” . |
| Approach: | They propose a method to bridge the gap between semantic embeddings and valid social measures by using the Construct Validity Protocol. |
| Outcome: | The proposed method bridges the gap between semantic embeddings and valid social measures . it reduces confounding in embeddable space and provides a standardized Validity Suite . |
Learn and Consolidate: Continual Adaptation for Zero-Shot and Multilingual Neural Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual neural machine translation models perform poorly on language pairs with no parallel corpus. |
| Approach: | They propose a two-stage approach that encourages original models to acquire language-agnostic multilingual representations from new data and preserves the model architecture without introducing parameters. |
| Outcome: | The proposed approach improves performance in translation directions where existing models are weak and mitigates degeneration in the well-performing translation directions, offering flexibility in the real-world scenario. |
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)
Copied to clipboard
Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang
| Challenge: | Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level. |
| Approach: | They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context. |
| Outcome: | The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set. |
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction (2026.acl-long)
Copied to clipboard
Ziyou Jiang, Mingyang Li, Junjie Wang, Yuekai Huang, Jie Huang, Zhiyuan Chang, Zhaoyang Li, Qing Wang
| Challenge: | Existing methods for harmful meme detection only learn the combination of harmful elements and lack understanding of these implicit expressions. |
| Approach: | They propose a method that detects harmful memes by replicating the design concept of malicious users. |
| Outcome: | The proposed method achieves the highest accuracy with 81.1% and has slight accuracy decreases when generalized to type-shifting and temporal-evolving memes. |
Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning (2023.acl-long)
Copied to clipboard
Barun Patra, Saksham Singhal, Shaohan Huang, Zewen Chi, Li Dong, Furu Wei, Vishrav Chaudhary, Xia Song
| Challenge: | XY-LENT: X-Y bitext enhanced Language ENcodings achieves state-of-the-art performance over 5 cross-lingual tasks within all model size bands. |
| Approach: | They propose a method for building multilingual representation models that are competitive with existing models and more parameter efficient. |
| Outcome: | The proposed model outperforms XLM-R XXL and is 5x and 6x smaller respectively. |
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)
Copied to clipboard
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
| Challenge: | AEGIS examines whether current models can effectively audit AI-generated images in academic papers. |
| Approach: | They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics. |
| Outcome: | AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis. |
latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent advances in text generation have limited applications due to multimodality problem. |
| Approach: | They propose a method which uses latent variables to capture word categorical information and invoke an advanced curriculum learning technique to overcome multi-modality problem. |
| Outcome: | The proposed method outperforms strong baselines without an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm. |
Affective and Dynamic Beam Search for Story Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | AffGen introduces ‘intriguing twists’ in narratives by employing two novel techniques—Dynamic Beam Sizing and Affective Reranking. |
| Approach: | They propose to use dynamic beam sizing and affective reranking to generate interesting stories using two novel techniques. |
| Outcome: | The proposed method outperforms baseline models in generating affectively charged and interesting narratives. |
MRE-MI: A Multi-image Dataset for Multimodal Relation Extraction in Social Media Posts (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to Multimodal Relation Extraction focus on single image scenarios . current approaches focus on text paired with a single image, ignoring valuable insights provided by remaining images. |
| Approach: | They propose a human-annotated dataset that includes multi-image and single-image instances for relation extraction. |
| Outcome: | The proposed model significantly improves relation extraction in multi-image scenarios. |
When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation (2021.acl-short)
Copied to clipboard
| Challenge: | Subword segmentation algorithms can produce sub-optimal segmentation when the target language is rich in morphological changes or there is not enough data for learning compact composition rules. |
| Approach: | They compare character-based and subword-based neural machine translation systems . they find character-driven models are better at handling morphological phenomena . |
| Outcome: | The character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains. |
FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)
Copied to clipboard
Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao
| Challenge: | Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge . |
| Approach: | They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance. |
| Outcome: | The proposed model improves performance on e-commerce image-text retrieval task by a large margin. |
Reverse Preference Optimization for Complex Instruction Following (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for identifying and evaluating preference pairs with multiple constraints are noisy. |
| Approach: | They propose a method that dynamically reverses constraints to ensure the chosen response is perfect. |
| Outcome: | The proposed method reduces noise in preference pairs by reversing constraints to ensure the chosen response is perfect. |
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have achieved great success in various NLP tasks, but the vast model parameters pose challenges in downstream fine-tuning. |
| Approach: | They propose a task-agnostic prompting strategy that analyzes each dialogue utterance before task execution to enhance LLMs' comprehension in multi-turn dialogues. |
| Outcome: | The proposed strategy outperforms other zero-shot prompts and matches or exceeds efficacy of few-shot ones. |
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play (2026.acl-long)
Copied to clipboard
Xiachong Feng, Deyi Yin, Xiaocheng Feng, Yi Jiang, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Qiming Li, Yuxuan Gu, Bing Qin, Lingpeng Kong
| Challenge: | Existing self-play approaches to developing general reasoning in language models rely on terminal game outcomes. |
| Approach: | They propose a game-based reasoning transfer model that addresses two barriers to reasoning transfer. |
| Outcome: | The proposed model improves mathematical reasoning, general reasoning, and code generation benchmarks. |
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio. |
| Approach: | They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
| Outcome: | The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
Text Level Graph Neural Network for Text Classification (D19-1)
Copied to clipboard
| Challenge: | Recent researches have explored graph neural network (GNN) techniques on text classification, but they are faced with the problems of fixed corpus level graph structure which don’t support online testing and high memory consumption. |
| Approach: | They propose a graph neural network model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus. |
| Outcome: | The proposed model outperforms existing models on several text classification datasets even with consuming less memory. |
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning (2026.findings-acl)
Copied to clipboard
Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang
| Challenge: | Large language model (LLM)-integrated applications face security vulnerabilities from prompt injection (PI) attacks. |
| Approach: | They propose a model enhancement method that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning to enable LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. |
| Outcome: | The proposed method outperforms baselines in three critical dimensions while maintaining utility performance without degradation. |
Exploring Better Text Image Translation with Multimodal Codebook (2023.acl-long)
Copied to clipboard
| Challenge: | Current studies on text image translation face bottlenecks due to lack of a publicly available dataset and poor optical character recognition. |
| Approach: | They propose a text image translation model with a multimodal codebook and an OCR dataset for Chinese-English translation. |
| Outcome: | The proposed model can associate the image with relevant texts, providing useful supplementary information for translation. |
Estimating Soft Labels for Out-of-Domain Intent Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect out-of-dominance (OOD) intents are limited by the lack of OOD samples. |
| Approach: | They propose an adaptive soft pseudo labeling method that can estimate soft labels for pseudo OOD samples when training OOD detectors. |
| Outcome: | The proposed method outperforms competing methods on three benchmark datasets and consistently outperformed previous methods. |
Dynamic Emotion and Personality Profiling for Multimodal Deception Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for deception detection lack sample-level dynamic annotations for emotions and personality. |
| Approach: | They propose a multi-model multi-prompt annotation scheme and a strict label quality evaluation standard for deception, emotion, and personality annotations. |
| Outcome: | The proposed framework outperforms state-of-the-art models on the MDPE and DDEP datasets. |
EchoMLLM: Incentivizing Echocardiographic Video Understanding with Keyframe Grounding and Report Generation (2026.findings-acl)
Copied to clipboard
Heyu Huang, Wanran Sun, Chi Chen, Bo Chen, Zonghao Guo, Yuhua Li, Ruixuan Li, Kunlun He, Maosong Sun
| Challenge: | Echocardiography analysis requires a dual capability: rigorous quantitative keyframe localization and comprehensive qualitative synthesis. |
| Approach: | They propose a unified framework designed for real-world echocardiography video understanding. |
| Outcome: | a new framework is designed to support real-world echocardiography video understanding . it reduces temporal grounding errors by up to 76% and improves report generation quality by 65% . |
LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)
Copied to clipboard
Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li
| Challenge: | Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases. |
| Approach: | They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities. |
| Outcome: | The proposed model outperforms open-source models but struggles on longer contexts. |
PaSa: An LLM Agent for Comprehensive Academic Paper Search (2025.acl-long)
Copied to clipboard
| Challenge: | We introduce PaSa, an advanced Paper Search agent powered by large language models . despite being trained on synthetic data, PaSA outperforms existing baselines on RealScholarQuery . |
| Approach: | They introduce PaSa, an advanced Paper Search agent powered by large language models . they optimize PaSA using a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained queries . |
| Outcome: | The paper analyzes the performance of a paper search agent using a synthetic dataset . it significantly outperforms existing benchmarks on RealScholarQuery . |
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2021.acl-long)
Copied to clipboard
Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou
| Challenge: | Existing pre-training objectives do not explicitly model relational facts in text . Experimental results show that ERICA can improve typical PLMs on several language understanding tasks, including relation extraction, entity typing and question answering. |
| Approach: | They propose a contrastive learning framework ERICA to obtain a deep understanding of entities and relations in text. |
| Outcome: | The proposed framework can improve PLMs on several language understanding tasks, especially under low-resource settings. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for dialog understanding only consider self-augmented dialogs as positive samples and treat all other dialogs like negative ones. |
| Approach: | They propose a tree-structured pre-trained conversation model which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training. |
| Outcome: | The proposed model can achieve state-of-the-art results on the DialoGLUE benchmark. |
DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on cross-modal attention at the fusion stage, but modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modulation and decision-making. |
| Approach: | They propose a framework to align navigation-related modalities before fusion by cross-modal contrastive learning. |
| Outcome: | The proposed framework integrates with the majority of existing models, resulting in improved navigation performance on various VLN benchmarks, including R2R, R4R, and CVDN. |
DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents (2026.acl-long)
Copied to clipboard
JunShuo Zhang, Chengrui Huang, Feng Guo, Zihan Li, Ke Shi, Menghua Jiang, Jiguo Yu, Shuo Shang, Shen Gao
| Challenge: | Existing approaches to large language model (LLM) agents that follow the sequential "reason-then-act" paradigm suffer from limited exploration and incomplete environmental understanding as they interact with only a single environment per step. |
| Approach: | They propose a paradigm that enables an agent to interact with multiple environments simultaneously and share cross-trajectory experiences. |
| Outcome: | The proposed paradigm achieves state-of-the-art (SOTA) success rates while maintaining comparable efficiency to strong sequential baselines. |
Dual Low-Rank Multimodal Fusion (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tensor-based fusion methods make poor use of fine-grained temporal dynamics of multimodal sequential features. |
| Approach: | They propose a novel multimodal fusion method called Fine-Grained Temporal Low-Rank Multimodal Fusion that uses low-rank tensor approximation along dual dimensions of input features. |
| Outcome: | The proposed method outperforms the state-of-the-art tensor-based methods with a similar computational complexity. |
Unveiling the Implicit Toxicity in Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, but LLMs can generate diverse implicit toxic output that are difficult to detect via simply zero-shot prompting. |
| Approach: | They propose a reinforcement learning based attacking method to induce the implicit toxic outputs in large language models by fine-tuning toxicity classifiers. |
| Outcome: | The proposed method generates implicit toxic outputs that are difficult to detect via zero-shot prompting on five widely-adopted toxicity classifiers. |
TemplateGEC: Improving Grammatical Error Correction with Detection Template (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for grammatical error correction (GEC) have been developed. |
| Approach: | They propose a method which integrates the detection labels from a Seq2Edit model to construct a template as the input. |
| Outcome: | The proposed method can perform human-in-the-loop error correction tasks. |
MemRec: Collaborative Memory-Augmented Agentic Recommender System (2026.acl-long)
Copied to clipboard
Weixin Chen, Yuhan Zhao, Jingyuan Huang, Zihe Ye, Mingxuan Ju, Tong Zhao, Neil Shah, Li Chen, Yongfeng Zhang
| Challenge: | Existing recommender systems rely on semantic user and item memories to make predictions, but these memories are kept in isolation. |
| Approach: | They propose a framework that architecturally decouples memory management from reasoning to decouple memory management and reasoning from the user and item memories. |
| Outcome: | The proposed framework decouples memory management from reasoning and achieves state-of-the-art performance on four benchmarks. |
Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark (2022.findings-emnlp)
Copied to clipboard
Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng
| Challenge: | a number of safety concerns hinder the deployment of open-domain dialog systems, such as offensive languages and toxic behaviors, such social bias is difficult to detect. |
| Approach: | They propose a Dial-Bias Framework for analyzing social bias in conversations . they introduce a Chinese social bias dialog dataset and conduct in-depth ablation studies . |
| Outcome: | The proposed framework is the first annotated Chinese social bias dialog dataset . the proposed framework also provides a fine-grained dialog bias measurement benchmark . |
Enhancing LLM Language Adaption through Cross-lingual In-Context Pre-training (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing cross-lingual transfer are limited by parallel resources and lack linguistic and domain coverage. |
| Approach: | They propose a cross-lingual in-context pre-training approach that leverages semantically related bilingual Wikipedia documents to enhance cross-linguistic transfer. |
| Outcome: | The proposed approach improves multilingual performance on three models across six target languages. |
AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)
Copied to clipboard
Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu
| Challenge: | Significant concerns emerge when addressing cultural sensitivity and local values. |
| Approach: | They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. |
| Outcome: | The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks. |
DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation (2025.findings-acl)
Copied to clipboard
Zhonghao Sun, Zhiliang Tian, Yiping Song, Yuyi Si, Juhua Zhang, Minlie Huang, Kai Lu, Zeyu Xiong, Xinwang Liu, Dongsheng Li
| Challenge: | Existing methods to fine-tune large language models pose privacy risks . researchers have synthesized data with strong generation capabilities closed-source LLMs to alleviate this problem . |
| Approach: | They propose to combine general LLMs with genetic algorithm to produce relevant and diverse synthetic text under differential privacy constraints. |
| Outcome: | The proposed method significantly improves the performance of the model in downstream tasks while ensuring privacy. |
SENT: Sentence-level Distant Relation Extraction via Negative Training (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use bag labels, which introduce noise, to train the model. |
| Approach: | They propose to use negative training to train a model using complementary labels to separate the noisy data from the training data. |
| Outcome: | The proposed method improves on previous methods on sentence-level evaluation and de-noise effect. |
SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for hateful video detection rely on multimodal feature fusion . existing methods rely only on blind feature mixing, which leads to feature dilution . |
| Approach: | They propose a framework that shifts from blind feature mixing to decision-level arbitration . it instantiates disentangled experts to rigorously preserve modality-specific semantics . |
| Outcome: | The proposed framework outperforms state-of-the-art methods on HateMM and MultiHateClip benchmarks. |
BioGraphia: A LLM-Assisted Biological Pathway Graph Annotation Platform (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing methods for obtaining pathway information from biomedical literature rely on simplifying assumptions that limit their ability to capture true complexity of biological reactions. |
| Approach: | They propose a web-based platform to facilitate collaborative pathway graph annotation. |
| Outcome: | The platform supports multi-user collaboration with real-time monitoring, curation, and interactive pathway graph visualization. |
A Survey on Open Information Extraction from Rule-based Model to Large Language Model (2024.findings-emnlp)
Copied to clipboard
Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, Yue Zhang
| Challenge: | Open Information Extraction (OpenIE) is a key NLP task aimed at extracting structured information from unstructured text sources. |
| Approach: | They propose to categorize OpenIE into rule-based, neural, and pre-trained large language models and discuss each within a chronological framework. |
| Outcome: | The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework. |
StructuralLM: Structural Pre-training for Form Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | Existing pre-trained language models focus on text-only representation, neglecting cell-level layout information. |
| Approach: | They propose a pre-training approach to leverage cell and layout information from scanned documents. |
| Outcome: | The proposed model achieves state-of-the-art in various downstream tasks . it uses 2Dposition embeddings to model word-level layout information . |
MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown their strong ability in the field of machine translation, yet they suffer from high computational cost and latency. |
| Approach: | They propose a framework which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. |
| Outcome: | The proposed framework transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. |
Biomedical Event Extraction based on Knowledge-driven Tree-LSTM (N19-1)
Copied to clipboard
| Challenge: | Biomedical event extraction requires domain-specific knowledge and deep understanding of complex contexts. |
| Approach: | They propose a knowledge base-driven tree-structured long short-term memory networks framework . tree-LSTM framework incorporates dependency structures and entity properties from ontologies . |
| Outcome: | The proposed framework is based on the BioNLP shared task with Genia dataset and achieves state-of-the-art results. |
Revisiting a Pain in the Neck: A Semantic Reasoning Benchmark for Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Semantic phrases (SP) are lexical combinations whose meanings or usages may not be fully derived from their individual components. |
| Approach: | They propose to consolidate existing multiword expression resources into a unified testbed to assess language models in semantic phrase processing tasks. |
| Outcome: | The evaluation suite covers idiomatic expressions, noun compounds, and verbal constructions. |
MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)
Copied to clipboard
Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin
| Challenge: | Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images. |
| Approach: | They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs. |
| Outcome: | The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks. |
CMDL: A Large-Scale Chinese Multi-Defendant Legal Judgment Prediction Dataset (2024.findings-acl)
Copied to clipboard
| Challenge: | Legal Judgment Prediction (LJP) has attracted significant attention in recent years. |
| Approach: | They propose a large-scale Chinese Multi-Defendant LJP dataset . they propose case-level evaluation metrics dedicated for the multi-defendant scenario . |
| Outcome: | The proposed methods show weaknesses when applied to cases involving multiple defendants. |
Logits Reranking via Semantic Labels for Hard Samples in Text Classification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on text classification models ignores the semantic information inherent in labels, treating them as one-hot vectors. |
| Approach: | They propose a model-agnostic method that leverages label semantics and auto detection of hard samples to improve classification accuracy. |
| Outcome: | The proposed method shows significant improvements across different PLMs. |
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020.acl-demos)
Copied to clipboard
Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
| Challenge: | ConvLab-2 inherits Convlab's framework but integrates more powerful dialogue models and supports more datasets. |
| Approach: | They present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models and perform an end-to-end evaluation. |
| Outcome: | The new tool inherits ConvLab's framework and extends it by integrating many recently proposed state-of-the-art dialogue models. |
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)
Copied to clipboard
Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si
| Challenge: | Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. |
| Approach: | They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. |
| Outcome: | The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. |
LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search (2025.naacl-long)
Copied to clipboard
Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, Jiatong Li, Tong Xie, Xiaoshui Huang, Shufei Zhang, Marco Pavone, Yuqiang Li, Wanli Ouyang, Dongzhan Zhou
| Challenge: | LLaMA-Berry is an advanced mathematical reasoning framework to enhance the problem-solving ability of large language models (LLMs). |
| Approach: | They propose a Monte Carlo Tree Search and Self-Refine framework to optimize reasoning paths and a pairwise reward model to evaluate different paths globally. |
| Outcome: | The proposed framework overcomes inefficiencies and limitations of step-wise and greedy search algorithms, enabling more efficient exploration of solution spaces. |
Continual Prompt Tuning for Dialog State Tracking (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to train a model on a sequence of tasks are not efficient enough to mitigate catastrophic forgetting. |
| Approach: | They propose a parameter-efficient framework that prevents forgetting and enables knowledge transfer between tasks by learning and freezing a pre-trained model. |
| Outcome: | The proposed framework avoids forgetting and enables knowledge transfer between tasks. |
EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)
Copied to clipboard
Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu
| Challenge: | Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values. |
| Approach: | They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction. |
| Outcome: | The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. |
ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings (2024.emnlp-main)
Copied to clipboard
| Challenge: | Attaching suffixes to harmful instructions can hack the defense of Large language models (LLMs) However, due to the unreadable of adversarial suffix, it can be relatively easily penetrated by common defense methods such as perplexity filters. |
| Approach: | They propose an algorithm to embed adversarial suffixes into coherent and understandable text to attack Large language models (LLMs) using a Advbench dataset. |
| Outcome: | The proposed approach reduces the computation time of adversarial suffixes and achieves a much better attack success rate than existing techniques. |
Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies address the problem of translating English data into other languages, but they are limited in form and scale. |
| Approach: | They propose a framework to unify cross-lingual and cross-modal pre-training by using English data. |
| Outcome: | The proposed framework unifies cross-lingual and cross-modal pre-training on different data. |
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression (2025.acl-long)
Copied to clipboard
| Challenge: | gist-based context compression methods can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, but it faces challenges in tasks like synthetic recall. |
| Approach: | They propose two strategies to improve gist-based context compression in large language models. |
| Outcome: | The proposed methods can achieve only slight performance loss on retrieval-augmented generation and long-document QA tasks, but they face challenges in tasks like synthetic recall. |
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)
Copied to clipboard
Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun
| Challenge: | AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery. |
| Approach: | They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows. |
| Outcome: | The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages. |
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge retrieval methods fail to account for interrelationship between knowledge pieces . however, current methods fail in a situation where multiple knowledge pieces are relevant . |
| Approach: | They propose an energy-based retriever that directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately. |
| Outcome: | The proposed retriever outperforms the baseline energy-based retriever in knowledge retrieval tasks. |
Sparse Progressive Distillation: Resolving Overfitting under Pretrain-and-Finetune Paradigm (2022.acl-long)
Copied to clipboard
Shaoyi Huang, Dongkuan Xu, Ian Yen, Yijue Wang, Sung-En Chang, Bingbing Li, Shiyang Chen, Mimi Xie, Sanguthevar Rajasekaran, Hang Liu, Caiwen Ding
| Challenge: | Conventional wisdom in pruning Transformer-based language models is that it reduces model expressiveness, but new research shows pruning increases risk of overfitting when performed at the fine-tuning phase. |
| Approach: | They propose to reduce pruning risk under pretrain-and-finetune paradigm . they propose to use knowledge distillation to improve pruning performance . |
| Outcome: | The proposed method outperforms the leading competitors on the GLUE benchmark. |
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating stories with complex plots rely on detailed prompts, which inadvertently limit the creative potential of the generated stories. |
| Approach: | They propose a retrieval-auGmented stoRy generation framework with a fOrest of eVidEnce to enhance stories’ complexity. |
| Outcome: | The proposed framework enables generating more diverse plotlines from human-written stories. |
Location-Aware Visual Question Generation with Lightweight Models (2023.emnlp-main)
Copied to clipboard
Nicholas Suwono, Justin Chen, Tun Hung, Ting-Hao Huang, I-Bin Liao, Yung-Hui Li, Lun-Wei Ku, Shao-Hua Sun
| Challenge: | a novel task aims to generate engaging questions from location-aware information . a lightweight model can be used to generate such questions . |
| Approach: | They propose a task to generate engaging questions from location-aware data . they represent location-based information with surrounding images and a GPS coordinate . |
| Outcome: | The proposed method outperforms baselines regarding human evaluation and evaluation metrics. |
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)
Copied to clipboard
Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng
| Challenge: | Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence. |
| Approach: | They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics . |
| Outcome: | The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate . |
EvoRoute: Experience-Driven Self-Routing LLM Agent Systems (2026.acl-long)
Copied to clipboard
| Challenge: | EvoRoute is a self-evolving model routing paradigm that transcends static, pre-defined model assignments. |
| Approach: | They propose a model routing paradigm that transcends static, pre-defined model assignments. |
| Outcome: | Experiments on GAIA and BrowseComp+ show that EvoRoute reduces execution cost and latency by over 70%. |
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
You Li, Heyu Huang, Chi Chen, Kaiyu Huang, Chao Huang, Zonghao Guo, Zhiyuan Liu, Jinan Xu, Yuhua Li, Ruixuan Li, Maosong Sun
| Challenge: | Existing MLLMs still struggle to achieve precise grounding in multi-image scenarios. |
| Approach: | They propose a Chain-of-Thought framework that integrates single-image grounding with multi-image comprehension to address this challenge. |
| Outcome: | The proposed model outperforms existing models in multi-image grounding tasks by 24.94% and surpasses larger 70B models. |
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models (2024.acl-short)
Copied to clipboard
| Challenge: | Recent studies have revealed significant deficiencies of LVLMs in understanding visual contents, leaving the gap between current embodied intelligence and large vision-language models (LVLM) . |
| Approach: | They propose to use a benchmark to evaluate LVLMs' spatial understanding of embodied environments to evaluate their ability to understand visual contents. |
| Outcome: | The proposed benchmark is derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective. |
Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on speech-to-singing voice conversion (STS) are limited by the scarcity of paired speech-song data and the suboptimal quality of outputs. |
| Approach: | They propose a self-supervised singing voice pre-training model that transforms a speech-to-singing voice into a paired singing voice. |
| Outcome: | The proposed model improves both STS and singing voice synthesis tasks by combining spoken language and a self-supervised singing voice pre-training model. |
A Length-Extrapolatable Transformer (2023.acl-long)
Copied to clipboard
Yutao Sun, Li Dong, Barun Patra, Shuming Ma, Shaohan Huang, Alon Benhaim, Vishrav Chaudhary, Xia Song, Furu Wei
| Challenge: | Existing Transformers can only deal with the in-distribution size of inputs. |
| Approach: | They propose a relative position embedding to explicitly maximize attention resolution . they also use blockwise causal attention during inference for better resolution a . |
| Outcome: | The proposed model achieves strong performance in interpolation and extrapolation settings. |
3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding (2023.emnlp-main)
Copied to clipboard
| Challenge: | 3D visual grounding aims to localize the desired objects in a 3D point cloud by a free-form language description. |
| Approach: | They propose a relation-aware framework which captures relative spatial relationships between objects and enhances object attributes. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on three benchmarks . it captures relative spatial relationships between objects and enhances object attributes . |
Adaptive Ordered Information Extraction with Deep Reinforcement Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for information extraction follow a fixed extraction order for complex tasks with multiple elements to be extracted in one instance. |
| Approach: | They propose an adaptive ordered IE paradigm to find optimal element extraction order for different instances and a reinforcement learning framework to generate optimal order dynamically. |
| Outcome: | The proposed method beats existing methods and improves on several public datasets. |
The Medical Scribe: Corpus Development and Model Performance Analyses (2020.lrec-1)
Copied to clipboard
Izhak Shafran, Nan Du, Linh Tran, Amanda Perry, Lauren Keyes, Mark Knichel, Ashley Domin, Lei Huang, Yu-hui Chen, Gang Li, Mingqiu Wang, Laurent El Shafey, Hagen Soltau, Justin Stuart Paul
| Challenge: | Existing tools to assist in clinical note generation using audio of provider-patient encounters are lacking. |
| Approach: | They develop an annotation scheme to extract relevant clinical concepts from audio of provider-patient encounters and train a state-of-the-art tagging model. |
| Outcome: | The proposed model is more useful than the F-scores reflect and can be used in clinical notes. |
INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)
Copied to clipboard
Di Wu, Liting Jiang, Bohui Mao, Hongyan Xie, Haoxiang Su, Zhongjiang He, Ruiyu Fang, Shuangyong Song, Hao Huang, Xuelong Li
| Challenge: | Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks. |
| Approach: | They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages. |
| Outcome: | The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages. |
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)
Copied to clipboard
Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng
| Challenge: | Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies. |
| Approach: | They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer. |
| Outcome: | Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks. |
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)
Copied to clipboard
Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted. |
| Approach: | They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space. |
| Outcome: | The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns. |
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization (2022.coling-1)
Copied to clipboard
| Challenge: | Experimental results show that our method outperforms full-model tuning in few-shot abstractive summarization tasks. |
| Approach: | They propose a soft prompts architecture with prompt pre-training and prompt fine-tuning paradigm to support few-shot abstractive summarization. |
| Outcome: | The proposed model outperforms Prompt Tuning and Profix-Tuning on CNN/DailyMail and XSum datasets and outperfies Profix Tuning by a large margin. |
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)
Copied to clipboard
Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi
| Challenge: | Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning. |
| Approach: | They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets. |
| Outcome: | The proposed framework improves CLIP models by exploiting text-image pairs in training. |
"I Don’t Know What to Say": A Fact-Filling Questionnaire Method to Help Non-Experts Talk to LegalAI Assistant (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have greatly expanded the scope of legal AI. |
| Approach: | They propose a method that generates questionnaires to help users refine queries . they leverage an iterative training process that collects valuable questionnaires . |
| Outcome: | The proposed method improves the completeness of queries and ensures the performance of domain-specific models in downstream legal tasks. |
Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)
Copied to clipboard
Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei
| Challenge: | Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other . |
| Approach: | They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations . |
| Outcome: | The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training . |
Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained large language models struggle to perform logical reasoning reliably despite advances in scale and compositionality. |
| Approach: | They propose a Differentiable Symbolic Reasoning framework that uses symbolic programming to improve LMs' logical reasoning abilities. |
| Outcome: | The proposed framework outperforms competitive baselines when faced with systematic changes in sequence length. |
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)
Copied to clipboard
Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou
| Challenge: | Existing work on confidence in LLMs is limited. |
| Approach: | They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level. |
| Outcome: | The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods. |
UTC-IE: A Unified Token-pair Classification Architecture for Information Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Information Extraction (IE) tasks have been solved with different models because of their output structures. |
| Approach: | They propose a Unified Token-pair Classification architecture for Information Extraction that introduces Plusformer on top of the token-pear feature matrix. |
| Outcome: | The proposed approach outperforms task-specific and unified models on all tasks in 10 datasets and achieves better results on 2 joint IE datasets. |
Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing (2026.acl-long)
Copied to clipboard
| Challenge: | Role-playing agents lack a deep understanding of complex human psychological mechanisms. |
| Approach: | They propose a situation-aware framework that decouples personality traits into bidirectional LoRA adapters. |
| Outcome: | Empirical results show that PD-LLM achieves superior performance in both static fidelity and dynamic adaptability. |
Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to update a multilingual model with new language pairs are expensive and time-consuming. |
| Approach: | They propose an entropy-based vocabulary substitution method that walks through new language pairs for incremental learning while remaining the size of the original vocabulary. |
| Outcome: | The proposed method achieves better performance and saves excess overhead in a multilingual machine translation task. |
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing Large Reasoning Models have demonstrated broad application potential, yet their safety and reliability remain critical concerns. |
| Approach: | They conduct a safety evaluation of 13 MLRMs across 5 benchmarks and examine their safety performance. |
| Outcome: | The proposed model improves safety on jailbreak and safety-awareness benchmarks. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)
Copied to clipboard
Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan
| Challenge: | Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). |
| Approach: | They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge. |
| Outcome: | The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples. |
Multimedia Generative Script Learning for Task Planning (2023.findings-acl)
Copied to clipboard
| Challenge: | Goal-oriented generative script learning aims to generate subsequent steps to reach a specific goal . ability to capture historical states in visual modalities provides detailed information not covered by text . |
| Approach: | They propose a goal-oriented generative script learning task to generate subsequent steps by tracking historical states in both text and vision modalities. |
| Outcome: | The proposed task outperforms baselines in three aspects of the current task. |
Synergistic Augmentation: Enhancing Cross-Domain Zero-Shot Slot Filling with Small Model-Assisted Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to slot filling are limited due to data scarcity and timeconsuming efforts. |
| Approach: | They propose a framework that harnesses the power of a small model to augment inferential capabilities of LLMs without additional training. |
| Outcome: | The proposed framework improves slot filling performance on a spoken language dataset and a NER dataset. |
MNER-MI: A Multi-image Dataset for Multimodal Named Entity Recognition in Social Media (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent research has focused on multimodal named entity recognition (MNER) but current approaches focus on text and a single accompanying image, leaving a significant research gap in multi-image scenarios. |
| Approach: | They propose to construct a human-annotated MNER dataset with multiple images called MNER-MI and a temporal prompt model with multiple image to address the new challenges in multi-image scenarios. |
| Outcome: | The proposed method achieves state-of-the-art results on both MNER-MI and MNER -MI-Plus, demonstrating its effectiveness. |
Generative Entity Typing with Curriculum Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Entity typing fails to assign an entity to the types beyond the predefined type set. |
| Approach: | They propose a generative entity typing paradigm that assigns types to entities . traditional classification-based approaches fail to assign entities to the types beyond the predefined set . they employ curriculum learning to train the model on heterogeneous data . |
| Outcome: | The proposed model outperforms the state-of-the-art model on heterogeneous training data. |
FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | LLM-based agents are susceptible to undesired planning hallucinations when lacking specific knowledge for expertise-intensive tasks. |
| Approach: | They propose a benchmark to evaluate the efficacy of workflow-guided agent planning by formalizing different formats of workflow knowledge. |
| Outcome: | The proposed benchmark aims to improve the planning reliability of LLM-based agents by incorporating external workflow-related knowledge. |
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment (2021.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that denoising word alignment improves cross-lingual transferability . most applications and resources are still English-centric, making non-English users hard to access. |
| Approach: | They propose to denoise word alignment as a cross-lingual pre-training task . they first self-label word alignments for parallel sentences and then mask tokens . |
| Outcome: | The proposed model improves cross-lingual transferability on token-level tasks, especially on question answering, and structured prediction. |
Self-Adjust Softmax (2025.emnlp-main)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Guoxuan Chen, Han Shi, Jing Xiong, Xiaozhe Ren, Chao Huang, Zhenguo Li, Yu Li
| Challenge: | Usually, tokens with larger attention scores are important for the final prediction. |
| Approach: | They propose to modify softmax(z) to z softmax and its normalized variant to improve the Transformer attention mechanism by making minor adjustments to the softmax function. |
| Outcome: | The proposed model provides enhanced gradient properties compared to the vanilla softmax function. |
Inquisitive Question Generation for High Level Text Comprehension (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing data-driven questions generate questions that fill gaps in knowledge . a dataset of 19K questions is used to generate meaningful questions . |
| Approach: | They propose a dataset of 19K questions that are elicited while a person is reading a document. |
| Outcome: | The proposed model generates reasonable questions, but the task is challenging. |
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing work on deep self-attention distillation for natural language processing tasks is limited by computational resources and latency. |
| Approach: | They generalize deep self-attention distillation in MINILM by using only self- attention relation distillation for taskagnostic compression of pretrained Transformers. |
| Outcome: | The proposed model outperforms the state-of-the-art in a multilingual and multilingual teacher model. |
GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)
Copied to clipboard
Hengyu Luo, Zihao Li, Joseph Attieh, Sawal Devkota, Ona de Gibert, Xu Huang, Shaoxiong Ji, Peiqin Lin, Bhavani Sai Praneeth Varma Mantina, Ananda Sreenidhi, Raúl Vázquez, Mengjie Wang, Samea Yusofi, Fei Yuan, Jörg Tiedemann
| Challenge: | Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios. |
| Approach: | They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks. |
| Outcome: | The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks. |
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs (2023.emnlp-main)
Copied to clipboard
Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, Yongbin Li
| Challenge: | Recent research has demonstrated that Large Language Models (LLMs) can enhance their capabilities by utilizing external tools. |
| Approach: | They propose a runnable evaluation system consisting of 73 API tools and an annotation system for 314 tool-use dialogues with 753 API calls. |
| Outcome: | The proposed benchmark assesses the effectiveness of existing LLMs by analyzing 314 tool-use dialogues with 753 API calls. |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pre-trained models suffer from domain shift and are not optimal for specific domains. |
| Approach: | They propose a general approach to developing small, fast and effective pretrained models for specific domains by adapting off-the-shelf general pretrained model and performing task-agnostic knowledge distillation in target domains. |
| Outcome: | The proposed approach achieves better performance over the BERT BASE model in domain-specific tasks while 3.3 smaller and 5.1 faster than the BRT BASE. |
Self-Sum: Teaching an Agent to Decide Itself When and What to Summarize (2026.findings-acl)
Copied to clipboard
Hongru Wang, Rui Wang, Jushi Kai, Boyang Xue, Yongqi Li, Shijue Huang, Xiaoteng Ma, Jeff Z. Pan, Amos Storkey
| Challenge: | Existing methods for summarizing long-horizon agents rely on fixed, rule-based summarization strategies. |
| Approach: | They propose a framework that empowers agents to autonomously decide when and what to summarize by modeling it as an internal cognitive action unified with environmental actions. |
| Outcome: | The proposed framework outperforms no-summarization and rule-based training methods on long-horizon benchmarks and shows strong generalization gains. |
AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation (2023.acl-long)
Copied to clipboard
Rongjie Huang, Huadai Liu, Xize Cheng, Yi Ren, Linjun Li, Zhenhui Ye, Jinzheng He, Lichao Zhang, Jinglin Liu, Xiang Yin, Zhou Zhao
| Challenge: | Existing models for speech-to-speech translation suffer from distinct degradation in noisy environments and fail to translate visual speech. |
| Approach: | They propose a text-based audio-visual speech-to-speech translation model that integrates visual information with audio-only data to improve system robustness. |
| Outcome: | The proposed model outperforms models trained on audio-only corpus in two languages . it also improves with low-resource audio-visual data, compared with baselines . |
LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks, such as MMLU, C-Eval, and GSM8K, evaluate models by posing a variety of problems, including problems about mathematics, science, law, and general knowledge. |
| Approach: | They propose a benchmark which assesses the model’s lateral thinking within an interactive framework. |
| Outcome: | The proposed evaluation benchmark assesses the model’s lateral thinking within an interactive framework. |
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings (2022.acl-long)
Copied to clipboard
| Challenge: | Contextualized embeddings are expensive and resource-demanding, hence environmentally unfriendly. |
| Approach: | They propose a method to convert contextualized embeddings from pre-trained models into static embeddables using synonym knowledge and weighted vector distribution. |
| Outcome: | The proposed method outperforms baseline embeddings by a large margin through extrinsic and intrinsic tasks. |
KC-GenRe: A Knowledge-constrained Generative Re-ranking Method Based on Large Language Models for Knowledge Graph Completion (2024.lrec-main)
Copied to clipboard
| Challenge: | Knowledge graph completion (KGC) is a critical task to predict missing facts among entities. |
| Approach: | They propose a knowledge-constrained generative re-ranking method based on generative large language models for KGC that can predict missing facts among entities. |
| Outcome: | The proposed method achieves state-of-the-art performance on four datasets and 9.0% and 11.1% compared to the previous methods. |
PsychePass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournaments (2026.findings-acl)
Copied to clipboard
| Challenge: | evaluating therapeutic competence of large language models remains challenging due to unstructured and longitudinal nature of counseling. |
| Approach: | They propose a framework that calibrates the therapeutic competence of LLMs via trajectory-anchored tournaments. |
| Outcome: | The proposed framework calibrates the therapeutic competence of LLMs via trajectory-anchored tournaments. |
Analyzing and Modeling LLM Response Lengths with Extreme Value Theory: Anchoring Effects and Hybrid Distributions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches treat length as an incidental output property rather than a statistically regular phenomenon worthy of rigorous modeling. |
| Approach: | They propose a statistical framework for modeling and controlling large language model response lengths using extreme value theory and cross-validation on Qwen and DeepSeek architectures. |
| Outcome: | The proposed model improves tail fit and generalizability while maintaining generalizzability. |
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multilingual benchmarks focus primarily on language understanding tasks. |
| Approach: | They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages. |
| Outcome: | Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve. |
Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs). |
| Approach: | They propose a self-supervised preference optimization framework that replaces the reward model with a preference loss and alignment loss to improve LLMs' ability to understand human preferences. |
| Outcome: | The proposed framework can be integrated with existing preference optimization methods and significantly boost their performance. |
MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectors (2025.findings-acl)
Copied to clipboard
| Challenge: | Hallucination remains a critical challenge for multimodal large language models, undermining their reliability in real-world applications. |
| Approach: | They propose a benchmark specifically designed for evaluating MLLMs’ capability in performing token-level hallucination detection (FHD) . they use curated training data to train a specialized model that significantly outperforms existing models. |
| Outcome: | The proposed model outperforms existing models in the evaluation of 9 MLLMs and reaches an average F1IoU of 40.59%. |
Robust Singing Voice Transcription Serves Synthesis (2024.acl-long)
Copied to clipboard
| Challenge: | Current AST methods struggle with accuracy and robustness when used for practical annotation. |
| Approach: | They propose a model that converts singing recordings into note sequences for automatic annotation of singing datasets. |
| Outcome: | The proposed model outperforms baseline models on enlarged, automatically annotated datasets. |
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (2024.findings-acl)
Copied to clipboard
Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang
| Challenge: | Existing methods for movie dubbing break phonemes in scripts, resulting in incomplete phoneme pronunciation and poor identity stability. |
| Approach: | They propose a method that switches dubbing learning from frame level to phoneme level . it uses a multimodal style adaptor to learn pronunciation style from audio . |
| Outcome: | The proposed method improves on two benchmarks, V2C and Grid, and is available on github. |
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets (2025.emnlp-main)
Copied to clipboard
Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu
| Challenge: | Existing datasets address understanding and generation in isolation, limiting the performance of unified vision large language models. |
| Approach: | They propose a dataset that facilitates mutual enhancement between multimodal understanding and generation. |
| Outcome: | The proposed framework integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment. |
MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Programming often involves translating detailed and complex specifications into code . current state-of-the-art models struggle to solve these problems, a new study shows . |
| Approach: | They propose a multi-modal coding dataset to evaluate algorithmic problem-solving skills in visually rich contexts. |
| Outcome: | The proposed model lacks powerful vision-code models due to the extreme demand for reasoning abilities. |
From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)
Copied to clipboard
Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination. |
| Approach: | They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning. |
| Outcome: | The proposed model significantly improves fine-grained speech quality discrimination. |
Template-free Prompt Tuning for Few-shot NER (2022.naacl-main)
Copied to clipboard
| Challenge: | Prompt-based methods have been successfully applied in few-shot learning tasks . however, when applied to token-level labeling tasks, it would be time-consuming to enumerate the template queries over all potential entity spans. |
| Approach: | They propose a method to reformulate NER tasks as LM problems without templates. |
| Outcome: | The proposed method is 30.12 times faster than the template-based method under few-shot settings. |
Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)
Copied to clipboard
Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song
| Challenge: | Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions. |
| Approach: | They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions. |
| Outcome: | The proposed model outperforms state-of-the-art methods and shows its utility. |
Do Not Guess, Verify: Logic-Guided Adaptive Reasoning for Multimodal Misinformation Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal misinformation detection paradigms rely on passive aggregation of multimodal features and social signals. |
| Approach: | They propose a verification-oriented framework that integrates large vision–language models into multimodal misinformation detection through explicit rationale-guided reasoning. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on multimodal misinformation detection benchmarks while significantly reducing computational cost. |
RaFe: Ranking Feedback Improves Query Rewriting for RAG (2024.findings-emnlp)
Copied to clipboard
Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang
| Challenge: | Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved to enhance document retrieval by reformulating queries. |
| Approach: | They propose a framework for training query rewriting models that leverages a reranker framework. |
| Outcome: | The proposed framework provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. |
Memory or Reasoning? Explore How LLMs Compute Mixed Arithmetic Expressions (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) can solve complex multi-step math reasoning problems, but their internal implementation is limited. |
| Approach: | They propose to use a "C**ausal **E**ffect **D**riven **F**ine-tuning method" to improve LLMs' reasoning ability. |
| Outcome: | The proposed method improves the model's reasoning ability by enhancing key components that are used to execute mixed arithmetic calculations. |
CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models (2024.findings-emnlp)
Copied to clipboard
Zhiwei Zha, Xiangru Zhu, Yuanyi Xu, Chenghua Huang, Jingping Liu, Zhixu Li, Xuwu Wang, Yanghua Xiao, Bei Yang, Xiaoxiao Xu
| Challenge: | Existing multimodal large language models lack the ability to perceive the visual world with a deep concept structure cognition. |
| Approach: | They propose a concept-level benchmark to assess MLLMs’ hierarchical concept understanding and reasoning abilities. |
| Outcome: | The proposed model outperforms state-of-the-art models in concept structure reasoning evaluation. |
On Construction of the ASR-oriented Indian English Pronunciation Dictionary (2020.lrec-1)
Copied to clipboard
| Challenge: | Indian English (IE) has distinctive characteristics, especially phonologically, from other varieties of English. |
| Approach: | They build a small IE spontaneous speech corpus and use a linguistically-guided IE pronunciation dictionary to apply it to IE. |
| Outcome: | The proposed system performs better on IE spontaneous speech data than the one trained with CMUdict. |
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)
Copied to clipboard
Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng
| Challenge: | Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal. |
| Approach: | They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs. |
| Outcome: | The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs. |
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality (2023.acl-long)
Copied to clipboard
Liang Li, Ruiying Geng, Chengyang Fang, Bing Li, Can Ma, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li
| Challenge: | Current datasets bias in the English language while leaving other languages underexplored. |
| Approach: | They propose a Chinese answer-to-sequence dataset with high quality and large scale . they propose encoding space for two hybrid knowledge resources to convert this task to a graph-totext problem. |
| Outcome: | The proposed method is effective in generating textual descriptions for the Chinese answer-to-sequence dataset. |
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)
Copied to clipboard
Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
| Challenge: | a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages. |
| Approach: | They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models. |
| Outcome: | The proposed benchmarks show that the current models perform worse than the human ceiling. |
JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models (2026.findings-acl)
Copied to clipboard
Qingjia Huang, Jingyu Zhang, Jianguo Wu, Yakai Li, Weijuan Zhang, Yankai Rong, Junyi Yao, Shengzhi Zhang, Xiaoqi Jia
| Challenge: | Currently, evaluation criteria and methods used for jailbreak effectiveness are inconsistent. |
| Approach: | They propose a framework to measure jailbreak effectiveness using a model that filters out jailbreak noise while preserving the original malicious question. |
| Outcome: | The proposed framework outperforms existing evaluation methods on a challenging benchmark containing 330 human-labeled, non-rejected jailbreak instances. |
AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu
| Challenge: | Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias. |
| Approach: | They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints. |
| Outcome: | The proposed benchmarks show that the models fail under causal, structural, or functional constraints. |
Multi-step Jailbreaking Privacy Attacks on ChatGPT (2023.findings-emnlp)
Copied to clipboard
| Challenge: | With the rapid evolution of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. |
| Approach: | They propose to integrate ChatGPT and Bing GPT3 into their applications to create a set of LLMs that can be used to generate NLP tasks with appropriate prompts. |
| Outcome: | The proposed models can be zero-shot or few-shot learners to solve specified tasks and can even be zero or few shot learners. |
Generating Sports News from Live Commentary: A Chinese Dataset for Sports Game Summarization (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods to generate sports summarization tasks are laborintensive and infeasible. |
| Approach: | They propose a Chinese dataset for sports game summarization and a model that consists of a selector and rewriter to evaluate the correctness of generated sports summaries. |
| Outcome: | The proposed model performs better on ROUGE and the two designed scores. |
TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing vision-and-language pre-training models suffer from long visual sequences . experimental results show that TRIPS gains a speedup of 40% over previous similar VLP models . |
| Approach: | They propose an efficient vision-and-language pre-training model with text-relevant image patch selection, TRIPS, which reduces the visual sequence progressively with a text-guided patch-selection layer in the visual backbone for efficient training and inference. |
| Outcome: | The proposed model can speed up training and inference by 40% over previous models. |
Few-Shot Semantic Parsing for New Predicates (2021.eacl-main)
Copied to clipboard
| Challenge: | a recent study shows that state-of-the-art neural semantic parsers are less accurate when there is only a handful of utterance-logical form pairs per predicate. |
| Approach: | They propose to use a meta-learning method to train a few-shot learning problem . they also propose to regularize attention scores with alignment statistics and apply a smoothing technique . |
| Outcome: | The proposed method outperforms baselines in one and two-shot settings. |
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tool learning methods focus on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness. |
| Approach: | They propose to predict query performance and cost required to accomplish a given task . they then assign queries to the optimal tools in a cost-effective manner . |
| Outcome: | The proposed method achieves higher performance at lower cost compared to baseline approaches. |
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Empirical results show misalignment at greater reasoning depths is driven mainly by alignment errors such as thematic shift and redundant reasoning. |
| Approach: | They propose a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences by constructing semantic-entropy-based matrices over intermediate steps and measuring their divergence. |
| Outcome: | The proposed method shows that it is consistent with previous studies and can be used as a diagnostic signal. |
Uncertainty-Aware Label Refinement for Sequence Labeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | Conditional random fields (CRF) for label decoding have been a problem for many tasks. |
| Approach: | They propose a two-stage label decoding framework that model long-term label dependencies while being much more computationally efficient. |
| Outcome: | The proposed method outperforms the CRF-based methods and greatly accelerates the inference process. |
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that streaming end-to-end speech recognition models suffer from higher word error rates (WER) compared to non-streaming models, streaming endto-ended ASR models are limited to short audio context or not use future context to satisfy low latency constraints. |
| Approach: | They propose a 2nd-pass rescoring model on top of the 1st-pass streaming model to improve recognition accuracy while keeping latency low. |
| Outcome: | The proposed method improves word error rate significantly compared to the existing model without adding any additional parameters or latency. |
Spelling Error Correction with Soft-Masked BERT (2020.acl-main)
Copied to clipboard
| Challenge: | Experimental results show that the proposed method is significantly better than the baselines including the one solely based on BERT. |
| Approach: | They propose a neural architecture which uses a network for error detection and a system for error correction based on BERT, with the latter connected to the other using what they call soft-masking technique. |
| Outcome: | The proposed method performs better than baselines including the one solely based on BERT, and is general and may be employed in other language detection-correction problems. |
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)
Copied to clipboard
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations. |
| Approach: | They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference. |
| Outcome: | The proposed method significantly mitigates object hallucinations across various model architectures. |
Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing defense methods improve the adversarial robustness by making models adapt to training set augmented with some adversarials. |
| Approach: | They propose to introduce a reweighting mechanism to calibrate the training distribution to obtain robust models. |
| Outcome: | The proposed method minimizes the loss of validation set mixed with clean examples and adversarial ones in an online learning manner. |
MM-ChatAlign: A Novel Multimodal Reasoning Framework based on Large Language Models for Entity Alignment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MMEA methods rely on knowledge representation learning (KRL) to measure the similarity of entity embeddings. |
| Approach: | They propose a framework that utilizes the visual reasoning abilities of MLLMs for multimodal entity alignment. |
| Outcome: | The proposed framework integrates the visual reasoning abilities of MLLMs for multimodal entity alignment. |
Representation Alignment and Adversarial Networks for Cross-lingual Dependency Parsing (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have improved dependency parsing accuracy in resource-rich languages . however, the accuracy drops sharply when the model is transferred to low-resource language . |
| Approach: | They propose a representation alignment and adversarial model to filter out useful knowledge from rich-resource language and ignore useless ones. |
| Outcome: | The proposed model outperforms baseline models on the benchmark datasets by 1.37 LAS and 1.34 UAS. |
Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models (2026.acl-long)
Copied to clipboard
Chung-ju Huang, Huiqiang Zhao, Yuanpeng He, Lijian Li, Wenpin Jiao, Zhi Jin, Peixuan Chen, Leye Wang
| Challenge: | Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously. |
| Approach: | They propose a confidential inference framework that partitions the LLM pipeline between a client-verified Confidential Virtual Machine (CVM) and the public cloud to protect client data without compromising the cloud’s model intellectual property or inference quality. |
| Outcome: | The proposed framework can defend against state-of-the-art token inference attacks while preserving model privacy, performance, and efficiency. |
AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) and generative models have motivated studies on automated game generation from natural language descriptions. |
| Approach: | They propose a novel multi-agent system, AutoUE, which coordinates multiple agents to end-to-end generate 3D games, covering model retrieval, scene generation, gameplay and interaction code synthesis, and automated game testing for evaluation. |
| Outcome: | The proposed system covers model retrieval, scene generation, gameplay and interaction code synthesis, and automated game testing for evaluation. |
Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models (2025.acl-long)
Copied to clipboard
Jie Liu, Wenxuan Wang, Su Yihang, Jingyuan Huang, Yudi Zhang, Cheng-Yi Li, Wenting Chen, Xiaohan Xing, Kao-Jung Chang, Linlin Shen, Michael R. Lyu
| Challenge: | Medical Multi-Modal Large Language Models (Med-MLLMs) are a promising new form of artificial general intelligence due to their ability to tackle complex tasks. |
| Approach: | They propose a new benchmark that comprehensively assesses medical multi-modal large language models in terms of distinct medical specialties and different diagnostic capacities. |
| Outcome: | The proposed model covers 15 medical specialties and different diagnostic capacities, and excludes overlap with existing VQA dataset. |
CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs (2026.findings-acl)
Copied to clipboard
Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi LI, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang
| Challenge: | Existing evaluations emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy. |
| Approach: | They propose a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path needed to reach a correct solution. |
| Outcome: | Evaluating 21 LRMs, the proposed framework quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution. |
Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher (2024.findings-acl)
Copied to clipboard
| Challenge: | Chinese Spelling Correction models are prone to over-correct and poor generalization for error patterns outside the standard distribution. |
| Approach: | They propose a teacher network guided by prior knowledge for distillation learning of CSC models. |
| Outcome: | The proposed method significantly enhances the CSC model’s language modeling capabilities, crucial for minimizing over-correction. |
GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for complex table question answering are often implicit, feeding the entire table into prompts. |
| Approach: | They propose a GraphOTTER that explicitly establishes the reasoning process to pinpoint the correct answers. |
| Outcome: | The proposed method is able to identify the correct answers on two benchmark datasets and two LLM backbones. |
Neural-DINF: A Neural Network based Framework for Measuring Document Influence (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to measure scholarly impact of documents without citations only consider word frequency change. |
| Approach: | They propose a neural network framework that measures document influence without citations by using word frequency changes and word semantic shifts. |
| Outcome: | The proposed model outperforms existing models on document influence evaluation without citations. |
On Robustness of Neural Semantic Parsers (2021.eacl-main)
Copied to clipboard
| Challenge: | Semantic parsing maps natural language (NL) utterances into logical forms (LFs) adversarial examples are created by adding tiny perturbations to inputs but can severely deteriorate model performance. |
| Approach: | They propose to construct robustness test sets based on existing benchmark corpora and to evaluate the effect of data augmentation. |
| Outcome: | The proposed method measures the performance of the proposed parsers on robustness test sets and evaluates the effect of data augmentation. |
LIME: Less Is More for MLLM Evaluation (2025.findings-acl)
Copied to clipboard
King Zhu, Qianbo Zang, Shian Jia, Siwei Wu, Feiteng Fang, Yizhi Li, Shuyue Guo, Tianyu Zheng, Jiawei Guo, Bo Li, Haoning Wu, Xingwei Qu, Jian Yang, Ruibo Liu, Xiang Yue, Jiaheng Liu, Chenghua Lin, Hamid Alinejad-Rokny, Min Yang, Shiwen Ni, Wenhao Huang, Ge Zhang
| Challenge: | Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs. |
| Approach: | They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding. |
| Outcome: | The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities. |
AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have improved text generation and reasoning. |
| Approach: | They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. |
| Outcome: | The proposed framework embeds multi-bit provenance into planning decisions while preserving utility. |
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)
Copied to clipboard
Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao, Xinke Jiang, Jinyang Zhang, Yinghao Zhu, Zheng Li, Liantao Ma, Junfeng Zhao, Yasha Wang
| Challenge: | Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details. |
| Approach: | They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. |
| Outcome: | Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm. |
Scaling Laws for Fact Memorization of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Fact knowledge memorization is crucial for Large Language Models (LLMs) to generate factual and reliable responses. |
| Approach: | They analyze scaling laws for LLM’s fact knowledge and LLMs’ behaviors of memorizing different types of facts. |
| Outcome: | The proposed model can generalize on unseen facts and its scaling law is similar to general pre-training. |
Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety (2026.acl-long)
Copied to clipboard
Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu, Dongyuan Li, Yankai Chen, Weizhi Zhang, Yangning Li, Angelo Zangari, Jizhou Guo, Chunyu Miao, Liancheng Fang, Langzhou He, Yinghui Li, Renhe Jiang, Philip S. Yu
| Challenge: | Existing deep research frameworks lack adequate evaluation procedures and stage-specific protections. |
| Approach: | They propose a framework with open-domain evaluation and a stage-wise safety benchmark to address this oversight. |
| Outcome: | The proposed framework improves defense success rates by 16.53% while reducing over-refusal rates to approximately 6%. |
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to answer reading comprehension tasks are inefficient since the input is re-encoded within each module. |
| Approach: | They propose a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. |
| Outcome: | The proposed model outperforms the baseline model and achieves state-of-the-art results on two versions of TriviaQA and two variants of SQuAD. |
Personalized Video Comment Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Generating personalized responses in video poses a unique challenge for language models. |
| Approach: | They propose a new automatic metric based on Large Language Models with few-shot in-context learning that measures quality from the aspects of emotion, language style and content relevance. |
| Outcome: | The proposed metric measures quality from emotion, language style and content relevance with human evaluations. |
The Digital Dunning-Kruger Effect: Decoupling Hallucinations via Geometric Hidden-state Observation for Semantic Truthfulness (2026.acl-long)
Copied to clipboard
Yueheng Mao, Min Yu, Gengwang Li, Jianguo Jiang, Gang Li, Meng Zhang, Zhen Xu, Weiqing Huang, Ming Liu
| Challenge: | Large Language Models (LLMs) often generate overconfident yet factually incorrect hallucinations. |
| Approach: | They propose a black-box-based framework that captures stubborn hallucinations by integrating internal geometric dynamics with output probability distributions. |
| Outcome: | The proposed framework outperforms white-box methods and reduces computational overhead by over 90%. |
ReLoop: “Seeing Twice and Thinking Backwards” via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination mitigation rely on external verification or post-hoc correction, lacking internal mechanism to validate outputs directly during training. |
| Approach: | They propose a unified closed-loop training framework that encourages multimodal consistency for cross-modal understanding in MLLMs. |
| Outcome: | The proposed framework encourages multimodal consistency for cross-modal understanding in MLLMs. |
MGCL: Multi-Granularity Clue Learning for Emotion-Cause Pair Extraction via Cross-Grained Knowledge Distillation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional methods often rely on coarse-grained clause-level annotations, which overlook valuable fine-grain clues. |
| Approach: | They propose a method that captures fine-grained clues from a weakly-supervised perspective efficiently by using a teacher model to give sub-clause clues without needing fine-grain annotations. |
| Outcome: | The proposed method achieves state-of-the-art performance while offering improved interpretability. |
Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario. |
| Approach: | They propose a multimodal task-oriented dialog dataset with subjective preferences and recommendation acts that is well-annotated with sales experts. |
| Outcome: | The proposed model is powered by a state-of-the-art multimodal model for these tasks. |
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)
Copied to clipboard
Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li
| Challenge: | Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). |
| Approach: | They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities. |
| Outcome: | The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks. |
A Progressive Framework for Role-Aware Rumor Resolution (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for rumor resolution ignore intrinsic propagation mechanisms of rumors and present poor adaptive ability when unprecedented news emerges. |
| Approach: | They propose to identify triggering posts and exploit their characteristics to facilitate rumor verification. |
| Outcome: | The proposed model and scheme exploits rumor diffusion patterns and linguistic features to facilitate verification. |
CmEAA: Cross-modal Enhancement and Alignment Adapter for Radiology Report Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for automatic radiology report generation suffer from data bias. |
| Approach: | They propose a method that connects a vision encoder with a frozen large language model by using a cross-modal enhancement and alignment adapter. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods on IU X-Ray and MIMIC-CXR datasets. |
Tree-Instruct: A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Extensive research has highlighted the importance of data complexity as a crucial metric, but the impact of complexity remains relatively unexplored. |
| Approach: | They propose to add a specified number of nodes to instructions’ semantic trees to enhance the instruction complexity in a controllable manner. |
| Outcome: | The proposed approach outperforms diverse yet complex instructions under the same token budget and can control the difficulty level of modified instructions. |
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)
Copied to clipboard
Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang
| Challenge: | Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals . |
| Approach: | They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation. |
| Outcome: | The proposed method mitigates behavior collapse and improves performance across benchmarks. |
Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on overcoming catastrophic forgetting on original language pairs while lacking encouragement to learn new knowledge from incremental learning. |
| Approach: | They propose a knowledge transfer method that can adapt original MNMT models to diverse incremental language pairs by flexibly introducing knowledge from external models into original models, which encourages the models to learn new language pairs. |
| Outcome: | The proposed method outperforms baselines on multiple languages while maintaining performance on original language pairs. |
360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. |
| Approach: | They propose a hierarchical multi-agent framework that uses 360 assessment to accumulate experience through fine-grained assessment. |
| Outcome: | The proposed framework is based on corporate organizational practices and employs a dual-level experience pool for agents to accumulate experience through fine-grained assessment. |
ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)
Copied to clipboard
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
| Challenge: | ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |
| Approach: | They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments. |
| Outcome: | The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |
Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances, Resources, and Future Directions (2025.findings-emnlp)
Copied to clipboard
Yaozu Wu, Dongyuan Li, Yankai Chen, Renhe Jiang, Henry Peng Zou, Wei-Chieh Huang, Yangning Li, Liancheng Fang, Zhen Wang, Philip S. Yu
| Challenge: | Large Language Models (LLMs) are used to assist with driving decisions, but they face limitations in perception and computational demands. |
| Approach: | They propose a survey of LLM-based multi-agent ADSs and their applications . they analyze agent-human interactions in scenarios where LLM agents engage with humans . |
| Outcome: | The proposed approach reduces human intervention and improves safety and efficiency. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
Text-to-Song: Towards Controllable Music Generation Incorporating Vocal and Accompaniment (2024.acl-long)
Copied to clipboard
Zhiqing Hong, Rongjie Huang, Xize Cheng, Yongqi Wang, Ruiqi Li, Fuming You, Zhou Zhao, Zhimeng Zhang
| Challenge: | Existing studies focus on singing voice synthesis and music generation independently. |
| Approach: | They propose a novel task called Text-to-Song synthesis which incorporates both vocal and accompaniment generation. |
| Outcome: | The proposed method can synthesize songs with comparable quality and style consistency. |
SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes (2026.acl-long)
Copied to clipboard
Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang, Junda Wu, Chengkai Huang, Lina Yao, Julian McAuley, Jingbo Shang
| Challenge: | Existing preference-based approaches fail to address this challenge by exploiting language priors to bypass visual grounding. |
| Approach: | They propose a framework that leverages scene graphs as structured visual information to perform controllable structural interventions. |
| Outcome: | The proposed framework improves answer accuracy and reasoning faithfulness across seven visual reasoning benchmarks. |
RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)
Copied to clipboard
Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li
| Challenge: | Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. |
| Approach: | They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone . |
| Outcome: | Experiments on four TVR datasets show that the proposed method performs better than other methods. |
BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs (2026.acl-long)
Copied to clipboard
Yue Wang, Ruotian Ma, Xingyu Chen, Zhengliang Shi, Morunliu Yang, Wanshun Chen, Huang Liu, Jiadi Yao, Xin He, Qu Yang, Qingxuan Jiang, Fanghua Ye, Juntao Li, Zhaopeng Tu, Xiaolong Li, Liefeng Bo, Min Zhang
| Challenge: | Existing approaches often fail to leverage the linguistic intelligence of Large Language Models (LLMs) Existing models lack the ability to follow text instructions for controllable Text-to-Speech (TTS). |
| Approach: | They propose a framework where an LLM acts as a conductor, understanding user instructions and generating a textual plan - explicit vocal features. |
| Outcome: | The proposed model outperforms open- and closed-source models in speech synthesis and achieves zero-shot cross-lingual generalization. |
ClaimLens: Automated, Explainable Fact-Checking on Voting Claims Using Frame-Semantics (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Existing fact-checking solutions lack transparency and explainability . a lack of transparency can make it difficult for users to trust and understand the reasoning behind the outcomes. |
| Approach: | They propose an automated fact-checking system focused on voting-related factual claims that leverages frame-semantic parsing to provide structured and interpretable fact verification. |
| Outcome: | The proposed system can extract relevant information from voting-related factual claims using public records and Vote semantic frame. |
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)
Copied to clipboard
Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). |
| Approach: | They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other. |
| Outcome: | The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters. |
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models (2024.lrec-main)
Copied to clipboard
Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Tianxiang Sun, Cheng Chang, Qinyuan Cheng, Ding Wang, Xiaofeng Mou, Xipeng Qiu, Xuanjing Huang
| Challenge: | Recent advances in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. |
| Approach: | They propose a hierarchical reasoning aggregation framework to address this problem . they propose dynamic sampling to adjust the number of reasoning chains . |
| Outcome: | The proposed framework outperforms existing ensemble methods on complex reasoning tasks. |
Lingke: a Fine-grained Multi-turn Chatbot for Customer Service (C18-2)
Copied to clipboard
| Challenge: | e-commerce chatbots usually need a mass of human dialogue data to train, but for multi-turn conversations, the performance is poor. |
| Approach: | They propose an information retrieval augmented multi-turn chatbot which can answer questions based on unstructured documents and deal with multi-turned conversations. |
| Outcome: | The proposed solution outperforms all other models in multi-turn conversations and can learn from conversation records. |
Relation Extraction with Temporal Reasoning Based on Memory Augmented Distant Supervision (N19-1)
Copied to clipboard
| Challenge: | Distant supervision is an important paradigm for automatically extracting relations . but the examples collected can be noisy and pose significant challenge for labeling . |
| Approach: | They propose a method to predict whether two entities participate in a relation at a given time spot. |
| Outcome: | The proposed model performs better in WIKI-TIME and NYT-10 datasets compared with the best existing models . the proposed model is based on a dataset with a valid period of a certain relation of two entities in the knowledge base . |
FroM: Frobenius Norm-Based Data-Free Adaptive Model Merging (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new adaptive merging method is proposed to improve fine-tuning performance . traditional methods often encounter task interference when merging full fine-uning models . |
| Approach: | They propose an adaptive merging method that directly measures model parameters using the Frobenius norm . |
| Outcome: | The proposed method outperforms baseline methods in various fine-tuning scenarios. |
PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models have demonstrated considerable capabilities across various tasks . however, they often fall short of the performance achieved by domain-specific state-of-the-art models . |
| Approach: | They propose a tuning-free method to augment domain-specific abilities of Large language models . they leverage insights from the response preference of expert models to augment LLMs . |
| Outcome: | The proposed method outperforms the expert model on 4 ScienceWorld tasks. |
Guidelines as Environments: A World Model Approach to Rule Following (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models for guideline-following are a poor fit for ambiguous, text-defined constraints. |
| Approach: | They propose a Rule-Grounded Causal World Model that builds an explicit state space from guideline text itself. |
| Outcome: | Experiments show that the proposed model can be used to model rule execution with an explicit state space from the guideline text itself. |
Case2Code: Scalable Synthetic Data for Code Generation (2025.coling-main)
Copied to clipboard
Yunfan Shao, Linyang Li, Yichuan Ma, Peiji Li, Demin Song, Qinyuan Cheng, Shimin Li, Xiaonan Li, Pengyu Wang, Qipeng Guo, Hang Yan, Xipeng Qiu, Xuanjing Huang, Dahua Lin
| Challenge: | Large Language Models (LLMs) have shown outstanding breakthroughs in code generation. |
| Approach: | They propose a case-to-code induction task that exploits the expressiveness and correctness of programs by incorporating LLMs into their training. |
| Outcome: | The proposed task improves distribution case-to-code induction and various coding generation tasks. |
StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models struggle to maintain temporal, spatial, and narrative coherence across image sequences . existing models lack depth and engagement of human-authored stories . |
| Approach: | They propose a topic-driven narrative optimizer that integrates image descriptions, topic generation, and GPT-4-based refinements. |
| Outcome: | The proposed framework outperforms existing models in visual relevance, coherence, and fluency. |
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning (2026.findings-acl)
Copied to clipboard
Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang, Fu Li
| Challenge: | Generative engines (GEs) are replacing ranked links with citation-grounded answers . current methods are unable to accumulate or transfer effective strategies across tasks and engines . |
| Approach: | They propose a multi-agent framework where planning, editing, and fidelity-aware evaluation serve as the execution layer. |
| Outcome: | The proposed framework outperforms heuristic baselines in visibility and citation fidelity on three mainstream engines. |
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li
| Challenge: | Extensive experiments demonstrate that treating attention as a feature map and applying convolution as . a processing method significantly enhances Transformer performance. |
| Approach: | They propose to use the convolution operator to mimic the processing methods in computer vision to treat attention as a feature map and apply it to neighboring attention scores across different heads. |
| Outcome: | The proposed model can be adapted to various attention-related models and achieves high performance. |
LoRACoE: Improving Large Language Model via Composition-based LoRA Expert (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that the Mixture of Experts architecture improves performance of large language models. |
| Approach: | They propose a method to build static experts using LoRA parameters . they propose to use rank-level parameters to build experts based on rank-based parameters based in LoRA module. |
| Outcome: | The proposed method improves task performance across a broader range of tasks. |
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has focused on smaller, task-specific models enhanced by distilling knowledge from LLMs, but the diversity and quality of negative knowledge remains understudied. |
| Approach: | They propose a quality-guided contrastive rationale distillation framework that aims to enhance reasoning capabilities through contrastive knowledge learning. |
| Outcome: | The proposed method consistently outperforms existing distillation techniques yielding higher-quality rationales. |
Promoting Data and Model Privacy in Federated Learning through Quantized LoRA (2024.findings-emnlp)
Copied to clipboard
Zhu JianHao, Changze Lv, Xiaohua Wang, Muling Wu, Wenhao Liu, Tianlong Li, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Existing federated learning frameworks require substantial data and computational resources to develop large language models. |
| Approach: | They propose a method that distributes a quantized version of the model’s parameters during training and combine it with a popular fine-tuning method to significantly reduce communication costs. |
| Outcome: | The proposed method enables accurate estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one. |
MASTER: A Multi-Agent System with LLM Specialized MCTS (2025.naacl-long)
Copied to clipboard
Bingzheng Gan, Yufan Zhao, Tianyi Zhang, Jing Huang, Li Yusu, Shu Xian Teo, Changwang Zhang, Wei Shi
| Challenge: | Large Language Models (LLMs) are increasingly being explored for problem-solving tasks . their strategic planning capability is often viewed with skepticism due to their limited planning capabilities. |
| Approach: | They propose a framework that coordinates agent recruitment and communication through LLM specialized MCTS. |
| Outcome: | The proposed framework achieves 76% accuracy on HotpotQA and 80% on WebShop . it relies on extensive sampling simulations to approximate the true reward distribution . |
Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization (D19-1)
Copied to clipboard
| Challenge: | Existing studies measure the superiority of DA methods in terms of their performance on a specific test set, but some do not exhibit consistent improvements across translation tasks. |
| Approach: | They propose to evaluate DA methods from two perspectives to determine their generalization ability . they find that DA method's test performance does not exhibit consistent improvements across translation tasks . |
| Outcome: | The proposed methods do not exhibit consistent improvements across translation tasks. |
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models pre-trained on massive corpora have shown impressive few-shot learning ability on many NLP tasks. |
| Approach: | They propose to recast structured output in the form of code instead of natural language and use generative LLMs of code to perform IE tasks. |
| Outcome: | The proposed method outperforms fine-tuning moderate-size pre-trained models and prompting NL-LLMs under few-shot settings. |
Contrastive Learning with Adversarial Examples for Alleviating Pathology of Language Model (2023.acl-long)
Copied to clipboard
| Challenge: | Existing interpretation methods fail to obtain faithful attributions on these models, thereby failing to reveal potential flaws and biases. |
| Approach: | They propose a Contrastive learning regularization method which calibrates the sentence representation of out-of-distribution examples and utilizes adversarial examples to introduce direction information in regularization. |
| Outcome: | The proposed method alleviates the model pathology while impacting generalization ability on in-distribution examples and thus helps interpretation methods obtain more faithful results. |
MVP-Tuning: Multi-View Knowledge Retrieval with Prompt Tuning for Commonsense Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for commonsense reasoning rely on multi-hop knowledge retrieval and suffer low accuracy due toembedded noise in the acquired knowledge. |
| Approach: | They propose to use multi-hop knowledge retrieval to model knowledge and input text together. |
| Outcome: | The proposed method outperforms baselines on 5 commonsense reasoning datasets and is number one on theleaderboard. |
UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies rely on shallow unsupervised data generated by token surface matching regardless of global context-aware semantics of the surrounding text tokens. |
| Approach: | They propose an Unsupervised Pseudo Semantic Data Augmentation mechanism to enrich training data without human intervention. |
| Outcome: | The proposed model improves on general zero-shot cross-lingual understanding tasks on different languages without human intervention. |
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)
Copied to clipboard
Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo
| Challenge: | Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench . |
| Approach: | They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool . |
| Outcome: | The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions . |
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to mitigate hallucinations include prompt engineering and model optimization, but lack domain generalization and potential errors in fine-tuning data may exacerbate the hallucism. |
| Approach: | They propose an expert-aware adaptive contrast decoding that uses expert differences in MoE’s higher layers to mitigate hallucinations on QA tasks. |
| Outcome: | The proposed method outperforms baseline models on four datasets Large language models (LLMs) show strong performance but suffer from hallucinations, limiting their application. |
Aria-UI: Visual Grounding for GUI Instructions (2025.findings-acl)
Copied to clipboard
| Challenge: | Using a multimodal model, GUI agents can ground from language instructions to target elements . relying on HTML or AXTree inputs is a challenge for GUI agents . |
| Approach: | They propose a large multimodal model specifically designed for GUI grounding that adopts a pure vision approach instead of auxiliary inputs. |
| Outcome: | The proposed model outperforms vision-only and AXTree-reliant models on offline and online agents. |
CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)
Copied to clipboard
Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang
| Challenge: | Large language models (LLMs) have revolutionized natural language processing. |
| Approach: | They propose a Chinese-based platform that assesses Chinese LLMs using a standardized workflow and a unique sampling strategy. |
| Outcome: | CLEVA evaluates Chinese LLMs on a standardized workflow and a competitive leaderboard with minimal coding. |
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training (2021.naacl-main)
Copied to clipboard
Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou
| Challenge: | Existing methods for learning cross-lingual representations are lacking in the field of NLP. |
| Approach: | They propose a framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. |
| Outcome: | The proposed approach improves cross-lingual transferability on benchmarks. |
LC4EE: LLMs as Good Corrector for Event Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Event extraction (EE) is a critical task in natural language processing, yet deploying a practical EE system remains challenging. |
| Approach: | They propose to leverage the superior extraction capability of LLMs and instruction-following ability of LRMs to construct a robust and highly available EE system. |
| Outcome: | The proposed method can identify and correct errors in SLMs predictions based on automatically generated feedback information and improve performance. |
Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in Large Language Models (2025.naacl-long)
Copied to clipboard
Tongxuan Liu, Wenjiang Xu, Weizhe Huang, Yuting Zeng, Jiaxing Wang, Xingyu Wang, Hailong Yang, Jing Li
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks but their performance in complex logical reasoning tasks remains unsatisfactory. |
| Approach: | They propose a propositional logic prompting method which generates expanded logical information descriptions and utilizes them as an additional augmentation to original contexts. |
| Outcome: | Extensive experiments show that Logic-of-Thought boosts the performance of various prompting methods with a striking margin across five logical reasoning tasks. |
KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)
Copied to clipboard
Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu
| Challenge: | Recent advances in pre-trained language models have made it possible to generate human-like text. |
| Approach: | They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached. |
| Outcome: | The proposed game lacks incentives and relies on players to explore on their own. |
FLAT: Chinese NER Using Flat-Lattice Transformer (2020.acl-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) models are difficult to use because of the complex nature of the lattice structure and the low inference speed. |
| Approach: | They propose a character-word lattice structure that converts lattics into flat structures consisting of spans. |
| Outcome: | The proposed model outperforms other lexicon-based models on four datasets and is highly parallel. |
Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have become integral components in various autonomous agent systems. |
| Approach: | They propose an exploration-based trajectory optimization approach that allows agents to learn from their exploration failures. |
| Outcome: | The proposed method outperforms baseline methods on three complex tasks by a large margin. |
Learning Kernel-Smoothed Machine Translation with Retrieved Examples (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to update deployed models are prone to overfit . however, non-parametric methods are liable to over-fit the retrieved examples . |
| Approach: | They propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER) this approach allows users to adapt models to emerging cases without retraining . |
| Outcome: | The proposed approach achieves 1.1 to 1.5 BLEU scores over existing methods without retraining . the proposed model is released on https://github.com/jiangqn/KSTER. |
The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have yielded impressive gains on mathematical reasoning benchmarks via supervised fine-tuning (SFT). |
| Approach: | They investigate the mechanisms behind SFT improvements in small-scale large language models by examining four key questions: (1) Are performance gains primarily due to format alignment rather than reasoning? (2) Can high-quality supervision encourage genuine reasoning? (4) Are format alignment gains consistent across model sizes and architectures? |
| Outcome: | The proposed models outperform the proprietary models on OlympiadBench and Omni-Math, but lack the brittleness of the models under perturbations to test their reasoning abilities. |
Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou
| Challenge: | Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging . |
| Approach: | They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. |
| Outcome: | The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets. |
Domain Representative Keywords Selection: A Probabilistic Approach (2022.findings-acl)
Copied to clipboard
| Challenge: | a probabilistic approach to select a subset of a target domain representative keywords is crucial for many downstream tasks in natural language processing. |
| Approach: | They propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain. |
| Outcome: | The proposed approach provides more importance to distinctive keywords than common keywords contrasting with the context domain. |
DocRED: A Large-Scale Document-Level Relation Extraction Dataset (P19-1)
Copied to clipboard
Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun
| Challenge: | Existing relation extraction methods focus on extracting intra-sentence relations for single entities. |
| Approach: | They propose a relation extraction dataset from Wikipedia and Wikidata with three features . document-level relation extraction is a task to identify relational facts between entities . |
| Outcome: | The proposed dataset is the largest human-annotated dataset for document-level RE from plain text. |
Large Margin Neural Language Model (D18-1)
Copied to clipboard
| Challenge: | Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences. |
| Approach: | They propose a large margin criterion for training neural language models by minimizing perplexity on grammatical sentences and propose enlarged margins for task-specific training. |
| Outcome: | The proposed method gains up to 1.1 WER reduction for speech recognition and 1.0 BLEU increase for machine translation. |