Papers by Li Xiong
POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Positional bias (PB) manifests as non-uniform sensitivity across contextual locations . previous studies have addressed PB by modifying the underlying architectures or employing extensive contextual awareness training. |
| Approach: | They propose a position-to-position knowledge distillation framework that leverages position-induced disparities to counteract PB. |
| Outcome: | The proposed framework reduces positional bias and improves performance on retrieval and reasoning tasks. |
Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can solve reasoning and mathematical problems using the Chain-of-Thought technique, but require costly and long CoT data and fine-tuning. |
| Approach: | They propose a method that uses Sparse Autoencoders to extract interpretable features from vanilla CoT and use them to steer the LLM's internal states. |
| Outcome: | The proposed method uses Sparse Autoencoders (SAEs) to extract interpretable features from vanilla CoT and steer the LLM's internal states during generation. |
Enhance Robustness of Language Models against Variation Attack through Graph Integration (2024.lrec-main)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are used in many NLP applications but their vulnerability to adversarial attacks can lead to false or misleading information being distributed. |
| Approach: | They propose a method to incorporate a Chinese character variation graph into pre-trained language models to increase their robustness against character variation attacks in Chinese content. |
| Outcome: | The proposed method outperforms existing language models in combating adversarial attacks in Chinese content. |
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. |
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 . |
Dual Prompt Tuning based Contrastive Learning for Hierarchical Text Classification (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on hierarchy-aware text feature by exploiting explicit parent-child relationships, resulting in label confusion within each layer. |
| Approach: | They propose a dual-prompt tuning method which emphasizes discrimination among peer labels by performing contrastive learning on each hierarchical layer. |
| Outcome: | The proposed method outperforms existing methods on benchmark datasets and is available on github. |
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. |
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) often display unstable behaviors, e.g., hallucinating unsupported premises, overthinking simple tasks, and displaying higher sensitivity to prompt variations. |
| Approach: | They propose a graph-based analytical framework that clusters long, verbose CoT outputs into semantically coherent reasoning steps, then constructs directed reasoning graphs to capture contextual and logical dependencies among these steps. |
| Outcome: | The proposed framework enables quantitative evaluation of internal reasoning structure and quality beyond conventional metrics and provides practical insights for prompt engineering and cognitive analysis of LLMs. |
ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Causal chain reasoning models suffer from two main transitive problems: threshold effect and scene drift. |
| Approach: | They propose a framework that uses exogenous variables to represent causal pairs and estimates the threshold and scene contradictions using structural causal recurrent neural networks. |
| Outcome: | The proposed framework outperforms baselines on Chinese and English CCR datasets. |
LightSeq: A High Performance Inference Library for Transformers (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing inference frameworks for natural language processing are not the best choice for online service of sequence processing problems. |
| Approach: | They propose a highly efficient inference library for Transformer models that includes GPU optimization techniques to streamline computation and reduce memory footprint. |
| Outcome: | The proposed library achieves 14x speedup compared with TensorFlow and 1.4x speed up compared to a concurrent CUDA implementation. |
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (2024.findings-acl)
Copied to clipboard
Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
| Challenge: | Neural architecture search (NAS) uses weight-sharing supernets to generate diverse subnetworks without retraining. |
| Approach: | They propose a weight-sharing supernet that leverages mixture-of-experts to enhance supernet model expressiveness with minimal training overhead. |
| Outcome: | The proposed method achieves state-of-the-art (SoTA) performance in NAS for fast machine translation models, surpassing NAS-BERT and AutoDistil across various model sizes. |
Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2 (2021.acl-srw)
Copied to clipboard
| Challenge: | Experimental results show that pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage. |
| Approach: | They conduct experiments on an English essay dataset using Chinese-GPT2 . they find that the model can generate better continuations by learning to generate the in the fine-tuning stage. |
| Outcome: | The pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage. |
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)
Copied to clipboard
Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng
| Challenge: | Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts. |
| Approach: | They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions. |
| Outcome: | The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field. |
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics (2025.findings-emnlp)
Copied to clipboard
Sheldon Yu, Yuxin Xiong, Junda Wu, Xintong Li, Tong Yu, Xiang Chen, Ritwik Sinha, Jingbo Shang, Julian McAuley
| Challenge: | Recent advances in chain-of-thought prompting have demonstrated the ability of large language models to perform multi-step reasoning. |
| Approach: | They propose a framework to analyze latent dynamics of CoT trajectories for interpretability . they segment generated CoT into discrete reasoning steps and abstract each step into a spectral embedding based on token-level Gram matrices . |
| Outcome: | The proposed framework segments generated CoT steps into discrete reasoning steps, abstracts each step into a spectral embedding based on token-level Gram matrices, and clusters these embeddements into semantically meaningful latent states. |
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)
Copied to clipboard
Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li
| Challenge: | Existing studies focus on specialized agents designed for particular tasks. |
| Approach: | They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed. |
| Outcome: | The proposed model can scale to get generalized agent capabilities. |
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings (P18-1)
Copied to clipboard
| Challenge: | Neural machine translation uses source and target word embeddings to improve translation quality . source and targeted word embeds are at the two ends of a long information processing procedure . |
| Approach: | They propose a method to shorten the distance between source and target words in neural machine translation by bridging source and targeting word embeddings. |
| Outcome: | The proposed method shortens the distance between source and target words in neural machine translation and strengthens their association. |
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. |
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent (2025.findings-emnlp)
Copied to clipboard
Junda Wu, Yuxin Xiong, Xintong Li, Yu Xia, Ruoyu Wang, Yu Wang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Lina Yao, Jingbo Shang, Julian McAuley
| Challenge: | Existing fine-tuning and continual learning methods compress visual representations and emphasize task alignment over visual retention. |
| Approach: | They propose a modality-decoupled gradient descent (MDGD) that regulates gradient updates to preserve effective rank of visual features and explicitly disentangles visual learning from task-specific alignment. |
| Outcome: | The proposed model reduces visual forgetting and improves visual retention . it disentangles visual learning from task-specific alignment and preserves effective rank . |
FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information. |
| Approach: | They propose a method to enhance LLMs' context awareness by updating only the last Feed-Forward Network module to maximize the likelihood of the prompt before inference . |
| Outcome: | The proposed method improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6% and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%. |
WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario (2025.coling-main)
Copied to clipboard
Jiebin Zhang, Eugene J. Yu, Qinyu Chen, Chenhao Xiong, Dawei Zhu, Han Qian, Mingbo Song, Weimin Xiong, Xiaoguang Li, Qun Liu, Sujian Li
| Challenge: | Existing efforts to generate Wikipedia articles for new events fall short of real-world application. |
| Approach: | They propose a benchmark to generate Wikipedia articles for new events under real-world scenarios . they use systematic metrics and LLM-based metrics to assess verifiability, organization, and other aspects aligned with real-life scenarios. |
| Outcome: | The proposed benchmarks show that hierarchical-based methods generate more comprehensive content while fine-tuned methods achieve better verifiability. |
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)
Copied to clipboard
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs. |
| Approach: | They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge. |
| Outcome: | Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 . |
Don’t Change Me! User-Controllable Selective Paraphrase Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | a new technique allows paraphrase generation to be user-controlled . a user looking for cheap hotels in New York would not find the other answer helpful . |
| Approach: | They propose a method that provides a user with explicit tags that can be placed around any arbitrary segment of text to mean "don't change me!" they propose allowing user-controllable paraphrase generation by fine-tuning model that exhibits this behavior . |
| Outcome: | The proposed technique is language agnostic and tested in English and Chinese. |
Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing conversational question answering datasets are usually constructed from unstructured texts in English. |
| Approach: | They propose a Chinese tabular conversational question answering dataset based on financial reports . they select 2,463 tables and manually generate 2,463, conversations with 35,494 QA pairs . |
| Outcome: | The proposed dataset is based on Chinese financial reports extracted from listed companies in the past 30 years. |
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. |
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)
Copied to clipboard
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
| Challenge: | Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer. |
| Approach: | They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions. |
| Outcome: | The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios. |
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. |
Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden. |
| Approach: | They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations. |
| Outcome: | The proposed system improves time-to-target by 2.17-8.48 on real-world datasets. |
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. |
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to shorten CoTs use length penalties or global entropy reduction . Existing approaches to CoT reasoning have significant practical drawbacks . |
| Approach: | They propose a method that shortens CoTs by length penalties or global entropy reduction . they integrate ETR into Group Relative Policy Optimization and evaluate it . |
| Outcome: | The proposed objective improves accuracy–efficiency trade-off by +9.9% while reducing CoT length by 67% across four benchmarks. |
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 . |
SParC: Cross-Domain Semantic Parsing in Context (P19-1)
Copied to clipboard
Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher, Dragomir Radev
| Challenge: | Xu et al., 2017): a dataset for cross-domain semantic parsing in context with 4,298 question sequences. |
| Approach: | They present a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences. |
| Outcome: | The proposed dataset demonstrates that it has greater semantic diversity and can be generalized to unseen domains due to its cross-domain nature and the unseened databases at test time. |
CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | coding tasks require generated code to be fully executable and functionally correct . current agentic approaches struggle with multi-stage planning, generating, and debugging . |
| Approach: | They propose a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. |
| Outcome: | The proposed framework achieves top results on 7 code generation benchmarks and a 31.9% solving rate on the SWEBench benchmark. |
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)
Copied to clipboard
| Challenge: | High-Level Synthesis (HLS) is a hardware design tool that can be used to design hardware from C-like languages, but its widespread adoption is limited by strict coding constraints and design-specific optimizations. |
| Approach: | They propose a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning. |
| Outcome: | The proposed framework outperforms Gemini-3-pro in debugging and speedups across various HLS kernels and neural network accelerators. |
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. |
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)
Copied to clipboard
Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen
| Challenge: | Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection. |
| Approach: | They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization. |
| Outcome: | The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models. |
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)
Copied to clipboard
Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng
| Challenge: | Existing studies on large language model-based agents focus on evaluation benchmarks without training support. |
| Approach: | They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents. |
| Outcome: | The proposed model performs poorly in a large-scale and challenging shopping environment in China. |
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. |
Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Continual Learning (CL) have limited KT and catastrophic forgetting . a new method overcomes CF by isolating the knowledge of each task . |
| Approach: | They propose a method to overcome catastrophic forgetting and encourage knowledge transfer . they propose to discover a sub-network for each task and a soft-masking mechanism to preserve the previous knowledge. |
| Outcome: | The proposed method outperforms baselines in classification, generation, information extraction and their mixture. |
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. |
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. |
Certified Robustness to Word Substitution Attack with Differential Privacy (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that adversarial examples can be easily fooled by DNNs, making the robustness and security of NLP models significantly important. |
| Approach: | They propose a differential privacy-based algorithm to achieve certified robustness against word substitution at- tacks in text classification via differential privacy. |
| Outcome: | The proposed model achieves higher accuracy and more than 30X efficiency improvement over existing defense algorithms. |
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting. |
| Approach: | They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations. |
| Outcome: | The proposed method achieves state-of-the-art on three text classification tasks. |
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables. |
| Approach: | They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input. |
| Outcome: | The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets. |
Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs. |
| Approach: | They propose a framework with three modules designed to assess diversity, redundancy, and difficulty. |
| Outcome: | The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs. |
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. |
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
| Challenge: | Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure. |
| Approach: | They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction. |
| Outcome: | The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models. |
Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability Patching (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing gradient-based attribution methods are inapplicable to adversarial attacks . et al.: Targeted neuron tuning improves model robustness against jailbreak attacks despite the model's vulnerability to jailbreak. |
| Approach: | They propose a gradient-based method to identify key neurons sensitive to adversarial behaviors in open-ended generation tasks. |
| Outcome: | The proposed method detects key neurons sensitive to adversarial behaviors in open-ended tasks. |
CausalEval: Towards Better Causal Reasoning in Language Models (2025.naacl-long)
Copied to clipboard
Longxuan Yu, Delin Chen, Siheng Xiong, Qingyang Wu, Dawei Li, Zhikai Chen, Xiaoze Liu, Liangming Pan
| Challenge: | Large language models (LLMs) have been used for a variety of tasks, including problem-solving, decision-making, and understanding of the world. |
| Approach: | They propose a review of existing methods aimed at enhancing LMs for causal reasoning . they categorize existing methods as reasoning engines or as helpers providing knowledge or data to traditional methods . |
| Outcome: | The proposed methods perform better than existing methods on a range of tasks. |
CogNet-KG: Empowering Tutoring Dialogues with a Cognitively-Structured Knowledge Graph for STEM Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Educational knowledge graphs are a critical component of intelligent tutoring systems that are structured around cognitive principles and provide support for interactive teaching. |
| Approach: | They propose a cognitively-structured large-scale knowledge graph for STEM learning that models nearly 500 core concepts across five subjects with various cognitively grounded relations corresponding to specific learning objectives. |
| Outcome: | The proposed model generates a high-quality tutoring dialogue dataset CogDialogue-QA and a specialized tutorial LLM that internalizes this structured pedagogical reasoning. |
Learning to Ask Denotative and Connotative Questions for Knowledge-based VQA (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have attracted increasing attention due to their prominent performance on various tasks. |
| Approach: | They propose to let LLMs learn to ask informative questions to collect visual information . they introduce concepts of denotation and connotation to promote image and question understanding . |
| Outcome: | The proposed model can generate high-quality questions and efficiently collect required information without expensive training or annotations. |
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. |
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)
Copied to clipboard
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths. |
| Approach: | They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO. |
| Outcome: | The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages. |
Direct Token Optimization: A Self-Contained Approach to Large Language Model Unlearning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for large language models (LLMs) rely on external resources such as auxiliary models, retain datasets, or even commercial AI services. |
| Approach: | They propose a self-contained unlearning approach that optimizes the token-level objectives to unlearn specific sequences without external resources. |
| Outcome: | The proposed approach improves the forget quality up to 16.8 over the latest benchmarks while maintaining comparable model utility. |
e-CARE: a New Dataset for Exploring Explainable Causal Reasoning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing causal reasoning models only learn to induce empirical causal patterns that are predictive to the label, while human beings seek for deep and conceptual understanding of the causality to explain the observed causal facts. |
| Approach: | They present a human-annotated CAusal REasoning dataset with conceptual explanations of the causality. |
| Outcome: | The presented dataset shows that human-annotated explanations can be useful for promoting the accuracy and stability of causal reasoning models. |
Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs (2024.findings-acl)
Copied to clipboard
| Challenge: | Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. |
| Approach: | They propose a pluggable CTG framework for Large Language Models to control text . they use attribute scorers to evaluate attributes of sentences and construct dynamic attribute graphs . |
| Outcome: | The proposed framework achieves a peak improvement of 19.29% over baseline methods in two tasks. |
Multi-View Active Learning for Short Text Classification in User-Generated Data (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Using a microblog, a set of tasks can be tailored for queries. |
| Approach: | They propose a novel active learning model to overcome the lack of labeled data and the informal user language in mining user-generated data. |
| Outcome: | The proposed model outperforms existing models in four publicly available Twitter datasets and in four datasets with different applications. |
Rethinking Long Context Generation from the Continual Learning Perspective (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) struggle with processing long contexts due to the limited context window. |
| Approach: | They propose to combine a limited context window with a continual learning perspective to improve LLMs' efficiency in processing long contexts. |
| Outcome: | The proposed models improve the performance of Large Language Models (LLMs) by integrating learning strategies with existing approaches. |
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues spanning over 12 domains . despite of substantial progress made, there are challenges in creating challenging datasets in terms of size, multiple domains, semantic annotations and complexity. |
| Approach: | They propose a large-scale multi-domain Chinese Wizard-of-Oz dataset with rich semantic annotations that captures discourse phenomena for task-oriented dialogue modeling. |
| Outcome: | The proposed dataset contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues with more than 150K utterances spanning over 12 domains. |
Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data (2023.findings-acl)
Copied to clipboard
| Challenge: | Structure Aware Dense Retrieval (SANTA) model encodes user queries and structured data in one universal embedding space for retrieving structured data. |
| Approach: | They propose to use structured data and unstructured data to encode queries and structured data in one universal embedding space for retrieving structured data. |
| Outcome: | The proposed model achieves state-of-the-art on code search and product search and conducts convincing results in the zero-shot setting. |
LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown promising results in multilingual translation with limited bilingual supervision. |
| Approach: | They propose a Language-Aware Neuron Detecting and Routing framework that fine tunes LLMs to Machine Translation with diverse translation training data. |
| Outcome: | The proposed framework selectively finetunes LLMs to MT tasks with diverse translation training data. |
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. |
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples. |
| Approach: | They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks. |
| Outcome: | Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies. |
Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025.acl-long)
Copied to clipboard
| Challenge: | Recent research shows that vertical text input significantly degrades the accuracy of large language models (LLMs) in text classification tasks. |
| Approach: | They investigate the impact of vertical text input on the performance of LLMs . they find that chain of thought reasoning does not help LLM recognize vertical input . |
| Outcome: | The proposed model can significantly mislead models, posing a risk of bypassing detection in real-world scenarios involving harmful or sensitive information. |
Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) is an endto-end learning approach to machine translation. |
| Approach: | They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation. |
| Outcome: | The proposed network achieves comparable results with the Transformer system on English-German and English-French 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. |
WorkTeam: Constructing Workflows from Natural Language with Multi-Agents (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing workflow construction methods require specialized knowledge and task-switching skills. |
| Approach: | They propose a multi-agent workflow framework that incorporates a supervisor, orchestrator, and filler agent. |
| Outcome: | The proposed framework significantly increases the success rate of workflow construction . the proposed framework is based on a dataset of 3,695 real-world business samples . |
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading (2020.emnlp-main)
Copied to clipboard
Yifan Gao, Chien-Sheng Wu, Jingjing Li, Shafiq Joty, Steven C.H. Hoi, Caiming Xiong, Irwin King, Michael Lyu
| Challenge: | Document interpretation and dialog understanding are the two major challenges for conversational machine reading. |
| Approach: | They propose a discourse-aware entailment reasoning network to strengthen the connection and enhance the understanding of document and dialog. |
| Outcome: | The proposed model improves document interpretation and dialog understanding on the ShARC benchmark. |
What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases (2024.naacl-long)
Copied to clipboard
| Challenge: | Vision-language models have broad competence that is difficult to evaluate . current evaluation benchmarks focus on only assessing one or a few capabilities . |
| Approach: | They perform a large-scale transfer learning experiment to discover latent VL skills from data. |
| Outcome: | The results suggest that factor analysis can identify reasonable yet surprising VL skill factors . the results contribute to the design of balanced and broad-coverage vision-language evaluation methods. |
Generative Frame Sampler for Long Video Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing video large language models (LMMs) employ an impedance of thousands of frames to understand long videos. |
| Approach: | They propose a plug-and-play module integrated with VideoLLMs to facilitate efficient lengthy video perception. |
| Outcome: | The proposed module boosts the performance of open-source VideoLLMs and proprietary assistants on long-form video benchmarks. |
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. |
Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing neural machine translation models are not able to translate dialogues in real life scenarios. |
| Approach: | They propose a joint learning method to identify omission and typos and utilize context to translate dialogue utterances. |
| Outcome: | The proposed method improves translation quality by 3.2 BLEU over baselines and recovers omitted pronouns by 47.16%. |
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data. |
| Approach: | They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches. |
| Outcome: | The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance. |
EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for personality detection ignore the connection between psychological knowledge “emotion regulation” and personality traits. |
| Approach: | They propose to use emotion regulation and emotion features to retrieve few-shot samples and provide process CoTs for inferring labels from text. |
| Outcome: | The proposed method outperforms SOTA by 15.05/4.29 on the two benchmark datasets. |
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing defenses for large language models do not account for the sequential nature of text data. |
| Approach: | They propose a lightweight yet effective empirical privacy defense that leverages token-specific characteristics to protect training data of large language models. |
| Outcome: | The proposed approach provides strong protection against membership inference attacks and improves language modeling performance by 10% across different LLM architectures and datasets compared to baselines. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that multilingual pretrained models can recall factual knowledge without additional fine-tuning. |
| Approach: | They propose two parameter-free language representation projection modules to transfer factual knowledge between English and non-English languages. |
| Outcome: | The proposed modules improve factual knowledge retrieval accuracy and transferability across diverse non-English languages. |
DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)
Copied to clipboard
Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang
| Challenge: | Recent advances in neural theorem-proving resort to large language models and tree searches. |
| Approach: | They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate. |
Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversity (2025.findings-emnlp)
Copied to clipboard
Zihao Li, Feihao Fang, Xitong Zhang, Jiaru Zou, Zhining Liu, Wei Xiong, Ziwei Wu, Baoyu Jing, Jingrui He
| Challenge: | Using real-world datasets, we conduct the most comprehensive study to date, auditing various state-of-the-art reward models across nine sensitive attributes, including age, gender, ethnicity, etc. |
| Approach: | They propose a method to mitigate group disparities in reward modeling by using real-world data. |
| Outcome: | The proposed method is based on a population-based dataset with nine demographic attributes, including gender, ethnicity, age, gender, and ethnicity. |
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 . |
GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones. |
| Approach: | They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM. |
| Outcome: | The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task. |
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. |
Secoco: Self-Correcting Encoding for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a challenging field due to the wide variety of noises in real-world scenarios. |
| Approach: | They propose a framework that explicitly deals with noisy inputs for robust neural machine translation by introducing self-correcting predictors. |
| Outcome: | The proposed framework can correct noisy inputs and delete specific errors with the translation decoding process. |
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)
Copied to clipboard
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
| Challenge: | Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking. |
| Approach: | They propose an iterative adversarial training method that incorporates three key innovations to address these challenges. |
| Outcome: | Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%. |
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)
Copied to clipboard
Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen
| Challenge: | Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance. |
| Approach: | They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator. |
| Outcome: | The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16. |
Let Retrievers Think Before Action: Thought-Augmented Embedding for Dense Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models have demonstrated that explicit step-by-step thinking can substantially improve performance on complex tasks. |
| Approach: | They propose a model that generates preliminary thoughts for input queries before document retrieval. |
| Outcome: | The proposed model generates preliminary thoughts for input queries before document retrieval. |
Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. |
| Approach: | They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods. |
| Outcome: | The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models. |
Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multitask dense retrieval are not effective due to corpus inconsistency. |
| Approach: | They propose to train individual dense passage retrievers for different open-domain question-answering tasks and aggregate their predictions during test time. |
| Outcome: | The proposed method achieves state-of-the-art performance on 5 benchmark QA datasets, with up to 10% improvement in top-100 accuracy compared to a joint-training multi-task DPR on SQuAD. |
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (2025.findings-emnlp)
Copied to clipboard
Yubin Kim, Zhiyuan Hu, Hyewon Jeong, Eugene W Park, Shuyue Stella Li, Chanwoo Park, Shiyun Xiong, MingYu Lu, Hyeonhoon Lee, Xin Liu, Daniel McDuff, Cynthia Breazeal, Samir Tulebaev, Hae Won Park
| Challenge: | Large Language Models (LLMs) struggle with proactive engagement, authors say . a blind clinical evaluation confirmed that trained agents exhibit more realistic clinical behavior . |
| Approach: | They propose a training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection. |
| Outcome: | The proposed training strategy boosts performance on both benchmarks. |
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. |
MPO: Boosting LLM Agents with Meta Plan Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for interactive planning tasks suffer from planning hallucinations and require retraining for each new agent. |
| Approach: | They propose a framework that leverages explicit guidance through meta plans to assist agent planning and enables continuous optimization based on feedback from the agent’s task execution. |
| Outcome: | The proposed framework outperforms existing baselines on two representative tasks and significantly improves task completion efficiency and generalization capabilities. |
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text chunking are limited by text chunks and lack of domain-specific knowledge. |
| Approach: | They propose a dual-metric evaluation method to quantify text chunking quality . they aim to generate a structured list of chunking regular expressions . |
| Outcome: | The proposed method enables direct quantification of chunking quality . it substantiates the need to integrate LLMs into chunking process . |
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)
Copied to clipboard
Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang
| Challenge: | Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input. |
| Approach: | They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy . |
| Outcome: | The proposed model outperforms the latest SOTA methods in terms of performance and generalization. |
Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work reserves the principle dimensions of query and document embeddings for building more efficient retrieval systems. |
| Approach: | They propose to use Conditional Autoencoder to compress high-dimensional embeddings to maintain the same embeddable distribution and better recover ranking features. |
| Outcome: | The proposed algorithm achieves comparable ranking performance with its teacher model and makes the retrieval system more efficient. |
KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base (2022.acl-long)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks for conversational question answering do not handle uncertain reasoning . qa over large knowledge bases has attracted broad interest due to the popularity of intelligent virtual assistants . |
| Approach: | They propose a fuzzy semantic parsing framework that defines fuzzy comparison operations in grammar for uncertain reasoning based on fuzzy set theory. |
| Outcome: | The proposed framework achieves significant improvements over state-of-the-art models on a large-scale conversational question answering benchmark. |
ConTinTin: Continual Learning from Task Instructions (2022.acl-long)
Copied to clipboard
| Challenge: | a new learning paradigm is proposed for NLP, which seeks supervision for solving a target task. |
| Approach: | They propose a new learning paradigm that uses textual instructions to learn new tasks . the main goal of machine learning algorithms lies in seeking supervision for solving a target task. |
| Outcome: | The proposed learning paradigm is based on a stream of more than 60 tasks . it makes full use of task instructions to improve forward-transfer and backward-transference . |
Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification. |
| Approach: | They explicitly align large reasoning models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks. |
| Outcome: | The proposed model aligns models with deduction, induction, and abduction meta-abilities using automatically generated, self-verifiable tasks. |
MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based sparse architectures are prone to overfitting on low-resource language translation. |
| Approach: | They propose a modularized MNMT framework that flexibly assembles dense and MoE-based sparse modules to achieve the best of both worlds. |
| Outcome: | The proposed framework outperforms existing models on low-resource language translation and zero-shot translation on benchmark datasets. |
Rationale-Enhanced Language Models are Better Continual Relation Learners (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations. |
| Approach: | They propose a multi-task rationale tuning strategy to help the model learn current relations robustly and conduct contrastive rationale replay to further distinguish analogous relations. |
| Outcome: | The proposed method outperforms the state-of-the-art models on two benchmarks. |
Detecting Machine-Generated Text: Techniques and Challenges (2024.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial focuses on machine-generated text and deepfakes. |
| Approach: | This tutorial aims to provide a comprehensive overview of text detection techniques . it will focus on machine-generated text and deepfakes . |
| Outcome: | This tutorial focuses on machine-generated text and deepfakes. |
Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)
Copied to clipboard
Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu
| Challenge: | Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability. |
| Approach: | They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures. |
| Outcome: | The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios. |
Bacteria Biotope Relation Extraction via Lexical Chains and Dependency Graphs (D19-57)
Copied to clipboard
| Challenge: | In this paper, we describe our approach for the Bacteria Biotopes relation extraction subtask in the BioNLP Shared Task 2019 . |
| Approach: | They propose a novel approach for dependency graph construction based on lexical chains . they then propose 'neuro network' model which uses short-term memories and syntax information . |
| Outcome: | The proposed approach achieves the best F1 (66.3%) in the official evaluation participated by 7 teams. |
Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)
Copied to clipboard
Songju Lei, Xize Cheng, Mengjiao Lyu, Jianqiao Hu, Jintao Tan, Runlin Liu, Lingyu Xiong, Tao Jin, Xiandong Li, Zhou Zhao
| Challenge: | Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video. |
| Approach: | They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights. |
| Outcome: | The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio. |
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. |
SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multi-hop knowledge graph reasoning suffer from slow and poor convergence . a transformer model can be used to learn and predict in an end-to-end fashion, giving faster convergence compared to previous methods . |
| Approach: | They propose a Sequence-to-sequence based multi-hop reasoning framework . it uses an encoder-decoder transformer structure to translate the query to a path . |
| Outcome: | The proposed framework can learn and predict in an end-to-end fashion, which gives better and faster convergence. |
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs. |
| Approach: | They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories. |
| Outcome: | The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models. |
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. |
Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)
Copied to clipboard
| Challenge: | Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct. |
| Approach: | They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns. |
| Outcome: | The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns. |
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)
Copied to clipboard
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
| Challenge: | Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately . |
| Approach: | They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes . |
| Outcome: | The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show . |
End-to-End Open-Domain Question Answering with BERTserini (N19-4)
Copied to clipboard
| Challenge: | a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles. |
| Approach: | They propose an end-to-end question answering system that integrates BERT with an IR reader. |
| Outcome: | The proposed system improves on a standard benchmark test collection. |
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. |
Socratic Human Feedback (SoHF): Expert Steering Strategies for LLM Code Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used for generating code solutions, but struggle with complex programming problems without human guidance. |
| Approach: | They use the “Socratic Feedback” paradigm to map observed feedback strategies to five stages of Socratic Questioning to identify failures in LLMs. |
| Outcome: | The proposed models solved 74% of the problems that the models initially failed to solve on their own. |
ExCAR: Event Graph Knowledge Enhanced Explainable Causal Reasoning (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work infers the causation between events based on knowledge from annotated causal event pairs, but additional evidence information is unexploited. |
| Approach: | They propose an Event graph knowledge enhanced explainable CAusal Reasoning framework that acquires additional evidence information from a large-scale causal event graph as logical rules for causal reasoning. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in human evaluation and in animal models. |
Com2 : A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models (2025.acl-long)
Copied to clipboard
Kai Xiong, Xiao Ding, Yixin Cao, Yuxiong Yan, Li Du, Yufei Zhang, Jinglong Gao, Jiaqian Liu, Bing Qin, Ting Liu
| Challenge: | Existing works focus on complex tasks like math and code, while complex commonsense reasoning remains underexplored due to its uncertainty and lack of structure. |
| Approach: | They propose to build a benchmark for large language models based on complex commonsense reasoning based upon causal event graphs and causal theory. |
| Outcome: | The proposed benchmark combines a complex commonsense reasoning benchmark with a detective story to achieve a more challenging subset. |
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. |
QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)
Copied to clipboard
Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang
| Challenge: | Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses, but the inherent gap between user queries and relevant documents hinders precise matching. |
| Approach: | They propose a retrieval-augmented generation (RAG)-based approach to bridge this gap by attaching document fingerprints to the embedding to estimate the expectation of potential queries. |
| Outcome: | Experiments across diverse datasets, languages, and embedding models confirm the proposed solution is simple-yet-effective with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues. |
PsyPath: Psychologically-guided Self-Exploration for Personality Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Personality detection aims to label traits via identifying linguistic cues from written text. |
| Approach: | They propose a framework that allows large language models to generate and answer psychologically meaningful questions and a hybrid scoring mechanism to evaluate the generated nodes in the reasoning paths. |
| Outcome: | The proposed framework outperforms baselines on two benchmark datasets and significantly improves performance and interpretability in downstream tasks. |
T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)
Copied to clipboard
Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li
| Challenge: | Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications. |
| Approach: | They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning. |
| Outcome: | The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation. |
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)
Copied to clipboard
Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo
| Challenge: | a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Approach: | They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Outcome: | The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains. |
PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Image translation is a task that translates an image containing text in the source language to the target language. |
| Approach: | They propose an end-to-end image translation framework that bridges the modality gap between visual inputs and textual inputs/outputs of machine translation (MT). |
| Outcome: | The proposed framework outperforms existing models on a large-scale image translation corpus . it significantly outperformed both cascaded and strong models on the e-commerce domain . |
GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods for large language models rely on static benchmarks and standardized evaluation protocols. |
| Approach: | They propose an adaptive evaluation framework that integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity. |
| Outcome: | Empirical results show that the framework distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness. |
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. |
SPE: Symmetrical Prompt Enhancement for Fact Probing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work probes PLMs for the extent of factual knowledge through prompts . however, these methods do not consider symmetry of the task: object and subject prediction. |
| Approach: | They propose a continuous prompt-based method that leverages symmetry of the task by constructing symmetrical prompts for subject and object prediction. |
| Outcome: | The proposed method improves on a popular factual probing dataset on lAMA. |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
Trigger Word Detection and Thematic Role Identification via BERT and Multitask Learning (D19-57)
Copied to clipboard
| Challenge: | Using natural language processing to discover and mine drug-related knowledge from text has been a hot topic in recent years. |
| Approach: | They propose to use a pre-trained biomedical language representation model to extract mutation-disease knowledge from PubMed. |
| Outcome: | The proposed approaches achieve 0.60 (ranks 1) and 0.25 (rank 2) on task 1 and task 2 respectively in terms of F1 metric. |
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)
Copied to clipboard
Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev
| Challenge: | CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems. |
| Approach: | They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries . |
| Outcome: | The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains. |
A Structure-Aware Generative Adversarial Network for Bilingual Lexicon Induction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Bilingual lexicon induction (BLI) is the task of inducing word translations with a learned mapping function that aligns monolingual word embedding spaces in two different languages. |
| Approach: | They propose a model that explicitly captures multiple topological structure information to achieve accurate bilingual lexicon induction. |
| Outcome: | The proposed model captures multiple topological structure information to achieve accurate BLI on a public dataset. |
Towards Optimal Evaluation Efficiency for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) require large-scale benchmarks, which are costly in terms of time, computational resources, or API tokens. |
| Approach: | They propose an efficient evaluation framework that selects a question subset based on pre-tested results and uses semantic analysis to evaluate whether the subset preserves the original benchmark. |
| Outcome: | The proposed evaluation framework outperforms previous methods in reliability and score accuracy. |
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)
Copied to clipboard
Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin
| Challenge: | e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features. |
| Approach: | They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent. |
| Outcome: | The proposed model outperforms baseline models and provides better recall and triage for specialized agents. |
HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Traditional retrieval systems focus on lexical or semantic similarity rather than logical relevance. |
| Approach: | They propose a new RAG framework that augments retrieval with logical reasoning . hopRAG uses a retrieve-reason-prune mechanism to explore multi-hop neighbors . |
| Outcome: | The proposed framework outperforms conventional retrieval systems and state-of-the-art benchmarks on multi-hop QA tasks. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
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. |
CARE-STaR: Constraint-aware Self-taught Reasoner (2025.findings-acl)
Copied to clipboard
Zhiliang Li, Bo Tang, Yijun Niu, Beihong Jin, Qiwen Shi, Yuchen Feng, Zhiyu Li, Jie Hu, Mingchuan Yang, Feiyu Xiong
| Challenge: | Recent research on instruction following has demonstrated that LLMs can handle complex instructions. |
| Approach: | They propose to assign constraints to different levels of constraints in instructions . they use chain-of-thought and self-taught reasoner methods to identify constraints . |
| Outcome: | The proposed method outperforms supervised fine-tuning (SFT) on three instruction-following benchmarks. |
Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) are difficult to evaluate and often lack the ability to capture user opinions. |
| Approach: | They propose an LLM-powered interviewer that conducts in-the-moment user experience interviews right after users interact with LLMs and automatically gathers insights about user opinions from massive interview logs. |
| Outcome: | The proposed interviewer captures interesting user opinions, e.g., bipolar views on the displayed reasoning process of DeepSeek-R1 and demands for information freshness and multi-modality. |
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)
Copied to clipboard
Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang
| Challenge: | Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs . |
| Approach: | They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service . |
| Outcome: | The proposed benchmark evaluates the security of RAG against 14 representative RAG components. |
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. |
MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong performance even with limited parallel data. |
| Approach: | They propose a multiple language-aware LoRA knowledge transfer framework that selectively adapts LLMs to MT by transferring knowledge from a large teacher to a small student model. |
| Outcome: | The proposed framework outperforms baseline models on multilingual language pairs by +1.7 BLEU on average. |
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies. |
| Approach: | They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward. |
| Outcome: | The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach. |
Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like the Model Context Protocol (MCP). |
| Approach: | They investigate the vulnerability of Large Language Models to hidden adversarial prompts . they evaluate two critical attack scenarios: malicious content relay and sensitive data leakage . |
| Outcome: | The proposed extension could introduce new security vulnerabilities. |