Papers by Chen Zeng
Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for dialogue state tracking with domain-slot-value labels are expensive . current models are limited due to high cost of data annotation and lack of data in some domains . |
| Approach: | They propose a framework based on domain-slot related description to tackle the challenge of few-shot cross-domain DST. |
| Outcome: | The proposed framework outperforms existing methods on MultiWOZ and gains strong slot accuracy compared to existing models. |
FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing classification and regression models that only extract finer-grained information from magnetic resonance imaging (MRI) may not be effective for Alzheimer's disease (AD). |
| Approach: | They propose to use a 3D Adapter in a Vision Transformer to extract the patient's EHR information and questions related to the disease as text prompts. |
| Outcome: | The proposed model can discriminate and predict the corresponding MMSE score based on the extracted brain structural information and textual content . |
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)
Copied to clipboard
Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu
| Challenge: | Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited. |
| Approach: | They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm. |
| Outcome: | The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%. |
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)
Copied to clipboard
Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang
| Challenge: | Current multimodal large language models (MLLMs) show limited understanding of dental images. |
| Approach: | They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning. |
| Outcome: | The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks. |
Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument Extraction (2024.findings-acl)
Copied to clipboard
Wanlong Liu, Li Zhou, DingYi Zeng, Yichen Xiao, Shaohuan Cheng, Chen Zhang, Grandee Lee, Malu Zhang, Wenyu Chen
| Challenge: | mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring correlations among multiple events. |
| Approach: | They propose a multi-event argument argument extraction model which extracts arguments from all events simultaneously. |
| Outcome: | The proposed model performs better on four public datasets while saving time. |
LLM-Rec: Personalized Recommendation via Prompting Large Language Models (2024.findings-naacl)
Copied to clipboard
Hanjia Lyu, Song Jiang, Hanqing Zeng, Yinglong Xia, Qifan Wang, Si Zhang, Ren Chen, Chris Leung, Jiajie Tang, Jiebo Luo
| Challenge: | Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning. |
| Approach: | They propose a novel approach which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations. |
| Outcome: | The proposed approach improves recommendation quality and even basic MLP models achieve comparable or even better results than complex content-based methods. |
Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Latent Synthesis is an efficient textual data utilization framework for end-to-end speech processing models . labeled speech data are scarcer and more expensive for collection compared to textual ones . |
| Approach: | They propose a textual data utilization framework for E2E speech processing models . they train a latent synthesizer to convert textual information into an intermediate latent representation . |
| Outcome: | The proposed framework improves on low-resource speech recognition and spoken language understanding tasks. |
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)
Copied to clipboard
| Challenge: | a number of tools are used to perform complex tasks, but the tool utilization process can cause errors. |
| Approach: | They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks. |
| Outcome: | The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios. |
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)
Copied to clipboard
Jun Zhang, Yicheng Ji, Feiyang Ren, Yihang Li, Bowen Zeng, Zonghao Chen, Ke Chen, Lidan Shou, Gang Chen, Huan Li
| Challenge: | Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance. |
| Approach: | They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks . |
| Outcome: | The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding . |
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)
Copied to clipboard
| Challenge: | Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead. |
| Approach: | They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type . |
| Outcome: | The proposed method can prevent the linear growth of the privacy budget. |
An Empirical Study of Frame Selection for Text-to-Video Retrieval (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for text-to-video retrieval select a subset of frames to represent video content . current methods only explore video contents while ignoring relevancy to texts . |
| Approach: | They propose to use a subset of frames to represent video content for TVR . they analyze six different frame selection methods to determine their effectiveness . |
| Outcome: | The proposed method improves retrieval efficiency without sacrificing visual details . the proposed method explores the video contents while ignoring relevancy to texts . |
Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for text classification based on large language models are difficult to apply directly to solve. |
| Approach: | They propose a data quality enhancement method to improve LLMs' performance in classification tasks by using a greedy algorithm to select data and then performing fine-tuning. |
| Outcome: | The proposed method improves the performance of large language models in text classification tasks and significantly improves training efficiency, saving nearly half of the training time. |
Multilingual Brain Surgeon: Large Language Models Can Be Compressed Leaving No Language behind (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for MC focus on quantization and network pruning. |
| Approach: | They propose a calibration method that samples calibration data from various languages proportionally to the language distribution of the model training datasets. |
| Outcome: | The proposed method improves the performance of existing English-centric compression methods on the BLOOM multilingual LLM. |
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang
| Challenge: | Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. |
| Approach: | They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data. |
| Outcome: | The proposed framework transforms user-generated content into user queries and generates responses from the policy model. |
Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK). |
| Approach: | They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two popular datasets. |
A Compressive Memory-based Retrieval Approach for Event Argument Extraction (2025.coling-main)
Copied to clipboard
| Challenge: | Existing retrieval-based EAE methods have input length constraints and the gap between the retriever and the inference model. |
| Approach: | They propose a retrieval-based retrieval mechanism that overcomes input length constraints . they use compressive memory to cache retrieved information and support continuous updates . |
| Outcome: | The proposed method outperforms retrieval-based methods on three public datasets. |
MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)
Copied to clipboard
Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng, Jianhui Chen, Lei Hou, Xu Han, Yankai Lin, Zhiyuan Liu, Ruobing Xie, Jie Zhou, Juanzi Li
| Challenge: | Existing datasets for event understanding have limited coverage due to complexity of tasks. |
| Approach: | They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation . |
| Outcome: | The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction. |
Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)
Copied to clipboard
Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin
| Challenge: | Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation" |
| Approach: | They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations. |
| Outcome: | The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC) |
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks. |
| Approach: | They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety. |
| Outcome: | The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs. |
An Iteratively Parallel Generation Method with the Pre-Filling Strategy for Document-level Event Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generate event roles require a given generation order . parallel methods suffer from inadequate training and manifest zero accuracies on some event roles. |
| Approach: | They propose an iteratively parallel generation method with the Pre-Filling strategy to generate event roles in parallel to avoid order selection. |
| Outcome: | The proposed method outperforms other entity-enhanced models and achieves state-of-the-art performance on two public datasets. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). |
| Approach: | They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM. |
| Outcome: | The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%. |
FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue (2023.acl-long)
Copied to clipboard
| Challenge: | Existing pre-trained language models rely on a contrastive framework and are difficult to use in practice. |
| Approach: | They propose a dialogue pre-training model which distills future knowledge to the representation of the previous dialogue context using a self-training framework. |
| Outcome: | The proposed model can be applied to various downstream dialogue tasks. |
GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement learning fine-tuning methods suffer from inefficient exploration and slow convergence . supervised fine- tuning methods have limited performance ceiling and less solid theoretical foundation . |
| Approach: | They propose a Guess-Think-Answer framework that combines supervised and supervised learning in a unified training paradigm. |
| Outcome: | The proposed framework outperforms both standalone SFT and RL training models on three text classification benchmarks. |
CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models (2026.acl-long)
Copied to clipboard
Haibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Ruolin Chen, Yinqian Sun, Qian Zhang, Yi Zeng
| Challenge: | Existing benchmarks for Large Language Models (LLMs) are limited to false belief tasks, highlighting bottlenecks in specific dimensions. |
| Approach: | They propose a benchmark to evaluate Large Language Models' Theory of Mind capabilities . they evaluate 8000 bilingual instances across 46 paradigms and validated by 49 human annotators . |
| Outcome: | The proposed benchmark reveals performance heterogeneities and bottlenecks in 22 representative models. |
Xiaomingbot: A Multilingual Robot News Reporter (2020.acl-demos)
Copied to clipboard
Runxin Xu, Jun Cao, Mingxuan Wang, Jiaze Chen, Hao Zhou, Ying Zeng, Yuping Wang, Li Chen, Xiang Yin, Xijin Zhang, Songcheng Jiang, Yuxuan Wang, Lei Li
| Challenge: | Xiaomingbot is a multilingual and multimodal software robot with four capabilities: news generation, news translation, news reading and avatar animation. |
| Approach: | They propose to build a multilingual and multimodal software robot with four inte- gal capabilities: news generation, news translation, news reading and avatar animation. |
| Outcome: | The proposed system generates Chinese news, then reads it in multiple languages and generates an animated avatar reading it. |
Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction (2024.acl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Quad Prediction (ASQP) aims to predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review. |
| Approach: | They propose a self-training framework with a pseudo-label scorer to assess the match between reviews and their pseudo-labels and train a generative model on it. |
| Outcome: | The proposed framework can predict all quads (aspect term, aspect category, opinion term, sentiment polarity) for a given review, and it can significantly improve self-training. |
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. |
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)
Copied to clipboard
Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang
| Challenge: | i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data. |
| Approach: | They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data. |
| Outcome: | i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks. |
BiKT: Enabling Bidirectional Knowledge Transfer Between Pretrained Models and Sequential Downstream Tasks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing frameworks adapt from initial pretrained model to each downstream task directly, but ignore sequential nature of downstream tasks and feedback effect on pretrained models. |
| Approach: | They propose a framework to enable bidirectional knowledge transfer between pretrained models and downstream tasks in rounds. |
| Outcome: | The proposed framework improves on 9 GLUE datasets and 6 SuperGLUEs. |
PersLLM: A Personified Training Approach for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. |
| Approach: | They propose a framework for better data construction and model tuning to unlock the potential of LLM personification by using Chain-of-Thought prompting and anti-induction. |
| Outcome: | The proposed framework improves data construction and model tuning for insufficient data usage and rigid behavior patterns. |
Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation (2026.acl-industry)
Copied to clipboard
| Challenge: | PRISM-DUEL is a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) PRIMS-DUEl is motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ad. |
| Approach: | They propose a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) they obtain label-free pairwise preferences and rationales from an LLM judge over pairs of generated images and use a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad's visual content. |
| Outcome: | The proposed framework preserves visual similarity and semantic faithfulness while increasing diversity. |
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su
| Challenge: | Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context. |
| Approach: | They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration. |
| Outcome: | Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness. |
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)
Copied to clipboard
Damai Dai, Chengqi Deng, Chenggang Zhao, R.x. Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y. Wu, Zhenda Xie, Y.k. Li, Panpan Huang, Fuli Luo, Chong Ruan, Zhifang Sui, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs. |
| Approach: | They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them. |
| Outcome: | The proposed architecture achieves comparable performance with GShard with 2B parameters and computation. |
MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora. |
| Approach: | They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization . |
| Outcome: | The proposed method improves the generalization performance of large langugae models. |
Instant Personalized Large Language Model Adaptation via Hypernetwork (2026.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang
| Challenge: | Existing parameter-efficient fine-tuning methods require training a separate adapter for each user, making them computationally expensive and impractical for real-time updates. |
| Approach: | They propose a scalable framework that maps a user's profile directly to a full set of adapter parameters. |
| Outcome: | The proposed framework outperforms prompt-based personalization and OPPU while using substantially fewer computational resources at deployment. |
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)
Copied to clipboard
Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui
| Challenge: | coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored . |
| Approach: | They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding. |
| Outcome: | The proposed benchmark aims to accelerate the development of more scaffold-aware agents. |
KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases (2025.findings-emnlp)
Copied to clipboard
Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing methods for retrieval-augmented generation (RAG) are limited and fine-tuning incurs prohibitive costs of external signals. |
| Approach: | They propose a self-supervised framework that enhances RAG systems through efficient model adaptation. |
| Outcome: | The proposed framework achieves 90% of the performance gain obtained through GPT-4-supervised adaptation while relying entirely on self-annotation of much smaller models. |
AdaFuse: Adaptive Ensemble Decoding for Large Language Models (2026.acl-long)
Copied to clipboard
Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He
| Challenge: | Existing ensemble approaches to large language models lack flexibility for mid-generation adaptation. |
| Approach: | They propose an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation. |
| Outcome: | The proposed framework outperforms existing ensemble frameworks on open-domain QA, arithmetic reasoning, and machine translation tasks. |
Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)
Copied to clipboard
Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu
| Challenge: | Despite the success of speech recognition, how to encode the speech features effectively remains an open problem. |
| Approach: | They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation. |
| Outcome: | The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x. |
KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches in NLP focus on “WHY A” rather than contrastive “WHA NOT B” Experimental results show that contrastive explanations are beneficial to fit the scenarios by clarifying the difference between the predicted answer and other possible wrong ones. |
| Approach: | They propose to generate contrastive explanations with counterfactual examples in NLI by identifying key phrases from input sentences and using them as key perturbations to generate counterfacts. |
| Outcome: | The proposed framework improves on SNLI and ETPA models by 91.9%. |
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models generate hallucinated text when confronted with false premise questions . authors propose a method to mitigate false premises hallucinosity . |
| Approach: | They propose a method to constrain false premise attention heads during the model inference process. |
| Outcome: | The proposed method improves performance by constraining false premise attention heads . it yields a notable increase of nearly 20% of model performance . |
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)
Copied to clipboard
Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James Kwok, Yu Zhang
| Challenge: | Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality. |
| Approach: | They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data. |
| Outcome: | The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data. |
VERITAS: Leveraging Vision Priors and Expert Fusion to Improve Multimodal Data (2025.emnlp-main)
Copied to clipboard
| Challenge: | supervised fine-tuning (SFT) data is critical for large multimodal models . current methods suffer from factual errors and hallucinations due to inadequate visual perception . |
| Approach: | They propose a pipeline that integrates vision priors and state-of-the-art LMMs with statistical methods to enhance SFT data quality. |
| Outcome: | The proposed pipeline outperforms existing models in text-rich reasoning tasks while enhancing reasoning efficiency. |
Do Deep Neural Nets Display Human-like Attention in Short Answer Scoring? (2022.naacl-main)
Copied to clipboard
| Challenge: | DL-based graders often lack the ability to explain and justify how a prediction is made, which decreases their trustworthiness and hinders educators from embracing them in practice. |
| Approach: | They conducted a user study to determine whether DL-based graders align with human grader . they also ran a randomized controlled experiment to explore the impact of highlighting important words detected by DL grader. |
| Outcome: | The proposed method enables human graders to identify important words when marking short answer questions. |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for abnormal event detection face two predominant limitations . existing methods rely on specialized small models and are limited by performance bottlenecks . |
| Approach: | They propose a framework that leverages the advanced reasoning capabilities of large language models for abnormal event detection. |
| Outcome: | The proposed framework achieves the highest F1 score and an average improvement of 9.59% in OOD transfer tests. |
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)
Copied to clipboard
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu
| Challenge: | Existing slot filling models memorize inherent patterns of entities and contexts from training data. |
| Approach: | They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution . |
| Outcome: | The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts. |
LLM-Enhanced Query Generation and Retrieval Preservation for Task-Oriented Dialogue (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge retrieval methods for task-oriented dialogues are limited by data scarcity and lack of data to annotate. |
| Approach: | They propose an LLM-enhanced model of query-guided knowledge retrieval for task-oriented dialogue . they propose to select the most relevant knowledge from retrieved top-K records and incorporate them as prompts to guide a generator in response generation. |
| Outcome: | The proposed model outperforms state-of-the-art in three benchmarks on three standard benchmarks. |
Task-wrapped Continual Learning in Task-Oriented Dialogue Systems (2025.findings-naacl)
Copied to clipboard
| Challenge: | Continual learning is vital for task-oriented dialogue systems (ToDs), but its performance is limited by training separate adapters for each task, preventing global knowledge sharing. |
| Approach: | They propose a framework that employs task-wrapped Adapters to learn global and task-specific information through parameter sharing. |
| Outcome: | The proposed framework outperforms AdapterCL in 37 domains while using only 46% of the parameters. |
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are hindered by the rapid growth of key–value (KV) caches. |
| Approach: | They propose a hybrid KV cache compression framework that reduces KV memory by 7.9 and speeds up decoding by 1.52. |
| Outcome: | Experiments on 11 multimodal benchmarks show that HYBRIDKV cuts KV cache memory by 7.9 and speeds up decoding by 1.52. |
Sparse Adapter Fusion for Continual Learning in NLP (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for learning continuously face challenges such as inefficient parameter reuse across tasks and catastrophic forgetting when tasks are dissimilar. |
| Approach: | They propose a Sparse Adapter Fusion Method which dynamically fuses old and new adapters to address these challenges. |
| Outcome: | The proposed method outperforms state-of-the-art methods while utilizing less than 60% of the parameters. |
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)
Copied to clipboard
Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu
| Challenge: | Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves. |
| Approach: | They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop. |
| Outcome: | The proposed framework yields more stable training and higher long-horizon task success across open-world environments. |
Prototype Conditioned Generative Replay for Continual Learning in NLP (2025.naacl-long)
Copied to clipboard
| Challenge: | Generative replay methods that rely on a single task-specific token or prompt often fail to generate pseudo-samples that accurately reflect the true data distribution. |
| Approach: | They propose a Prototype Conditioned Generative Replay method which incorporates task-level statistics into a prototyping process. |
| Outcome: | The proposed method outperforms state-of-the-art (SOTA) methods on two different scenarios. |
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)
Copied to clipboard
Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen
| Challenge: | Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models. |
| Approach: | They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model. |
| Outcome: | The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD. |
CLEAR: Can Language Models Really Understand Causal Graphs? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing language models lack a conceptual framework for understanding causal graphs, but there is still potential for improvement. |
| Approach: | They develop a framework to define causal graph understanding by assessing language models’ behaviors through four practical criteria derived from diverse disciplines. |
| Outcome: | The proposed framework defines three complexity levels and encompasses 20 causal graph-based tasks across 20 different levels. |
On Diversified Preferences of Large Language Model Alignment (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) can be fine tuned with human feedback, but human preferences can be diversified due to annotators’ different tastes, which hinders the effectiveness of LLM alignment methods. |
| Approach: | They propose a calibration error metric to evaluate large language models (LLMs) and a multi-objective reward learning method to enhance the calibration performance of RMs on shared preferences. |
| Outcome: | The proposed model can be adopted as a key calibration error and MORE can achieve superior alignment performance. |
Headword-Oriented Entity Linking: A Special Entity Linking Task with Dataset and Baseline (2020.lrec-1)
Copied to clipboard
| Challenge: | specialized entity linking problem involves linking only headwords of entities to knowledge bases . full product names are rarely written in context, instead abbreviated to shorter, irregular versions . |
| Approach: | They propose a specialized entity linking problem where only the headwords of entities are to be linked to knowledge bases. |
| Outcome: | The proposed model provides a strong benchmark performance on the special task. |
ACECODER: Acing Coder RL via Automated Test-Case Synthesis (2025.acl-long)
Copied to clipboard
| Challenge: | Recent coder models have been driven by supervised fine-tuning, but the potential of reinforcement learning remains unexplored due to the lack of reliable reward data/model in the code domain. |
| Approach: | They propose a pipeline that generates extensive test-case pairs from existing code data and constructs preference pairs based on pass rates over sampled programs. |
| Outcome: | The proposed pipeline generates extensive (question, test-cases) pairs from existing code data and trains them with Bradley-Terry loss. |
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement (2026.acl-long)
Copied to clipboard
Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao, Bokai Ji, Dugang Liu, Xing Tang, Xiuqiang He, Xu Chen
| Challenge: | Recent advances in Large Language Models have demonstrated notable inferential capacities via reinforcement learning (RL) however, “zero-RL” approaches relying on fixed prompt templates introduce substantial sampling inefficiencies for weak LLMs. |
| Approach: | They propose a hierarchical metacognitive RL framework that decomposes zero-accuracy problems into subproblems and prompts the policy to refine answers by referencing previous wrong solutions. |
| Outcome: | The proposed framework improves sample utilization and sample efficiency and accelerates convergence compared to baselines. |
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models (2026.findings-acl)
Copied to clipboard
Lifan Zheng, Xue Yang, Jiawei Chen, Chenyan WU, Jingyuan Zhang, Fanheng Kong, Xinyi Zeng, Xiang Chen, Yu Tian
| Challenge: | Current methods for editing personality traits in large language models can change personalities but reduce performance. |
| Approach: | They propose a novel paradigm for personality editing that locates and edits LLM neurons and enables competitive personality control at inference time. |
| Outcome: | Experiments on LLaMA-3-8B-Instruct and Qwen2.5-7B-instruct show that the proposed approach can improve performance and improve performance. |
Value type: the bridge to a better DST model (2023.findings-acl)
Copied to clipboard
| Challenge: | Value type of the slots can provide lots of useful information for DST tasks. however, it has been ignored in most previous works. |
| Approach: | They propose a new framework for DST task based on slot value type . they propose to extract the type of token from each turn and train a Ner model to extract corresponding type-entity from each conversation according to the token. |
| Outcome: | The proposed framework is effective on two multi-domain task-oriented conversation datasets. |
From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)
Copied to clipboard
Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu
| Challenge: | Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context. |
| Approach: | They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations. |
| Outcome: | The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks. |
MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)
Copied to clipboard
Xuan Lu, Sifan Liu, Bochao Yin, Yongqi Li, Xinghao Chen, Hui Su, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen
| Challenge: | MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Approach: | They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Outcome: | The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains. |
Emergence of Abstract State Representations in Embodied Sequence Modeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Sequence modeling is a simple yet versatile task that can be applied to more complex decision-making domains. |
| Approach: | They build a sequence modeling Transformer which takes a language instruction, actions, and environmental observations as inputs and then trains a model to reconstruct environmental layouts. |
| Outcome: | The proposed model can reconstruct environmental layouts from the inputs of the model and language instructions play a role in the reconstruction accuracy. |
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning (2026.findings-acl)
Copied to clipboard
Xukai Wang, Xuanbo Liu, Mingrui Chen, Haitian Zhong, Xuanlin Yang, Bohan Zeng, Jinbo Hu, Hao Liang, Junbo Niu, Xuchen Li, Ruitao Wu, Ruichuan An, Yang Shi, Liu Liu, Qiang Liu, Zhouchen Lin, Xu-Yao Zhang, Wentao Zhang, Bin Dong
| Challenge: | Existing benchmarks designed to evaluate the reasoning capabilities of large models are limited in scope and lack flexibility to adapt difficulty according to evolving reasoning capacities of models. |
| Approach: | They propose a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
| Outcome: | The proposed benchmark incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. |
UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | a new benchmark summarization model is being developed to train few-shot summarizers . a large number of summarizing tasks are required to perform well in heterogeneous datasets. |
| Approach: | They propose a few-shot summarization model pre-trained with multiple summarizing tasks . they propose 'uniSumm' to be prefix-tuned to excel at any few-shot summarisation task . |
| Outcome: | The proposed model outperforms baseline models under automatic and human evaluations and achieves comparable results in human evaluation. |
GOBench: Stage-Wise Diagnostics and the Visual Paradox in Multimodal Graph Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks fail to represent multimodal problem specifications, score outcomes only and cannot localize where failures occur along the modeling pipeline. |
| Approach: | They propose a Graph Optimization benchmark that aligns multiple modalities with solver-derived oracles and a diagnostic protocol that evaluates intermediate artifacts as well as end results. |
| Outcome: | Graph Optimization benchmark (GOBench) evaluates intermediate artifacts as well as end results . vision reliably increases inference cost, while reliability impact is regime-dependent . current benchmarks fail to represent multimodal problem specifications, fail to localize failures . |
MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing low-bit quantization methods often exhibit severe performance degradation on complex reasoning tasks. |
| Approach: | They propose a plug-and-play method that uses a key channel's intrinsic quantization difficulty and relevance to the query to identify and preserve critical key channels that need higher precision. |
| Outcome: | Experiments on complex reasoning datasets show that the proposed method outperforms low-bit methods at a substantially reduced memory footprint. |
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems (2024.emnlp-industry)
Copied to clipboard
Yilun Kong, Jingqing Ruan, YiHong Chen, Bin Zhang, Tianpeng Bao, Shi Shiwei, Du Qing, Xiaoru Hu, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao, Xueqian Wang
| Challenge: | Large language models have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools. |
| Approach: | They propose a framework to enhance the task planning and tool usage abilities of LLMs in industrial systems. |
| Outcome: | The proposed framework enhances the task planning and tool usage abilities of LLM-based agents in industrial systems. |
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have underscored their exceptional reasoning prowess with natural language understanding across a broad spectrum of tasks. |
| Approach: | They examine whether Large Language Models actively recall or retrieve their internal repositories of factual knowledge when faced with reasoning tasks. |
| Outcome: | The proposed model improves reasoning performance while suppressing it leads to notable degradation. |
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing routing strategies rely on local token probabilities or post-hoc verification, introducing significant inference overhead. |
| Approach: | They propose a step-wise collaboration framework that generates only the first token of each reasoning step and routes it to a larger model only when initial token entropy exceeds a threshold. |
| Outcome: | The proposed approach reduces inference latency while preserving accuracy. |
MedDialog: Large-scale Medical Dialogue Datasets (2020.emnlp-main)
Copied to clipboard
Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, Pengtao Xie
| Challenge: | telemedicine is a medical practice that provides patient care remotely using video conferencing tools. |
| Approach: | They build large-scale medical dialogue datasets to facilitate research . they pretrain several models on the Chinese MedDialog dataset and compare their performance . |
| Outcome: | The proposed datasets show that models trained on MedDialog can generate doctor-like medical dialogues. |
MACSum: Controllable Summarization with Mixed Attributes (2023.tacl-1)
Copied to clipboard
Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang
| Challenge: | Existing work on controllable summarization with mixed attributes lacks designated annotations. |
| Approach: | They propose a human-annotated summarization benchmark for controllable summarizing with mixed attributes based on news and dialogue sources . |
| Outcome: | The proposed dataset contains human-annotated summarization datasets with mixed attributes . hard prompt models yield the best performance on most metrics and human evaluations . mixed-attribute control is still challenging for summarizing tasks . |
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis (2025.emnlp-main)
Copied to clipboard
Jianwei Wang, Chengming Shi, Junyao Yang, Haoran Li, Qianli Ma, Huiping Zhuang, Cen Chen, Ziqian Zeng
| Challenge: | Existing solutions to fine-tune large language models for domain-specific tasks are ineffective in addressing privacy concerns. |
| Approach: | They propose a privacy-preserving framework that fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. |
| Outcome: | The proposed framework fine-tunes a reward proxy model and uses reward signals to guide the synthetic data generation. |
Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang
| Challenge: | Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. |
| Approach: | They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals. |
| Outcome: | The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. |
EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are a promising tool for traditional education but lack authentic and domain-specific benchmarks to accurately interpret student handwritten solutions. |
| Approach: | They propose to use MLLMs to interpret unconstrained STEM student handwritten solutions with intertwined mathematical formulas, diagrams, and textual reasoning to bridge this gap. |
| Outcome: | The proposed model can detect and rectify recognition errors with minimal human intervention on unseen student solutions. |
LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)
Copied to clipboard
Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng
| Challenge: | E-commerce search relevance is a critical component of retrieval systems. |
| Approach: | They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies. |
| Outcome: | The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain. |
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions . |
| Approach: | They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts. |
| Outcome: | The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts. |
Preserving Language Capabilities in Vision-Language Models via Representation Regulation (2026.findings-acl)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) provide a unified framework to process both text-only and vision-language tasks. |
| Approach: | They propose a method to reduce the distance between visual and textual representations by introducing a Representation Distribution Difference (RDD) loss. |
| Outcome: | Empirical evidence shows that finetuning VLMs on vision-language data has degraded language capabilities. |
Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)
Copied to clipboard
| Challenge: | Entity matching (EM) is a critical step in entity resolution (ER). |
| Approach: | They propose a method that incorporates record interactions from different perspectives. |
| Outcome: | The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness. |
Jailbreaking? One Step Is Enough! (2025.acl-long)
Copied to clipboard
Weixiong Zheng, Peijian Zeng, YiWei Li, Hongyan Wu, Nankai Lin, Junhao Chen, Aimin Yang, Yongmei Zhou
| Challenge: | Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. |
| Approach: | They propose a Reverse Embedded Defense Attack mechanism that disguises the attack intention as the "defense" intention against harmful content. |
| Outcome: | The proposed method outperforms existing methods on open-source and closed-source models and enables successful jailbreak in one iteration. |
BMCook: A Task-agnostic Compression Toolkit for Big Models (2022.emnlp-demos)
Copied to clipboard
Zhengyan Zhang, Baitao Gong, Yingfa Chen, Xu Han, Guoyang Zeng, Weilin Zhao, Yanxu Chen, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing efforts to compress medium-sized models for specific tasks have limited results. |
| Approach: | They propose a task-agnostic compression toolkit for big models that implements quantization, pruning, distillation and MoEfication methods. |
| Outcome: | The proposed tool improves performance on a model with 3 billion parameters by 12x . it also outperforms the original model on three typical NLP benchmarks. |
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs (2026.acl-long)
Copied to clipboard
Wenlong Deng, Qi Zeng, Jiaming Zhang, Minghui Chen, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li
| Challenge: | Existing methods for data valuation rely on gradient computations, making them prohibitive for billion-parameter models. |
| Approach: | They propose a forward-only data valuation framework that enables efficient batch-scalable value estimation while maintaining effectiveness. |
| Outcome: | The proposed framework matches or outperforms gradient-based baselines in detecting influential data and mislabeled data while achieving significant efficiency improvements. |
ACEBench: A Comprehensive Evaluation of LLM Tool Usage (2025.findings-emnlp)
Copied to clipboard
Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Yuefeng Huang, Xiangcheng Liu, Wang Xinzhi, Wu Liu
| Challenge: | Existing benchmarks for evaluating LLMs’ tool usage face several limitations: limited evaluation scenarios, lacking assessments in real multi-turn dialogue contexts; narrow evaluation dimensions, with insufficient detailed assessments of how LLM use tools; and reliance on LLM or real API executions for evaluation, which introduces significant overhead. |
| Approach: | ACEBench is a benchmark for evaluating tool usage in Large Language Models . it categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
| Outcome: | ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. |
Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data. |
| Approach: | They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages. |
| Outcome: | The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks. |
Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton
| Challenge: | Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options. |
| Approach: | They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations . |
| Outcome: | The proposed model outperforms human experts in multiple medical tasks. |
When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning (2025.findings-emnlp)
Copied to clipboard
Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai
| Challenge: | Large reasoning models (LRMs) incur excessive computational overhead due to redundant reasoning, especially on simple tasks. |
| Approach: | They propose an Adaptive Self-Recovery Reasoning framework that suppresses unnecessary reasoning and enables implicit recovery. |
| Outcome: | The proposed framework suppresses unnecessary reasoning and enables implicit recovery. |
Reinforcement Learning–Guided Adaptive Tuning for Out-of-Distribution Harmful Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for testing harmful information on social media rely on fixed parameters that fail to handle substantial semantic discrepancies . RLAT can be used to adapt to semantic variations while preventing overfitting from continuous tuning. |
| Approach: | They propose a reinforcement learning-guided adaptive tuning method for harmful text detection that optimizes consistency loss and applies word-level attention constraints to reduce over-reliance on local words. |
| Outcome: | The proposed method outperforms state-of-the-art models in cross-platform and cross-temporal scenarios across multiple public datasets. |
Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that large language models can perform precise text editing tasks. |
| Approach: | InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models . |
| Outcome: | The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits. |
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction (2026.findings-acl)
Copied to clipboard
Zichun Guo, Yuling Shi, Wenhao Zeng, Chao Hu, Haotian Lin, Terry Yue Zhuo, Jiawei Chen, Xiaodong Gu, Wenping Ma
| Challenge: | Empirical evaluations on state-of-the-art MLLMs reveal a significant performance gap . ML models lack the fine-grained cross-modal reasoning required to bridge visual discontinuities. |
| Approach: | They propose a benchmark that renders fragmented documents directly from Markdown to facilitate evaluation of VRDU tasks. |
| Outcome: | The proposed benchmark renders fragmented documents directly from Markdown. |
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches allocate an equal number of rollouts to all questions during the RL process, which is inefficient. |
| Approach: | They propose a mechanism for dynamically allocating rollout budgets based on the difficulty of the problems, enabling more efficient RL training. |
| Outcome: | The proposed model improves response precision while preserving exploratory ability to uncover potential correct pathways. |
Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in AM models overlook the integration of supplementary discourse structure information, resulting in suboptimal outcomes. |
| Approach: | They propose a framework which generates discourse structure-aware prefixes for each layer of the generation model. |
| Outcome: | The proposed framework achieves state-of-the-art performance on two AM benchmarks. |
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)
Copied to clipboard
Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
| Challenge: | Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. |
| Approach: | They propose a comprehensive benchmark covering 29 languages, built on an English benchmark. |
| Outcome: | The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark. |
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generalized intent discovery lack pseudo label disambiguation and representation learning. |
| Approach: | They propose a prototype learning framework to decouple pseudo label disambiguation and representation learning. |
| Outcome: | The proposed method can decouple pseudo label disambiguation and representation learning. |
Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to lexically constrained neural machine translation suffer from high latency. |
| Approach: | They propose a plug-in algorithm for non-autoregressive translation for this problem . they propose ACT to familiarize the model with the source-side context of constraints . |
| Outcome: | The proposed model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints. |
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)
Copied to clipboard
Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li
| Challenge: | Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge. |
| Approach: | They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage. |
| Outcome: | The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold. |
KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment (2023.acl-long)
Copied to clipboard
| Challenge: | Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning . MU can be used to forget specific training instances as if they have never existed . |
| Approach: | They propose a general unlearning framework called KGA to induce forgetfulness . they propose several unlearning evaluation metrics with pertinence . |
| Outcome: | The proposed framework improves on large-scale datasets and provides insight into unlearning for NLP tasks. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules. |
| Approach: | They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection. |
| Outcome: | The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark. |
DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router (2026.findings-eacl)
Copied to clipboard
Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng
| Challenge: | Existing RAG methods lack fine-grained control over query and source sides, resulting in noisy retrieval and shallow reasoning. |
| Approach: | They propose an agentic RAG framework that integrates information sieving via LLM-as-a-knowledge-router. |
| Outcome: | Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional approaches. |
On the Generation of Medical Dialogs for COVID-19 (2021.acl-short)
Copied to clipboard
Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie
| Challenge: | under the pandemic of COVID-19, people experiencing COVI D19-related symptoms have a pressing need to consult doctors. |
| Approach: | They develop a medical dialog system that can provide COVID19-related consultations . they use two dialog datasets containing conversations between doctors and patients . |
| Outcome: | The proposed system can provide COVID19-related consultations, but is too small compared with general-domain dialog datasets. |
FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning (2026.findings-acl)
Copied to clipboard
Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng
| Challenge: | Low-rank adaptation methods for large language models have limitations in preserving world knowledge and limiting updates to preserve world knowledge. |
| Approach: | They propose a Fisher-optimized adaptive low Rank and Singular-VectorSelection framework for knowledge-preserving fine-tuning that allows efficient and task-sensitive updates. |
| Outcome: | The proposed framework outperforms existing methods for knowledge-preserving fine-tuning. |
DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)
Copied to clipboard
Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng
| Challenge: | Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk. |
| Approach: | They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression. |
| Outcome: | The proposed method surpasses state-of-the-art methods on long context tasks. |
LCQMC:A Large-scale Chinese Question Matching Corpus (C18-1)
Copied to clipboard
| Challenge: | Existing methods for question answering system lack large-scale question matching corpora . lack of large-sized question matching results in problem solving . |
| Approach: | They propose a large-scale Chinese question matching corpus which is released to the public . they use a search engine to collect large-sized question pairs related to high-frequency words . |
| Outcome: | The proposed corpus is more general than paraphrase corpus as it focuses on intent matching rather than paraphrasing. |
Efficient Hyperparameter Optimization for LLM Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hyperparameter optimization methods are inefficient in reinforcement learning due to model scale and resource-intensive training cycles. |
| Approach: | They propose a hyperparameter optimization method that adapts both model size and training budget as fidelity. |
| Outcome: | The proposed method significantly improves the computational efficiency of each trial (up to 14.9) over existing HPO methods. |
Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively. |
| Approach: | They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions. |
| Outcome: | The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions. |
AdaPrompt: Adaptive Model Training for Prompt-based NLP (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Prompt-based learning can tackle zero-shot and few-shot NLP tasks . authors propose a method that makes use of pre-trained language models . |
| Approach: | They propose to map NLP tasks into natural language prompts, which are then filled by pre-trained language models. |
| Outcome: | The proposed method outperforms standard prompt-based methods in few-shot settings. |
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings (2025.acl-long)
Copied to clipboard
| Challenge: | Existing low-resource security alignment methods struggle with the security risks posed by additional modalities. |
| Approach: | They propose to use multimodal datasets to enhance safety alignment but it is costly to construct these datasets. |
| Outcome: | Experiments on image, video, and audio-based MLLMs show that the proposed method can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds. |
Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies suggest that large language models can transfer skills learned in one language to others, but internal mechanisms behind this ability remain unclear. |
| Approach: | They find that LLMs map semantically identical inputs from different languages into a common semantic latent space that allows for consistent processing across languages. |
| Outcome: | The findings highlight the structural evolution of multilingual models during training and scaling up. |
Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation (2026.acl-long)
Copied to clipboard
Jiaju Chen, Yuxuan Lu, Xiaojie Wang, Huimin Zeng, Jing Huang, Jiri Gesi, Ying Xu, Bingsheng Yao, Dakuo Wang
| Challenge: | Existing "LLM-as-a-judge" evaluation frameworks are limited by persona descriptions and are not generalizable to other tasks. |
| Approach: | They propose a framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents and instantiate LLM agents with the persona. |
| Outcome: | The proposed framework can believably simulate human evaluators . it extracts stakeholders' diverse perspectives from the provided research papers and constructs personas for the agents . |
TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models often underperform due to complex queries, noisy data, and limited numerical capabilities. |
| Approach: | They propose a framework that integrates seamlessly with mainstream LLMs to improve tabular reasoning. |
| Outcome: | The proposed framework outperforms existing methods in state-of-the-art analysis. |
Automatic Instruction Evolving for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Evol-Instruct is an end-to-end framework that evolves instruction datasets without human effort. |
| Approach: | They propose an end-to-end framework that evolves instruction datasets without human effort by analyzing and analyzing evolutionary strategies for the given instruction data. |
| Outcome: | The proposed method outperforms human-designed methods on various benchmarks including MT-Bench, AlpacaEval, GSM8K, and HumanEval. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards (2026.acl-industry)
Copied to clipboard
| Challenge: | a large language model (LLM) is used as a business development agent for persuasive price negotiation in online travel agencies. |
| Approach: | They propose a reward-enhancing policy optimization method that integrates three complementary reward sources-a preference-trained reward model and an LLM-as-a-judge. |
| Outcome: | The proposed method improves average dialogue rating to 4.63 (+0.33 over GRPO) and raises share of conversations with at least one excellent response to 66.67% (+23.34 pp over grepo). |
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive summarization models often produce inconsistent statements or false facts. |
| Approach: | They propose an efficient weak-supervised adversarial data augmentation approach to generate factual consistency datasets by backpropagating gradients on token embeddings. |
| Outcome: | The proposed model can make interpretable factual errors tracing on public datasets and is cost-effective. |
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs . |
| Approach: | They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations . |
| Outcome: | The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation . |
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. |
EFSA: Towards Event-Level Financial Sentiment Analysis (2024.acl-long)
Copied to clipboard
| Challenge: | a large-scale Chinese dataset contains 12,160 news articles and 13,725 quintuples . a four-hop Chain-of-Thought LLM-based approach is devised for this task . |
| Approach: | They propose to extend financial sentiment analysis to event-level since events usually serve as the subject of the sentiment in financial text. |
| Outcome: | The proposed method can reach the current state-of-the-art on a large-scale Chinese dataset. |
Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)
Copied to clipboard
Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings. |
| Approach: | They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings. |
| Outcome: | The proposed method consistently improves retrieval performance across multiple datasets. |
Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect harmful outputs from prefill-level lacks utilization of the model’s decoding outputs, leading to relatively lower effectiveness and robustness. |
| Approach: | They propose a robust decoding mechanism that corrects harmful queries directly rather than rejecting them outright. |
| Outcome: | The proposed model improves model security without compromising reasoning speed. |
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models (2025.acl-long)
Copied to clipboard
Tao Zhang, Ziqian Zeng, YuxiangXiao YuxiangXiao, Huiping Zhuang, Cen Chen, James R. Foulds, Shimei Pan
| Challenge: | Large Language Models (LLMs) generate content that exhibits gender biases, raising ethical concerns. |
| Approach: | They propose to use a dataset to identify gender biases in Large Language Models (LLMs) this dataset is a "chosen" and "rejected" LLM alignment is an effective approach to mitigate gender bias. |
| Outcome: | The proposed dataset shows that it reduces gender bias and improves quality. |
LANTERN in the Event Stream: Training-Free Temporal Knowledge Graph Forecasting by Balancing Inertia and Shifts (2026.findings-acl)
Copied to clipboard
| Challenge: | Temporal knowledge graph forecasting (TKGF) uses long-window strengthscores and short-windowed novelty scores to predict missing entities in future queries. |
| Approach: | They propose a training-freeprompting framework that uses two perspectives of history to predict missing entities in future queries. |
| Outcome: | The proposed framework outperforms the state-of-the-art baselineAnRe framework in ICEWS14, ICEW05-15, and GDELT. |
MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)
Copied to clipboard
Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang
| Challenge: | Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases. |
| Approach: | They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process. |
| Outcome: | The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations. |
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jichao Wang, Liuyang Bian, Yufeng Zhou, Han Xiao, Yue Pan, Guozhi Wang, Hao Wang, Zhaoxiong Wang, Yafei Wen, Xiaoxin Chen, Shuai Ren, Lingfang Zeng
| Challenge: | Existing approaches to training GUI agents on dynamic tasks are based on SFT or Behavior Cloning. |
| Approach: | They propose a framework that integrates global trajectory insights directly into offline learning . they reconstruct diverse rollout candidates from static data and detect first failure point . |
| Outcome: | The proposed framework improves long-horizon task completion rates and robustness compared to baselines. |
Latent-Condensed Transformer for Efficient Long Context Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. |
| Approach: | They propose a Latent-Condensed Attention mechanism that performs structured context condensation directly within MLA's latent space. |
| Outcome: | The proposed approach reduces KV cache size and attention cost without adding parameters. |
SDD: Self-Degraded Defense against Malicious Fine-tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Open-source Large Language Models (LLMs) employ safety alignment methods to resist harmful instructions, but malicious fine-tuning can easily bypass these safeguards. |
| Approach: | They propose a framework to prevent malicious fine-tuning of large language models on harmful data by using alignment methods that encourage them to produce irrelevant responses to harmful prompts. |
| Outcome: | The proposed framework reduces the general capability of the LLM when malicious fine-tuning fails, rendering it incapable of following harmful instructions. |
KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)
Copied to clipboard
Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu
| Challenge: | Recent advances in pre-trained language models have made it possible to generate human-like text. |
| Approach: | They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached. |
| Outcome: | The proposed game lacks incentives and relies on players to explore on their own. |
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models (2023.acl-short)
Copied to clipboard
Jianyi Zhang, Aashiq Muhamed, Aditya Anantharaman, Guoyin Wang, Changyou Chen, Kai Zhong, Qingjun Cui, Yi Xu, Belinda Zeng, Trishul Chilimbi, Yiran Chen
| Challenge: | Knowledge distillation (KD) is an effective compression technique to derive a smaller student model from a larger teacher model by transferring the knowledge embedded in the teacher's network. |
| Approach: | They propose a framework and loss function that preserves the semantic similarities of teacher and student training examples to enable the student to retrieve from the knowledge base effectively. |
| Outcome: | The proposed framework preserves the semantic similarities of teacher and student training examples to achieve state-of-the-art performance on the GLUE benchmark. |