Papers by Fan Zhang
Soundwave: Less is More for Speech-Text Alignment in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing end-to-end speech large language models rely on large-scale annotated data for training, while data-efficient training has not been discussed in depth. |
| Approach: | They propose a training strategy and a novel architecture to address representation space gap and sequence length inconsistency in speech and text. |
| Outcome: | The proposed model outperforms other advanced speech LLMs in speech translation and AIR-Bench speech tasks with only a fraction of the training data. |
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaboration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. |
| Approach: | They propose a knowledge-aware adaptive collaboration framework to enhance cognitive synergy in multi-agent systems with large language models. |
| Outcome: | The proposed framework improves synergy between agents and language models by enabling agents to dynamically perceive their collaborators’ cognitive states. |
Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion Large Language Models (dLLMs) offer parallel decoding and bidirectional context modeling . aligning dLLms with reinforcement learning (RL) remains a challenge . |
| Approach: | They propose a variational framework that reformulates RL for dLLMs as a distribution matching problem. |
| Outcome: | The proposed framework reformulates RL for dLLMs as a distribution matching problem. |
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation (2025.findings-emnlp)
Copied to clipboard
Yuanhao Ding, Esteban Garces Arias, Meimingwei Li, Julian Rodemann, Matthias Aßenmacher, Danlu Chen, Gaojuan Fan, Christian Heumann, Chongsheng Zhang
| Challenge: | GUARD is a self-adaptive decoding method that balances coherence with diversity in open-ended text generation. |
| Approach: | They propose a self-adaptive decoding method that balances coherence and diversity . they combine global entropy estimates with local entropic deviations to integrate uncertainty . |
| Outcome: | GUARD achieves a good balance between diversity and coherence while exhibiting significant improvements in generation speed. |
NPHardEval: Dynamic Benchmark on Reasoning Ability of Large Language Models via Complexity Classes (2024.acl-long)
Copied to clipboard
| Challenge: | Complex reasoning ability is one of the most important features of Large Language Models. |
| Approach: | They propose a new benchmark that measures the reasoning ability of Large Language Models . it contains 900 algorithmic questions belonging to the NP-Hard complexity class . |
| Outcome: | The proposed benchmark contains 900 questions belonging to the NP-Hard complexity class and is updated on a monthly basis. |
Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (2025.findings-acl)
Copied to clipboard
Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Haochen Xue, Zelong Li, Jindong Wang, Yongfeng Zhang
| Challenge: | Using large language models, large language model models can be used to evaluate reasoning abilities in context-rich scenarios. |
| Approach: | They construct datasets for both propositional logic and abductive logic reasoning with four difficulty levels across 12 distinct domains based on Wikipedia categorization and those with purely abstract variables. |
| Outcome: | The proposed model can be used to benchmark LLMs in real-world scenarios, but not in context-rich scenarios. |
FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing research focuses on benchmarking LLMs in single-turn dialogues, neglecting the nuanced nature of human feedback within real-world usage scenarios. |
| Approach: | They propose a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese. |
| Outcome: | The proposed benchmarks show that human feedback can significantly impact LLMs’ responsiveness in real-world usage scenarios. |
DocAssistant: Integrating Key-region Reading and Step-wise Reasoning for Robust Document Visual Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing document understanding models focus on key information and generate answers straightforwardly . existing models ignore evidence from source documents and lack interpretability . |
| Approach: | They propose a visual encoder that fuses text into visual encoded visual encodes . they use multimodal large language models as data generators and checkers to generate step-wise question-and-answer pairs for document images. |
| Outcome: | The proposed model can answer step-wise questions without compromising the performance of the original model. |
FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)
Copied to clipboard
Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev
| Challenge: | Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity. |
| Approach: | They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models. |
| Outcome: | The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models. |
LANID: LLM-assisted New Intent Discovery (2024.lrec-main)
Copied to clipboard
| Challenge: | Data annotation is expensive in Task-Oriented Dialogue systems. |
| Approach: | They propose a framework that leverages Large Language Models' zero-shot capability to enhance the performance of a smaller text encoder on the NID task. |
| Outcome: | The proposed framework surpasses all strong baselines in both unsupervised and semi-supervised settings. |
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that current models are prone to generating unfaithful summaries . a proposed method is effective in identifying and correcting extrinsic hallucinations . |
| Approach: | They propose a model-agnostic post-processing technique to correct unfaithful summaries . they generate alternative candidates where names and quantities are replaced with compatible ones . |
| Outcome: | The proposed method corrects extrinsic hallucinations in unfaithful summaries. |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion (2023.acl-long)
Copied to clipboard
Wanrong He, Haoyu Dong, Yihuai Gao, Zhichao Fan, Xingzhuo Guo, Zhitao Hou, Xiao Lv, Ran Jia, Shi Han, Dongmei Zhang
| Challenge: | HermEs is a spreadsheet formula prediction language that is difficult for Excel users without programming experience to master. |
| Approach: | They propose a hierarchical approach to formula prediction via HiEraRchical forMulet ExpanSion . they propose generating formulas in a fixed order using hierarchically generated formulas . |
| Outcome: | The proposed approach improves formula prediction accuracy by guaranteeing correct grammar and streamlining token-level decoding with high-level Formulet. |
Harmful Factuality: LLMs Correcting What They Shouldn’t (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are trained for factual accuracy, but can conflict with the critical demand for source fidelity. |
| Approach: | They propose a reproducible framework to elicit and measure HFH using controlled entity-level perturbations and strategic entity selection. |
| Outcome: | The proposed framework reduces HFH rates by 50% across summarization, rephrasing, and QA tasks. |
TARo: Token-level Adaptive Routing for LLM Test-time Alignment (2026.findings-acl)
Copied to clipboard
Arushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang, Dipesh Tamboli, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang
| Challenge: | Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. |
| Approach: | They propose to use token-level Adaptive Routing to steer frozen LLMs toward structured reasoning entirely at inference time. |
| Outcome: | Extensive experiments show that TARo significantly improves reasoning performance by up to +22.4% over base model and +8.4% . |
Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025.acl-long)
Copied to clipboard
| Challenge: | Evidence retrieval is used to enhance Large Language Models (LLMs) but in real-world applications, it often returns lengthy documents with redundant or irrelevant content, confusing downstream readers. |
| Approach: | They propose a framework that reformulates evidence retrieval as a dynamic tree expansion process. |
| Outcome: | The proposed framework outperforms existing methods on five datasets. |
1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been recognized for their impressive capabilities in natural language processing (NLP). |
| Approach: | They propose a method to enhance the multilingual performance of Large Language Models by aggregating knowledge from diverse languages. |
| Outcome: | The proposed method reduces the performance disparity across languages and offers valuable insights for further exploration. |
Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)
Copied to clipboard
Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang
| Challenge: | Recent studies have focused on a single pass of lyrics generation with little human intervention. |
| Approach: | They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes. |
| Outcome: | The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly. |
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on retrieval-augmented generation (RAG) rarely address the issue of predictive uncertainty, i.e., how likely it is that a RAG model’s prediction is incorrect. |
| Approach: | They propose a framework that induces RAG models to alter latent factors and analyzes the effect on their answers. |
| Outcome: | The proposed framework identifies two critical factors affecting RAG models' confidence in their answers and analyzes the effect on their answers. |
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)
Copied to clipboard
Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge . |
| Approach: | They propose a framework that enables dynamic and continuous alignment of large language models with human preferences. |
| Outcome: | The proposed framework improves safety and accuracy of a 7B model with human annotations. |
Interpreting Twitter User Geolocation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results. |
| Approach: | They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations. |
| Outcome: | The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes. |
MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing benchmarks in the generic domain have evaluated long-context capabilities for LLMs. |
| Approach: | They propose a medical long-context benchmark with seven length levels ranging from 4K to 200K tokens. |
| Outcome: | The proposed benchmarks have seven length levels ranging from 4K to 200K tokens. |
DEMO: A Statistical Perspective for Efficient Image-Text Matching (2024.naacl-long)
Copied to clipboard
| Challenge: | Image-text matching is a problem that seeks to connect vision and language through semantic understanding. |
| Approach: | They propose a deep unsupervised hashing-based approach for image-text matching . they characterize each image using multiple augmented views, which are considered as samples . |
| Outcome: | The proposed approach achieves superior performance on image-text matching datasets compared with state-of-the-art methods. |
C2KD: Cross-layer and Cross-head Knowledge Distillation for Small Language Model-based Recommendation (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) show promise but their size and high inference costs limit deployment on resource-constrained devices. |
| Approach: | They propose a framework to transfer task-relevant knowledge from two complementary dimensions to Large Language Models (LLMs) Large Language models (LLMS) have demonstrated great potential in sequential recommendation tasks . |
| Outcome: | Extensive experiments across diverse model families show that the proposed framework achieves competitive performance compared to LLMs. |
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)
Copied to clipboard
Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song
| Challenge: | Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning. |
| Approach: | They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized. |
| Outcome: | The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized . |
HiSVD: Principled Low-Rank Approximation of LLMs via Hierarchical Modeling of Information Capacity and Spectral Structure (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating layer importance ignore the fine-grained influence of spectral distribution shape. |
| Approach: | They propose a hierarchical rank allocation framework with two stages to address this gap . they propose SVD-based lowrank approximation that exploits spectral heterogeneity . |
| Outcome: | Experiments show that HiSVD outperforms state-of-the-art methods on LLMs . |
MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment (2025.acl-long)
Copied to clipboard
| Challenge: | Existing personalized product search methods assume that users’ query fully captures their real motivation, but in practice, user's queries do not always articulate the requirements. |
| Approach: | They propose a Motivation-Aware Personalized Search method that embeds queries and consultations into a unified semantic space via LLMs and utilizes a Mixture of Attention Experts (MoAE) to prioritize critical semantics. |
| Outcome: | Extensive experiments on real and synthetic data show that the proposed method outperforms existing methods in retrieval and ranking tasks. |
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)
Copied to clipboard
Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang
| Challenge: | Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers. |
| Approach: | They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification. |
| Outcome: | The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification. |
DisComp: A Two-Stage Prompt Optimization Framework Combining Task-Agnostic and Task-Aware Compression (2025.findings-naacl)
Copied to clipboard
| Challenge: | Extended prompts can lead to substantial computational overhead and increased hardware demands, limiting the scalability and efficiency of large language models. |
| Approach: | They propose a two-stage prompt compression framework that combines task-agnostic and task-based strategies to efficiently compress prompt length without compromising performance. |
| Outcome: | The proposed framework outperforms task-agnostic and task-specific compression methods on three benchmark datasets and is up to 6.56 faster at inference compared to the best token-level compression method. |
Dynamic Energy-Based Contrastive Learning with Multi-Stage Knowledge Verification for Event Causality Identification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for event causal identification rely on rule-based or random sampling strategies, which introduce spurious causal positives. |
| Approach: | They propose an ECI method enhanced by Dynamic Energy-based Contrastive Learning with multi-stage knowledge verification which generates high-quality contrastive samples and effectively suppresses spurious causal disturbances. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two benchmarks. |
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models perform well in offline machine translation when the complete source sentence is provided . however, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation is required . |
| Approach: | They propose a new paradigm that includes constructing supervised fine-tuning data for simultaneous machine translation (SiMT) to achieve SiMT, source and target tokens are rearranged into interleaved sequences, separated by special tokens according to varying latency requirements. |
| Outcome: | The proposed approach achieves state-of-the-art performance across various SiMT benchmarks and evaluation metrics while maintaining efficient auto-regressive decoding. |
SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on general utility metrics, overlooking the preservation of semantically related concepts. |
| Approach: | They propose a method that introduces self-generated proximal visual tokens to prevent forgetting vulnerability. |
| Outcome: | The proposed framework outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
On Fake News Detection with LLM Enhanced Semantics Mining (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting fake news use only news embeddings to capture the lexical semantics between tokens. |
| Approach: | They propose a topic-based model with prompts to extract news embeddings from LLMs and a generalized page-rank model to extract local and global semantics. |
| Outcome: | The proposed model shows superior performance on five benchmark datasets over seven baseline methods. |
Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | a lack of knowledge breadth and task depth can hinder curriculum learning in domains such as medicine and finance. |
| Approach: | They propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension. |
| Outcome: | The proposed framework improves accuracy on medical evaluations by 2.49% and on financial evaluations 1.2% compared with the second-best method. |
iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)
Copied to clipboard
Jiaze Li, Yaya Shi, Zongyang Ma, Haoran Xu, Yandong.bai Yandong.bai, Huihui Xiao, Ruiwen Kang, Fan Yang, Tingting Gao, Di Zhang
| Challenge: | Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks. |
| Approach: | They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency. |
| Outcome: | The proposed model excels in video temporal understanding and general video understanding. |
Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models (2025.findings-acl)
Copied to clipboard
Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, QingqingLong QingqingLong, Yefeng Zheng, Xian Wu
| Challenge: | Hallucination is a critical challenge for large language models and large vision-language models (LVLMs) however, dedicated research on medical hallucinations remains unexplored. |
| Approach: | They provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes. |
| Outcome: | The proposed models have demonstrated impressive performance on a variety of medical benchmarks. |
DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)
Copied to clipboard
Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Wei Bi, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai
| Challenge: | Large Language Models (LLMs) are evolving towards autonomous agents . retrieval capabilities are well-benchmarked, but post-retrieval synthesis is under-evaluated due to open-ended writing. |
| Approach: | They propose a benchmark to evaluate information consolidation capabilities using survey papers as gold standards. |
| Outcome: | The proposed benchmark analyzes the post-retrieval synthesis stage of large language models . it leverages high-quality survey papers as gold standards and reverse-engineers research requests . the proposed benchmark outperforms single-turn generation and reduces hallucinations . |
VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens. |
| Approach: | They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method. |
| Outcome: | The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs. |
RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning (2025.emnlp-main)
Copied to clipboard
Yu Wang, Shiwan Zhao, Zhihu Wang, Ming Fan, Xicheng Zhang, Yubo Zhang, Zhengfan Wang, Heyuan Huang, Ting Liu
| Challenge: | Existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning. |
| Approach: | They introduce a module extension that integrates application-aware reasoning into the RAG pipeline. |
| Outcome: | Experiments show that RAG+ outperforms standard RAG variants and achieves gains of 3–5% in complex scenarios. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding (2021.acl-long)
Copied to clipboard
Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai
| Challenge: | Experimental results show that Synchronous Semantic Decoding (SSD) can achieve state-of-the-art unsupervised semantic parsing performance on multiple datasets. |
| Approach: | They propose an unsupervised method which solves the semantic gap and the structure gap by leveraging paraphrasing and grammar-constrained decoding. |
| Outcome: | The proposed method can solve the semantic gap and structure gap on multiple datasets. |
Sentiment-Aware Word and Sentence Level Pre-training for Sentiment Analysis (2022.emnlp-main)
Copied to clipboard
Shuai Fan, Chen Lin, Haonan Li, Zhenghao Lin, Jinsong Su, Hang Zhang, Yeyun Gong, JIan Guo, Nan Duan
| Challenge: | Existing pre-trained language representation models (PLMs) capture sentiment information from word-level while under-considering sentence-level information. |
| Approach: | They propose a Sentiment-aware pre-trained language model with combined Word-level and Sentence-level Pre-training tasks that enhance the PLM’s knowledge about sentiment words. |
| Outcome: | The proposed model achieves state-of-the-art on various sentence-level and aspect-level sentiment classification benchmarks. |
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding (2026.acl-long)
Copied to clipboard
Yuhang Zhou, Mingrui Zhang, Ke Li, Mingyi Wang, Qiao Liu, Qifei Wang, Jiayi Liu, Fei Liu, Serena Li, Weiwei LI, Mingze Gao, Abhishek Kumar, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang
| Challenge: | Large language models (LLMs) have shown promise on understanding and reasoning over tables, but current approaches remain limited. |
| Approach: | They propose a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. |
| Outcome: | The proposed framework decomposes table reasoning into three specialized roles: planning, coding, and answering. |
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches for few-shot text classification rely on exploitation of lexical features and distributional signatures on training data, while neglecting to strengthen the model's ability to adapt to new tasks. |
| Approach: | They propose a meta-learning framework integrated with an adversarial domain adaptation network to improve the model's adaptive ability and generate high-quality text embedding for new classes. |
| Outcome: | The proposed framework outperforms the state-of-the-art models on four datasets and shows clear superiority over existing models. |
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for explaining "black-box" models such as Influence Functions are becoming more popular. |
| Approach: | They propose a semantic-based evaluation metric that can better align with humans’ judgment of explanations than the widely adopted diagnostic or re-training measures. |
| Outcome: | The proposed method can better align with humans’ judgment of explanations than diagnostic or re-training measures. |
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)
Copied to clipboard
Jie Cao, Zhenxuan Fan, Zhuonan Wang, Tianwei Lin, Ziyuan Zhao, Rolan Yan, Wenqiao Zhang, Feifei Shao, Hongwei Wang, Jun Xiao, Siliang Tang
| Challenge: | Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing. |
| Approach: | They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation. |
| Outcome: | The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency. |
Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction (2025.acl-long)
Copied to clipboard
| Challenge: | Unlike traditional dialogue systems, goal-oriented proactive dialogue systems focus on achieving specific objectives by actively guiding and anticipating user needs. |
| Approach: | They propose a model-agnostic two-stage Consistency Reflection and Correction framework that allows the model to reflect on discrepancies between generated responses and dialogue contexts and suggest possible corrections. |
| Outcome: | The proposed framework significantly improves the consistency between generated responses and dialogue contexts on three datasets. |
ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations depend on external knowledge sources, incurring high computational costs and limiting real-time applicability, or extract the model’s internal states, leading to poor generalization. |
| Approach: | They propose a hallucination detection framework that leverages corrective in-context learning to guide LLMs to recognize their own prediction errors and adjust internal representations, critically without updating model weights. |
| Outcome: | The proposed framework outperforms existing methods on two benchmark datasets and achieves state-of-the-art performance. |
Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) struggle to generate correct plans for multi-constraint planning problems . a recent study showed that large language models have significant potential in solving planning problems. |
| Approach: | They propose an LLM-based planning framework that formalizes and solves multi-constraint planning problems as constrained satisfiability problems. |
| Outcome: | The proposed framework achieves a success rate of 93.9% and is effective with diverse paraphrased prompts. |
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inductive reasoning over knowledge graphs lack the ability to model the logical structures of complex queries. |
| Approach: | They propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs that encodes linearized query structures and entities using pre-trained language models to find answers. |
| Outcome: | The proposed framework encodes query structures and entities using pre-trained language models to find answers. |
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)
Copied to clipboard
Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov
| Challenge: | Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps. |
| Approach: | They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels . |
| Outcome: | The proposed benchmark aims to bridge symbolic reasoning and factual verification. |
WESR: A Benchmark and Strong Baseline for Word-level Event-Speech Recognition (2026.findings-acl)
Copied to clipboard
Chenchen Yang, Kexin Huang, Liwei Fan, Qian Tu, Botian Jiang, Dong Zhang, Linqi Yin, Shimin Li, Zhaoye Fei, Qinyuan Cheng, Xipeng Qiu
| Challenge: | aaron carroll: the precise localization of non-verbal vocal events remains a critical yet under-explored challenge. carroll says current methods suffer from insufficient task definitions with limited category coverage. carrol: knowing exactly where an event occurred is not enough; knowing exactly what it happened is. |
| Approach: | They propose a taxonomy of 21 vocal events with a new categorization into discrete versus continuous types. |
| Outcome: | The proposed model disentangles ASR errors from event detection while maintaining ASR quality. |
Dissecting Human and LLM Preferences (2024.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that human and Large Language Model preferences are important for model fine-tuning and evaluation. |
| Approach: | They dissect the preferences of human and 32 different Large Language Models to understand their quantitative composition. |
| Outcome: | The proposed model is compared with 32 different large language models using real-world user-model conversations. |
Towards More Efficient Post-training via Fourier Domain Adapter Framework (2025.findings-emnlp)
Copied to clipboard
| Challenge: | FDA reparameterizes the core projection operation of the adapter module directly in the Fourier domain. |
| Approach: | They propose a framework that reparameterizes the core projection operation of the adapter module directly in the Fourier domain. |
| Outcome: | The proposed framework outperforms existing parameter-efficient fine-tuning methods on GLUE, E2E NLG, and instruction tuning benchmarks. |
Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to reduce hallucination in large language models lack a robust mechanism for generating a generative model. |
| Approach: | They propose a framework that formulates retriever–generator training in RAG as a minimax game. |
| Outcome: | The proposed framework improves retrieval-augmented generation performance on seven benchmark datasets. |
DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks (2022.findings-naacl)
Copied to clipboard
| Challenge: | Experimental results show that Transformer Encoder model can't automatically capture word order, so explicit position embeddings are required to be fed into the target model. |
| Approach: | They propose a Transformer-based language model DecBERT that uses a causal attention mask to capture word order. |
| Outcome: | The proposed model improves on the GLUE language understanding benchmark and accelerates the pre-training process. |
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evidence retrieval models are based on probability ranking principle . existing models do not align with retrieval-enhanced verification frameworks . |
| Approach: | They propose a feedback-based evidence retriever that optimizes the evidence retrieval process by incorporating feedback from the claim verifier. |
| Outcome: | Empirical studies show that the proposed method is superior to baseline methods. |
Task-adaptive Label Dependency Transfer for Few-shot Named Entity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Named Entity Recognition (NER) ignore label dependency, resulting in suboptimal performance. |
| Approach: | They propose a meta-learning method to make label dependency transferable by learning general initialization and individual parameter update rule for label dependency. |
| Outcome: | The proposed method improves existing methods by learning general initialization and individual parameter update rule for label dependency. |
A Large Scale Speech Sentiment Corpus (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing corpus for sentiment analysis uses text inputs, but voice inputs are becoming more important as smart assistants and mobile voice control become more prevalent. |
| Approach: | They propose to extend the Switchboard-1 Telephone Speech Corpus by adding sentiment labels from 3 different human annotators for every transcript segment. |
| Outcome: | The proposed corpus contains 49500 labeled speech segments covering 140 hours of audio. |
Lattice Transformer for Speech Translation (P19-1)
Copied to clipboard
| Challenge: | Recent advances in sequence modeling have highlighted the strengths of the transformer architecture. |
| Approach: | They propose a general lattice transformer for speech translation where the input is the output of the automatic speech recognition (ASR) they propose 'controllable' lattica attention mechanism to consume latent representations. |
| Outcome: | The proposed model outperforms baseline and lattice LSTM on the Chinese-English translation task. |
Mind Reader: Latent User Demand-Guided Content Optimization for Generative Search Engine (2026.acl-long)
Copied to clipboard
Tong Chen, JiaWei Guo, Yuxi Li, Baiming Chen, Houxing Ren, Zhang Zhiwei, Yunxiang Zhang, Hanyang Xia, Kun Liang, Zhaoran Fan
| Challenge: | Generative Search Engines (GSEs) have reshaped information retrieval and Generating Engine Optimization (GEO) emerges to improve the content visibility in GSEs’ responses. |
| Approach: | They propose a method to optimize content to cover latent semantic information of GSEs by decomposing query into diverse perspectives and capturing underlying semantic information. |
| Outcome: | The proposed method outperforms baselines and effectively improves content visibility (with up to 2.44x objective metrics and 1.23x subjective metrics on average). |
ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Reasoning Models suffer from the "over-thinking" problem, causing performance degradation. |
| Approach: | They propose a unified model that balances reasoning performance and efficiency across multiple formats through a reinforcement learning framework augmented with length-aware optimization. |
| Outcome: | The proposed model reduces token costs while preserving performance compared to traditional models. |
SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models (2026.findings-acl)
Copied to clipboard
Shuaimin Li, Liyang Fan, Zeyang li, Zhuoyue Wan, Yufang Lin, Shiwen Ni, Feiteng Fang, Hamid Alinejad-Rokny, Yuanfeng Song, Kun Jing, Chen Jason Zhang, Min Yang
| Challenge: | Existing methods for evaluating code large language models assume access to proprietary training corpora or use external reference sets with manually tuned, non-generalizable thresholds. |
| Approach: | They propose a framework for self-referential leakage detection for gray-box and black-box settings. |
| Outcome: | The proposed framework improves average F1 by 21.52 points in the gray-box setting and 14.46 points in black-box settings over strong baselines. |
CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models have significantly improved reasoning and generation tasks by leveraging joint vision-language representations. |
| Approach: | They propose a framework that reconciles inconsistencies across knowledge sources . they use a four-stage pipeline to generate an internal response from parametric knowledge . |
| Outcome: | Experiments on KB-VQA show that CoRe-MMRAG achieves performance gains of 5.6% and 9.3% over baseline methods. |
PathQG: Neural Question Generation from Facts (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing research for question generation encodes text as a sequence of tokens without explicitly modeling fact information. |
| Approach: | They propose to incorporate facts in the input text for question generation in a comprehensive way. |
| Outcome: | The proposed model outperforms state-of-the-art models and human evaluation shows it generates relevant and informative questions. |
TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting (2026.acl-long)
Copied to clipboard
| Challenge: | Existing time series forecasting methods use a deep synchronous fusion strategy . high-level abstract semantics are inappropriately entangled with low-level temporal dynamics . |
| Approach: | They propose a framework based on hierarchical asynchronous fusion that decouples unimodal feature learning from cross-modal interaction. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches on long-term forecasting benchmarks. |
Fewer is More: Boosting Math Reasoning with Reinforced Context Pruning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown impressive capabilities, yet they struggle with math reasoning. |
| Approach: | They propose a coarse-to-fine pruner that prunes unimportant tokens to fit the context window. |
| Outcome: | The proposed approach outperforms prompting baselines across various LLMs and 5 math datasets and achieves 4.55% absolute improvements without any fine-tuning. |
Enhancing Event Causality Identification with LLM Knowledge and Concept-Level Event Relations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to identify causal relationships between events often overlook the dependencies between similar events. |
| Approach: | They propose an ECI method enhanced by LLM Knowledge and Concept-Level Event Relations (LKCER) the method constructs a conceptual-level heterogeneous event graph by leveraging local contextual information of related event mentions. |
| Outcome: | The proposed method outperforms previous state-of-the-art methods on both benchmarks, EventStoryLine and Causal-TimeBank. |
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)
Copied to clipboard
Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che
| Challenge: | E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations . |
| Approach: | They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues. |
| Outcome: | The proposed methods can be very effective in some cases, the authors say . |
EMCompress: Video-LLMs with Endomorphic Multimodal Compression (2026.findings-acl)
Copied to clipboard
| Challenge: | Static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether. |
| Approach: | They propose a novel task that compresses multimodal input while preserving answer invariance across reasonable downstream models. |
| Outcome: | The proposed task surpasses prior methods by 0.40 F-1 with competitive query rewriting. |
AnyTrans: Translate AnyText in the Image with Large Scale Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing and computer vision have made it possible to translate images with text in one language into equivalent images displaying that text translated into another language. |
| Approach: | They propose an all-encompassing framework for the task–In-Image Machine Translation (IIMT) that incorporates contextual cues from both textual and visual elements during translation. |
| Outcome: | The proposed framework can be constructed using open-source models and requires no training, making it highly accessible and expandable. |
Leibniz: Theory-of-Mind Driven Neuro-Symbolic Logical Reasoning via Multi-Agent Collaboration (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for logical reasoning with large language models suffer from insufficient rule semantic grounding and weak rule application mechanisms. |
| Approach: | They propose a theory-of-mind driven neuro-symbolic reasoning framework that integrates natural language and symbolic representations throughout the reasoning process. |
| Outcome: | The proposed model surpasses state-of-the-art models in reasoning accuracy and flexibility. |
Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder (2020.acl-main)
Copied to clipboard
| Challenge: | Existing text classification frameworks for operational risk prediction lack interpretability and labeled data are often misaligned. |
| Approach: | They propose a semi-supervised text classification framework that integrates multi-head attention mechanism with Semi-supervised variational inference for operational risk classification. |
| Outcome: | The proposed framework outperforms baseline methods on a real-world dataset and can use unlabeled data to learn visually interpretable representations. |
Aerial Vision-and-Dialog Navigation (2023.findings-acl)
Copied to clipboard
| Challenge: | Aerial visionand-dialling navigation (AVDN) is a new approach to autonomous drones that can converse with humans and follow natural language commands to complete tasks. |
| Approach: | They propose to use Aerial Visionand-Dialog Navigation (AVDN) to navigate a drone via natural language conversation by collecting a dataset of over 3k recorded navigation trajectories with asynchronous human-human dialogs between commanders and followers. |
| Outcome: | The proposed system can converse with humans and follow natural language commands to fly to the expected destination. |
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for unknown intent detection are limited by prior knowledge of class labels. |
| Approach: | They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means. |
| Outcome: | The proposed model performs well on three real task-oriented dialogue datasets in two languages. |
M³GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | GraphRAG systems have achieved remarkable progress in enhancing performance and reliability of large language models. |
| Approach: | They propose a GraphRAG benchmark focusing on multi-entity queries with six settings for comprehensive evaluation. |
| Outcome: | The proposed method can construct diverse data with semantically correct ground-truth reasoning paths. |
MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)
Copied to clipboard
Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang
| Challenge: | Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities. |
| Approach: | They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs . |
| Outcome: | The proposed framework improves instruction following performance without compromising general performance. |
Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for document-level Event Causality Identification rely on local semantic similarity for independent event-pair discrimination . Existing approaches ignore the influence of the overall narrative backbone in the propagation of causal dependencies and the role differentiation of events within multi-cause/multi-effect structures. |
| Approach: | They propose a suggest-verify-revise approach for document-level Event Causality Identification with narrative consistency (SVRECI) they integrate heuristic causal suggestions generated by an LLM with structural suggestions derived from hypergraph modeling . |
| Outcome: | The proposed approach outperforms existing methods on event-storylines and Causal-TimeBank datasets. |
Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)
Copied to clipboard
Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang
| Challenge: | Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios. |
| Approach: | They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice. |
| Outcome: | The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models . |
BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis (2024.emnlp-demo)
Copied to clipboard
Shuhang Lin, Wenyue Hua, Lingyao Li, Che-Jui Chang, Lizhou Fan, Jianchao Ji, Hang Hua, Mingyu Jin, Jiebo Luo, Yongfeng Zhang
| Challenge: | Recent advances in large language models have demonstrated impressive reasoning capabilities, indicating their potential to serve as the foundation for agents. |
| Approach: | They propose a detailed emulation system that combines large vision-language model and multi-agent system to emulate dynamic interactions between multiple agents over a period of time. |
| Outcome: | The proposed system combines large vision-language model and multi-agent system to emulate dynamic interactions between agents and their environments over a period of time. |
Mask Attention Networks: Rethinking and Strengthen Transformer (2021.naacl-main)
Copied to clipboard
Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang
| Challenge: | Existing research explores to enhance the two sublayers separately to improve the capability of Transformer for text representation. |
| Approach: | They propose to combine SAN and Feed-Forward Networks to create a dynamic mask attention network with a learnable mask matrix which can model localness adaptively. |
| Outcome: | The proposed model outperforms the original Transformer on translation and text summarization tasks. |
Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External Knowledge (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for Zero-shot Relational Learning depend on external knowledge, resulting in increased annotation costs and limited practical applicability. |
| Approach: | They propose a structure-aware paradigm that performs ZRL without external knowledge . it leverages intrinsic structural patterns in KGs to bridge semantic correlations for new relations with existing ones. |
| Outcome: | The proposed paradigm achieves 10.66% improvement in MRR while reducing annotation costs and enhancing practical applicability on three real-world benchmarks. |
X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding (2025.findings-emnlp)
Copied to clipboard
Wenqi Zhou, Kai Cao, Hao Zheng, Yunze Liu, Xinyi Zheng, Miao Liu, Per Ola Kristensson, Walterio W. Mayol-Cuevas, Fan Zhang, Weizhe Lin, Junxiao Shen
| Challenge: | Existing benchmark datasets focus on short to moderately long videos, leaving a substantial gap in evaluating extensive, ultra-long egocentric video recordings. |
| Approach: | X-LeBench is a benchmark dataset designed to evaluate long egocentric video recordings . it uses a life-logging pipeline to produce realistic, coherent daily plans . |
| Outcome: | X-LeBench is a new benchmark dataset designed to evaluate long-form egocentric video understanding . the approach produces realistic, coherent daily plans aligned with real-world video data . |
JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting factual hallucinations in generated content exhibit limitations in the first two stages of the halluciation detection pipeline. |
| Approach: | They propose a joint claim-and-query generation framework that can detect factual hallucinations in generated content. |
| Outcome: | The proposed method outperforms existing methods on open-domain QA hallucination detection benchmarks. |
Empathy in Diversity: Personalized Depression and Anxiety Therapy via Dialogue State Tracking and Patient-Aware Planning (2026.acl-long)
Copied to clipboard
Xinwei Yang, Junyi Fan, Yuqing Liu, Jiaxuan Wang, Jiashuai Zhang, Hongru Liang, Wenqiang Lei, Yao Song
| Challenge: | Recent efforts have turned to large language models (LLMs) as therapeutic agents for psychological therapy tasks, yet robustness across diverse patients remains underexplored. |
| Approach: | They propose a realistic role-play protocol for evaluating therapeutic dialogue agents and a de-identified, expert-annotated corpus of therapist–patient dialogues. |
| Outcome: | The proposed framework outperforms baselines on therapeutic outcomes and dialogue quality while improving conversational efficiency. |
A Lightweight Mixture-of-Experts Neural Machine Translation Model with Stage-wise Training Strategy (2024.findings-naacl)
Copied to clipboard
| Challenge: | Using mixture-of-experts (MoE) to deal with language heterogeneity is a challenge in neural machine translation (NMT). |
| Approach: | They propose a lightweight MoE-based NMT model that is trained via an elaborate stage-wise training strategy. |
| Outcome: | The proposed model achieves stable improvements in translation tasks by introducing fewer extra parameters compared to baseline models. |
NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding (2024.findings-emnlp)
Copied to clipboard
Chunkit Chan, Cheng Jiayang, Yauwai Yim, Zheye Deng, Wei Fan, Haoran Li, Xin Liu, Hongming Zhang, Weiqi Wang, Yangqiu Song
| Challenge: | Theory of mind evaluations currently focus on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations. |
| Approach: | They propose a benchmark to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states. |
| Outcome: | The proposed benchmark builds upon the Belief-Desire-Intention theory and conducts the necessary empirical experiments to evaluate large language models. |
Just Adjust One Prompt: Enhancing In-Context Dialogue Scoring via Constructing the Optimal Subgraph of Demonstrations and Prompts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Using large language models as chatbots can cause hallucinations and lack of empathy, authors report . a dimension-agnostic scoring method is proposed to improve the performance of chatbot performance . |
| Approach: | They propose a dimension-agnostic scoring method that leverages in-context learning . they propose to automatically generate prompts and then request the LLM multiple times . |
| Outcome: | The proposed method outperforms baselines on five datasets. |
Enhancing Goal-oriented Proactive Dialogue Systems via Dynamic Multi-dimensional Consistency Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on goal-oriented proactive dialogue systems failed to address the multi-dimensional consistency issue between generated responses and key contextual elements. |
| Approach: | They propose a Dynamic Multi-dimensional Consistency Reinforcement Learning framework which measures the impact of each consistency dimension on overall dialogue quality and provides feedback to improve response quality. |
| Outcome: | The proposed framework significantly improves the consistency of generated responses on two datasets. |
CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation (2025.findings-acl)
Copied to clipboard
Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan
| Challenge: | Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services. |
| Approach: | They propose a Chinese electronic medical records-based dataset for MQCIC and propose CF-IR method that disentangles clinical fact verification and inferential rule reasoning actions. |
| Outcome: | The proposed method outperforms Chain-of-Thought methods on 20 representative LLMs, covering general and medical models. |
FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reranking frameworks optimize semantic relevance, leading to unstable rankings and opaque decisions on long documents. |
| Approach: | They propose a structured reranking framework that reframes financial evidence selection as constraint satisfaction under a finance-aware schema. |
| Outcome: | FINCARDS improves early-rank retrieval over lexical and LLM-based reranking baselines while reducing ranking variance. |
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies studying OOD detection in NLP often rely on external data to diversify model predictions. |
| Approach: | They propose a framework which mimics OOD detection behavior without external data . they take text classification as an archetype and compare them to existing datasets . |
| Outcome: | The proposed framework can resolve in- and out-distribution examples in a natural way using existing datasets. |
Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on surface-level patterns, overlooking the deeper attack essences. |
| Approach: | They propose an Essence-Driven Defense Framework Against Jailbreak Attacks in Aligned Large Language Models that extracts the "attack essence" from a diverse set of known attack instances and stores it in an offline vector database. |
| Outcome: | The proposed framework outperforms existing methods by reducing the Attack Success Rate by at least 20%, underscoring its superior robustness against jailbreak attacks. |
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)
Copied to clipboard
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
| Challenge: | Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood. |
| Approach: | They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction . |
| Outcome: | The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones . |
VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation (2024.emnlp-main)
Copied to clipboard
Xuan He, Dongfu Jiang, Ge Zhang, Max Ku, Achint Soni, Sherman Siu, Haonan Chen, Abhranil Chandra, Ziyan Jiang, Aaran Arulraj, Kai Wang, Quy Do, Yuansheng Ni, Bohan Lyu, Yaswanth Narsupalli, Rongqi Fan, Zhiheng Lyu, Bill Yuchen Lin, Wenhu Chen
| Challenge: | Existing video metrics are lagging behind in providing reliable scores over generated videos due to lack of large-scale human-annotated dataset. |
| Approach: | They propose to use VideoFeedback to train a human-annotated multi-aspect score over 37.6K synthesized videos from 11 existing video generative models. |
| Outcome: | The proposed model outperforms the prior best metrics by 50 points in the test. |
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering (2025.acl-long)
Copied to clipboard
Ruisheng Cao, Hanchong Zhang, Tiancheng Huang, Zhangyi Kang, Yuxin Zhang, Liangtai Sun, Hanqi Li, Yuxun Miao, Shuai Fan, Lu Chen, Kai Yu
| Challenge: | Existing approaches to retrieval augmented generation neglect PDF structure and layout . individual PDFs often exceed prompt limits and user queries may span multiple documents. |
| Approach: | They propose a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. |
| Outcome: | The proposed framework organizes semi-structured PDF content into relational database and vectorstore . it defeats both RAG and structured baselines on three PDF-based QA datasets . |
Prompt Tuning with Contradictory Intentions for Sarcasm Recognition (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent advances have shown that Pre-trained Language Models (PLMs) can achieve promising performance in many downstream Natural Language Processing (NLP) tasks. |
| Approach: | They propose to incorporate prior knowledge about contradictory intentions into prompt tuning for sarcasm recognition by mimicking the actual intention by verbalizer engineering. |
| Outcome: | The proposed model mimics the actual intention by prompt construction and indicates whether the actual intent contradicts the literal content by verbalizer engineering. |
Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability. |
| Approach: | They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness. |
| Outcome: | The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding. |
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)
Copied to clipboard
Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen
| Challenge: | GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages. |
| Approach: | They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement. |
| Outcome: | The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3. |
Structure-aware Domain Knowledge Injection for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Structure-aware Continual Pre-Training (SCPT) and Structure-Aware Supervised Fine-Tuning (SSFT) are two-stage strategies for knowledge injection and alignment that reduces the training corpus needs to 5% while achieving 100% of traditional knowledge injection performance. |
| Approach: | They propose a method to efficiently transform foundation Large Language Models into domain specialists by using two-stage strategies: Structure-aware Continual Pre-Training and Structure-Aware Supervised Fine-Tuning. |
| Outcome: | The proposed method significantly reduces the training corpus needs to a mere 5% while achieving 100% of traditional knowledge injection performance. |
SedarEval: Automated Evaluation using Self-Adaptive Rubrics (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation paradigms rely on generic scoring rubrics that fail to consider the specificities of each question and its problem-solving process. |
| Approach: | They propose a new evaluation paradigm based on self-adaptive rubrics that mimic a human evaluator's analytical process. |
| Outcome: | The proposed evaluation paradigm achieves higher concordance rate with human graders than existing paradigms, including GPT-4. |
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based debiasing methods exhibit instability due to sensitivity to prompt changes . fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting . |
| Approach: | They propose a debiasing framework that encodes fairness-related features into separable directions in the hidden activation space. |
| Outcome: | The proposed framework performs inference-time debiasing without requiring retraining or prompt design . it detects bias signatures in activations and then computes debiased steering vectors . the proposed framework is available to download in the u.s. |
DecoCal: Decoding with Calibration in Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion Large Language Models (DLLMs) generate text via iterative token denoising . but decoding is challenging, with many tokens appearing predictable early . |
| Approach: | They propose a Decoding framework that performs Calibration of token-level confidence across diffusion steps and leverages the calibrated results to guide decoding decisions. |
| Outcome: | Experiments on multiple DLLMs and benchmarks show that DecoCal improves generation accuracy compared to existing strategies. |
Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep learning have led to significant improvement of document-level neural machine translation (NMT). |
| Approach: | They propose a long-short term masking self-attention on top of the standard transformer to capture the long-range dependence and reduce the propagation of errors. |
| Outcome: | The proposed model captures the long-range dependence and reduces errors on two publicly available document-level datasets. |
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing auto-regressive pre-trained language models are challenged by recent emerging numerical reasoning datasets due to the error-prone implicit calculation. |
| Approach: | They propose a pre-computation tool to pre-compute aggregation/arithmetic results for the table in advance, so they are handy and readily available for PLMs to answer numerical reasoning questions. |
| Outcome: | The proposed model improves on TAT-QA and T5 and BART-large on multiple benchmarks. |
Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for optimizing human annotation efforts are limited . et al., 2015) suggest that densely annotated image captions improve vision-language alignment . |
| Approach: | They propose an AI-in-the-loop methodology to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints. |
| Outcome: | The proposed method improves annotation speed and retrieval performance over the parallel method. |
Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to zero-shot relation classification can only identify seen relations . existing methods rely on descriptive information to improve understandability of relation types . |
| Approach: | They propose a logic-guided semantic representation learning model for zero-shot relation classification that builds connections between seen and unseen relations via implicit and explicit semantic representations with knowledge graph embeddings and logic rules. |
| Outcome: | The proposed model can generalize to unseen relation types and achieve promising improvements. |
A Generative Framework for Personalized Sticker Retrieval (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing relevance-based generative retrieval methods lack personalization, leading to a mismatch between diverse user expectations and the retrieved results. |
| Approach: | They propose a representation learning model that learns discriminative user representations to encode user-specific sticker preferences. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in generating relevant stickers for queries. |
QueryLink: Leveraging Query-Memory Alignment for Long-Term Reasoning in LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to integrating external memory prioritize memory organization while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories. |
| Approach: | They propose a framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space. |
| Outcome: | The proposed framework significantly outperforms SOTA methods on the LoCoMo and LongMemEval benchmarks and can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM. |
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)
Copied to clipboard
Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen
| Challenge: | Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected. |
| Approach: | They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans . |
| Outcome: | The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test . |
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)
Copied to clipboard
Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Nenkov Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, YU Chen, Xue Liu, Preslav Nakov, Zhuohan Xie
| Challenge: | FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions . |
| Approach: | They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures . |
| Outcome: | The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes. |
An LLM-based Framework for Biomedical Terminology Normalization in Social Media via Multi-Agent Collaboration (2025.coling-main)
Copied to clipboard
| Challenge: | Experimental results indicate that our approach exhibits competitive performance. |
| Approach: | They propose a tuning-free approach to normalize non-standard terms using large language models . they use a search engine and a domain knowledge base to expand the short texts into accurate descriptions . |
| Outcome: | The proposed approach is based on the "Recall and Re-rank" framework . it can be used to identify the standard term in a specified termbase for non-standardized mentions . |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
Masked Language Models Know Which are Popular: A Simple Ranking Strategy for Commonsense Question Answering (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results show that pre-trained language models can improve the typical answer generation of GLMs. |
| Approach: | They propose a ranking strategy that exploits WordNet to train a ranker that picks out the most popular answers for commonsense questions. |
| Outcome: | The proposed ranking strategy is tested on a commonsense question answering (QA) dataset and on negative samples from WordNet. |
SummaCoz: A Dataset for Improving the Interpretability of Factual Consistency Detection for Summarization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Summarization is an important application of Large Language Models. |
| Approach: | They integrate human-annotated and model-generated natural language explanations to elucidate how a summary deviates and becomes inconsistent with its source article. |
| Outcome: | The proposed model provides rationales for its judgments and improves its accuracy significantly. |
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing (2024.naacl-short)
Copied to clipboard
Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
| Challenge: | Existing adversarial attacks can cause LLMs to make wrong predictions on downstream tasks or generate harmful content misaligned with human values. |
| Approach: | They propose to use randomized smoothing to add noise to the input and then make predictions based on these denoised versions. |
| Outcome: | The proposed method surpasses existing methods in both empirical and certified robustness in defending against adversarial perturbations for both downstream tasks and human alignments (i.e., jailbreak attacks). |
You Only Query Twice: Multimodal Rumor Detection via Evidential Evaluation from Dual Perspectives (2025.coling-main)
Copied to clipboard
| Challenge: | Existing rumor detectors exhibit limitations in fully exploiting responses to the source tweet as essential public opinions, and in explaining and indicating the reliability of the results obtained. Existing research mainly combats this with content and response-based detection methods. |
| Approach: | They propose a Large Language Model with both multimodal source content and the corresponding response set to extract contrasting evidence to enable maximal utilization of informative responses. |
| Outcome: | The proposed approach can indicate the model’s uncertainty (i.e., reliability) of the results. |
AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)
Copied to clipboard
Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. |
| Approach: | They propose a reward-based generalizable reward model to guide the policy model for effective test-time search. |
| Outcome: | The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average. |
Interleaved Tool-Call Reasoning for Protein Function Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have highlighted the effectiveness of chain-of-thought reasoning in symbolic domains such as mathematics and programming. |
| Approach: | They propose a tool-augmented protein reasoning agent that unifies problem decomposition, tool invocation, and grounded answer generation. |
| Outcome: | The proposed protein function understanding agent outperforms text-only reasoning models with an average performance improvement of 103%. |
Scaling Laws for Code: A More Data-Hungry Regime (2026.acl-long)
Copied to clipboard
Xianzhen Luo, Wenzhen Zheng, Qingfu Zhu, Rongyi Zhang, Houyi Li, Siming Huang, YuanTao Fan, Wanxiang Che
| Challenge: | Code Large Language Models (LLMs) are revolutionizing software engineering, but scaling laws are primarily analyzed on Natural Language (NL). |
| Approach: | They fit Chinchilla law and Farsser law to test scaling laws for code . they find code is more data-hungry and requires higher data-to-parameter ratio . |
| Outcome: | The proposed scaling laws show that the more expressive Farsser law offers greater accuracy and scales with model size. |
Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-Agent Systems (MAS) are expensive due to static panel designs, where all N agents communicate at every T round. |
| Approach: | They propose an economic framework that transforms agent selection into a dynamic resource allocation game. |
| Outcome: | The proposed system reduces token consumption by over 25% on challenging benchmarks while reducing token consumption. |
On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)
Copied to clipboard
Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye
| Challenge: | Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. |
| Approach: | They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. |
| Outcome: | Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem. |
ReCode: Reinforcing Code Generation with Reasoning-Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Bringing process-level supervision into RL often neglects optimizing reasoning quality. |
| Approach: | They propose a framework for RL that integrates reasoning-process rewards with strict execution outcomes and a benchmark comprising preference pairs of superior and inferior reasoning processes. |
| Outcome: | The proposed framework outperforms the base version of ReCode by 16.1% and reaches performance comparable to GPT-4-Turbo. |
Training Simultaneous Speech Translation with Robust and Random Wait-k-Tokens Strategy (2023.emnlp-main)
Copied to clipboard
| Challenge: | Simultaneous Speech Translation (SimulST) is a task focused on ensuring high-quality translation of speech in low-latency situations. |
| Approach: | They propose a token-level cross-modal alignment method to improve the translation of text to audio . they use audio transcription pairs to pre-train the encoder and a random wait-k-tokens strategy to optimize the task. |
| Outcome: | The proposed method achieves better trade-off between translation quality and latency. |
Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing defenses for neural ranking models are data-centric and require retraining and adversarial data generation. |
| Approach: | They propose a model-centric defense that addresses vulnerability at its architectural source without costly retraining or adversarial data generation. |
| Outcome: | The proposed approach outperforms state-of-the-art models on MS MARCO and TREC 19 while maintaining strong performance on clean data. |
Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches involve models iterating and improving their previous responses based on internal reflection ability or external feedback. |
| Approach: | They propose a reflection framework that leverages meta-thoughts and self-consistency to enhance the iterative reflection capability of Large LanguageModels. |
| Outcome: | The proposed framework achieves an average improvement of 10.1% over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. |
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration (2026.findings-acl)
Copied to clipboard
Chongsheng Zhang, Hao Wang, Zelong Yu, Esteban Garces Arias, Julian Rodemann, Zhanshuo Zhang, Qilong Li, Gaojuan Fan, Krikamol Muandet, Christian Heumann
| Challenge: | Existing approaches to synthesis of relational/structured tabular data lack effective feedback mechanism to optimize quality of generated data. |
| Approach: | They propose a relational data generator with dynamic guidance framework that uses chain-of-thought steps to generate tabular data for enhancing downstream imbalanced classification performance. |
| Outcome: | The proposed framework outperforms existing approaches in both data fidelity and downstream imbalanced classification performance on real and synthetic datasets. |
PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling (2024.emnlp-main)
Copied to clipboard
| Challenge: | Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task. |
| Approach: | They propose a method to optimize prompts for LLM-driven multi-step tasks using a human-designed feedback rule. |
| Outcome: | The proposed method outperforms human-engineered prompts and several other prompt optimization methods on 11 representative multi-step tasks. |
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)
Copied to clipboard
Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang
| Challenge: | FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. |
| Approach: | They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. |
| Outcome: | The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download. |
GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work of GUI action grounding fine-tunes data from pre-trained MLLMs, but data is limited to specific GUI environments. |
| Approach: | They propose to use a GUI-based agent to collect environment-specific data and fine-tune GUI grounding models with the collected data. |
| Outcome: | The proposed model can be extended to other GUI environments to improve performance. |
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills (2025.emnlp-main)
Copied to clipboard
Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
| Challenge: | Existing methods for LRM unlearning overlook critical information leakage in reasoning traces, even when final answers are successfully removed. |
| Approach: | They propose a method that suppresses reasoning traces while preserving the model's general reasoning ability. |
| Outcome: | The proposed method significantly reduces reasoning trace leakage and achieves strong performance across reasoning and safety benchmarks, including WMDP, StrongReject, JBB-Behaviors and WildJailbreak. |
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)
Copied to clipboard
Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones. |
| Approach: | They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
| Outcome: | The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
Learning to Control the Specificity in Neural Response Generation (P18-1)
Copied to clipboard
| Challenge: | Existing generative conversational models tend to favor general and trivial responses which appear frequently. |
| Approach: | They propose a controlled response generation mechanism to handle different utterance-response relationships in terms of specificity. |
| Outcome: | The proposed model outperforms state-of-the-art models under automatic and human evaluations. |
Tackling Long Code Search with Splitting, Encoding, and Aggregating (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing pretraining models take the first 256 tokens of code snippets by default, limiting the input length to 512. |
| Approach: | They propose a baseline SEA model which splits long code into code blocks and aggregates them to obtain a comprehensive long code representation. |
| Outcome: | The proposed model can model long code without changing their internal structure and re-pretraining. |
Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points. |
| Approach: | They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot. |
| Outcome: | The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems. |
AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation (2024.acl-long)
Copied to clipboard
Zhaowei Wang, Wei Fan, Qing Zong, Hongming Zhang, Sehyun Choi, Tianqing Fang, Xin Liu, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. |
| Approach: | They propose a framework AbsInstruct to enhance LLMs’ abstract ability through instruction tuning. |
| Outcome: | The proposed framework can enhance LLMs’ abstraction ability with strong generalization performance while maintaining their general instruction-following abilities. |
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for large language models constrain update to low-rank subspaces, limiting expressiveness and performance. |
| Approach: | They propose a distributed PEFT approach that initializes adapters across different devices and aggregates their delta updates collectively on (W) Empirically, HD-PiSSA provides 16 higher effective updated ranks than data-parallel LoRA or PiSSA when fine-tuning on 8 GPUs with the same per-device adapter rank. |
| Outcome: | Empirically, HD-PiSSA outperforms LoRA and PiSSA in math, code, and multi-task learning tasks. |
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for multi-hop reasoning ignore grounding on supporting facts of each step, which tends to generate inaccurate decompositions. |
| Approach: | They propose an interpretable stepwise reasoning framework that incorporates supporting sentences and questions at each intermediate step and utilizes the inference of the current hop for the next until reasoning out the final result. |
| Outcome: | The proposed model can boost performance and yield a better interpretable reasoning process without decomposition supervision. |
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)
Copied to clipboard
| Challenge: | relying on large language models for information has raised concerns about reliability and accuracy of outputs. |
| Approach: | They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process. |
| Outcome: | The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility. |
LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review (2025.acl-demo)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of generating inaccurate discharge summary content or fabricating information without valid sources. |
| Approach: | They propose a tool for empowering LLMs with Logic-Controlled Discharge Summary generation. |
| Outcome: | The proposed tool identifies the writing logic of discharge summaries and integrates it with EMRs to generate silver discharge summararies. |
Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)
Copied to clipboard
Linzhuang Sun, Mingyang Chen, Hao Liang, Tianpeng Li, Zhou Yijie, Chenzheng Zhu, Tianyu Guo, Huanyao Zhang, Jingxuan Wei, Bihui Yu, Fan Yang, Wentao Zhang
| Challenge: | Existing methods for training effective AI agents often resort to synthetic data generation. |
| Approach: | They propose a plug-and-play framework for data quality control in tool-use scenarios . they construct a tool-verify dataset and release a benchmark to assess its performance . |
| Outcome: | The proposed framework surpasses Qwen2.5-72B-Instruct on Tool-V-Bench and the previous APIGen-MT dataset. |
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration (2025.findings-acl)
Copied to clipboard
| Challenge: | Long-context understanding is crucial for many NLP applications, but transformers struggle with efficiency due to quadratic complexity of self-attention. |
| Approach: | They propose a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous attention patterns. |
| Outcome: | The proposed method achieves high alignment with full-attention models while reducing memory and compute overhead. |
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)
Copied to clipboard
Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou
| Challenge: | Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective. |
| Approach: | They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types. |
| Outcome: | The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment. |
Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction (2020.findings-emnlp)
Copied to clipboard
Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, Sadao Kurohashi
| Challenge: | Existing methods to extract relation triplets from plain text introduce exposure bias . prior work has focused on pipeline methods that ignore intrinsic interactions between subtasks and propagate classification errors through the tasks. |
| Approach: | They propose a model that reduces the decoding length to three within a triplet and removes the order among triplets. |
| Outcome: | The proposed model overfits to both datasets while showing better generalization. |
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on rigid pipelines that overlook user needs and provide numerical results without clear explanations. |
| Approach: | They propose an evaluation framework that employs human-like strategies for efficient, dynamic, multi-round evaluations using only a few samples per round. |
| Outcome: | The evaluation agent framework reduces evaluation time to 10% of traditional methods while delivering comparable results. |
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)
Copied to clipboard
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
| Challenge: | a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks. |
| Approach: | They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories . |
| Outcome: | The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points. |
A Simple Concatenation can Effectively Improve Speech Translation (2023.acl-short)
Copied to clipboard
| Challenge: | Experimental results show that in our unified cross-modal ST model, models can effectively utilize the auxiliary information from speech and text. |
| Approach: | They propose a unified cross-modal ST method which concatenates speech and text as the input and builds a teacher that can utilize both cross-modities simultaneously. |
| Outcome: | The proposed method can effectively utilize the auxiliary information from speech and text, and achieve compelling results on MuST-C datasets. |
FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for generating a entailment tree exhibit the reasoning chains from knowledge facts to predicted answers, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps. |
| Approach: | They propose a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems. |
| Outcome: | The proposed method outperforms existing models and achieves state-of-the-art performance in fact selection and structural correctness. |
Augmenting Large Language Model Translators via Translation Memories (2023.findings-acl)
Copied to clipboard
Yongyu Mu, Abudurexiti Reheman, Zhiquan Cao, Yuchun Fan, Bei Li, Yinqiao Li, Tong Xiao, Chunliang Zhang, Jingbo Zhu
| Challenge: | Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. |
| Approach: | They propose to use translation memories (TMs) as prompts to prompt large language models (LLMs) they find that the ability of LLMs to "understand" prompts is helpful . |
| Outcome: | The results are comparable to state-of-the-art NMT systems with bilingual data and are tuned on downstream tasks. |
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)
Copied to clipboard
Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou
| Challenge: | XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios . |
| Approach: | They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora. |
| Outcome: | The proposed dataset is labeled in English and includes only natural language understanding tasks. |
An Enhanced Knowledge Injection Model for Commonsense Generation (2020.coling-main)
Copied to clipboard
Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan, Ruofei Zhang
| Challenge: | a recent study shows that digging the relationship of concepts from scratch is non-trivial for commonsense generation tasks. |
| Approach: | They use a retrieve-and-edit framework to retrieve a prototype with these concepts . they use qt and qq to generate commonsense questions at scale . |
| Outcome: | The proposed method significantly improves the performance on commonsense generation tasks. |
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios (2025.coling-main)
Copied to clipboard
Junjie Ye, Guanyu Li, SongYang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing evaluations of tool learning focus on validation of tools for large language models with expected outcomes, but this focus ignores the complex capabilities required for LLMs to effectively use tools. |
| Approach: | They propose a fine-grained system for evaluation of large language models’ tool learning capabilities in authentic scenarios. |
| Outcome: | The proposed system examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning: format alignment, intent comprehension, behavior planning, tool selection, and answer organization. |
Visual Named Entity Linking: A New Dataset and A Baseline (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tasks in Visual Entity Linking (VEL) rely on textual data to complement multi-modal linking or only link objects with general entities. |
| Approach: | They propose a task to link regions of images with corresponding entities in Knowledge Bases . they propose three sub-tasks, based on a human-annotated visual person dataset . |
| Outcome: | The proposed task is based on a human-annotated visual person linking dataset . the proposed sub-tasks are validated on the WIKIPerson dataset based upon the proposed methods . |
KiPT: Knowledge-injected Prompt Tuning for Event Detection (2022.coling-1)
Copied to clipboard
| Challenge: | Existing prompt-based methods may suffer from low precision because they lack event-related semantic knowledge. |
| Approach: | They propose a Knowledge-injected Prompt Tuning model to improve prompt tuning . event detection aims to detect events from text by identifying and classifying event triggers . |
| Outcome: | The proposed model outperforms baseline models in few-shot scenarios. |
Manifold Adversarial Augmentation for Neural Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that NMT models can drop significantly when small perturbations are added to input sentences. |
| Approach: | They propose a data augmentation approach to sample sentences from the vicinity distributions in higher-level representations. |
| Outcome: | The proposed method improves translation accuracy on training samples from higher-level representations. |
CCG: Rare-Label Prediction via Neural SEM–Driven Causal Game (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-label classification (MLC) faces persistent challenges from label imbalance, spurious correlations, distribution shifts, especially in rare label prediction. |
| Approach: | They propose a Causal Cooperative Game framework that models multi-player cooperative process for multi-label classification. |
| Outcome: | The proposed framework improves rare label prediction and overall robustness compared to baselines. |
Effective Long-Context Scaling of Foundation Models (2024.naacl-long)
Copied to clipboard
Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma
| Challenge: | Large language models (LLMs) are rapidly deployed and continue to evolve through scaling. |
| Approach: | They propose a method to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens. |
| Outcome: | The proposed model can surpass gpt-3.5-turbo-16k's overall performance on long-context benchmarks with a cost-effective instruction tuning procedure that is free of expensive annotations. |
Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for document retrieval rely on static document identifiers . experimental results show that generative retrieval is outperforms dense retrieval in document retrievals. |
| Approach: | They propose a bootstrapped pre-training method that dynamically adjusts document identifiers during pre-train to accommodate the continuing memorization of the corpus. |
| Outcome: | The proposed method significantly outperforms existing pre-training generative retrieval baselines and performs well even in zero-shot settings. |
KCL: Few-shot Named Entity Recognition with Knowledge Graph and Contrastive Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a key subtask in natural language processing but is limited to a few labeled samples. |
| Approach: | They propose a few-shot method that harnesses the power of Knowledge Graph and Contrastive Learning to improve the prototypical semantic space learning. |
| Outcome: | The proposed method improves the prototypical semantic space learning by using knowledge graphs and contrastive learning to learn the label semantic representation. |
Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)
Copied to clipboard
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang
| Challenge: | Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions. |
| Approach: | They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency . |
| Outcome: | The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo . |
DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning (2025.coling-main)
Copied to clipboard
Raymond Li, Yuxi Feng, Zhenan Fan, Giuseppe Carenini, Weiwei Zhang, Mohammadreza Pourreza, Yong Zhang
| Challenge: | In-context Learning (ICL) has proven to be effective in a variety of complex tasks, but the selection of the most beneficial demonstration examples remains an open research problem. |
| Approach: | They propose a demonstration retrieval framework that learns a weighted combination of LLM hidden states where rich semantic information is encoded. |
| Outcome: | Experiments on two popular NL2SQL benchmarks show that the proposed method outperforms state-of-the-art models. |
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (2024.emnlp-main)
Copied to clipboard
Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Current research emphasizes LLMs’ capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. |
| Approach: | They propose a multi-level benchmark to evaluate the robustness of large language models in tool learning by establishing five external environments with varying levels of noise. |
| Outcome: | The proposed model outperforms the GPT-4 model in tool learning in three critical phases: tool selection, parameter identification, and content filling. |
Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and Intensity (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks measure whether Large language models recognize emotions . authors: LLMs can be used to validate, but they can still judge anger inappropriately . |
| Approach: | They propose a benchmark to measure whether Large language models validate anger . they use explicit norm judgments and implicit acceptability tests to measure norms . |
| Outcome: | The study finds that large differences in sanctioning thresholds and institutional norm signatures are not reducible to overall strictness. |
Triggerless Backdoor Attack for NLP Tasks with Clean Labels (2022.naacl-main)
Copied to clipboard
Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Yi Yang, Shangwei Guo, Chun Fan
| Challenge: | Backdoor attacks are a new threat to neural natural language processing models due to the fragility and lack of interpretability of NLP models. |
| Approach: | They propose a method to perform backdoor attacks without an external trigger . they propose to use clean-labeled examples to generate poisoned clean-labelled examples . |
| Outcome: | The proposed strategy is effective and hard to defend due to its triggerless nature. |
Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Neural machine translation models are often criticized for failures that happen without competency awareness. |
| Approach: | They propose a method that extends conventional NMT with a self-estimator to translate a source sentence and estimate its competency. |
| Outcome: | The proposed method performs on translation tasks intact and on quality estimation tasks better than existing methods. |
Bilateral Masking with prompt for Knowledge Graph Completion (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing word matching methods fail to obtain satisfactory single embedding representations for entities. |
| Approach: | They propose a bi-encoder-based approach to enhance entity representations by using prompts to narrow the distance between the predicted entity and the known entity. |
| Outcome: | The proposed model achieves state-of-the-art performance on the WN18RR dataset. |
Exploring Reasoning Reward Model for Agents (2026.findings-acl)
Copied to clipboard
Kaixuan Fan, Kaituo Feng, Manyuan Zhang, Tianshuo Peng, Zhixun Li, Yilei Jiang, Shuang Chen, Xiangyu Yue
| Challenge: | Existing methods for agentic reinforcement learning rely on sparse outcome-based reward for training, leading to suboptimal results. |
| Approach: | They propose an agent-based reward model that produces structured feedback for agentic trajectories, including an explicit reasoning trace and a focused critique. |
| Outcome: | The proposed model produces structured feedback for agentic trajectories including an explicit reasoning trace, a focused critique, and an overall score that evaluates process performance. |
RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for table entity linking ignore row and column contexts . existing methods for TEL focus on understanding sequential text contexts, making it difficult to adapt to the row and columns structure of tables. |
| Approach: | They propose to leverage row and column contexts to enhance the semantics of mentions in entity disambiguation. |
| Outcome: | The proposed method outperforms the state-of-the-art (SOTA) baseline by 1.5% on the in-domain dataset and 3.7% on average across three out-of domain datasets. |
PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)
Copied to clipboard
Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin
| Challenge: | Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations. |
| Approach: | They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments. |
| Outcome: | The proposed method has been deployed in a real-world commercial search system. |
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)
Copied to clipboard
| Challenge: | 3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency. |
| Approach: | They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity. |
| Outcome: | The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources. |
Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Comp-Comp is an iterative benchmarking framework grounded in the principles of comprehensiveness and compactness. |
| Approach: | They propose a benchmark framework that incorporates the principle of comprehensiveness and compactness. |
| Outcome: | The proposed framework is domain-agnostic and adaptable to a wide range of specialized fields. |
COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms treat facts independently or employ myopic search, failing to optimize collective subgraph utility. |
| Approach: | They propose a framework that formalizes evidence retrieval as a constrained submodular maximization problem. |
| Outcome: | The proposed framework captures the trade-off between information relevance and structural complexity. |
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Temporal Logic (TL) can be used to specify complex high-level specifications for systems in many engineering domains. |
| Approach: | They propose a framework for translation between NL and TL using Large Language Models . they use a dataset to create a model with 23K NL-TL pairs and human annotation . |
| Outcome: | The proposed framework achieves higher accuracy (> 95%) using only 10% training data compared with baseline model. |
MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction (2026.findings-acl)
Copied to clipboard
Zhili Pu, Lantian Zhang, Hao Duan, Zhixing Zhang, Keyun Zhu, Yongqi Fan, Ruihui Hou, Tong Ruan, Yun Tang
| Challenge: | Large language models (LLMs) offer a new paradigm for molecular property prediction (MPP), yet a semantic gap between natural language and molecul representations limits their ability to capture structure–activity relationships (SAR). |
| Approach: | They propose an ML–LLM–Rule collaborative framework for MPP that injects ML-derived substructure attribution values into LLMs and calibrates them under specific chemical contexts. |
| Outcome: | The proposed framework outperforms baseline models on multiple benchmark datasets and is highly interpretable. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on cross-modal attention at the fusion stage, but modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modulation and decision-making. |
| Approach: | They propose a framework to align navigation-related modalities before fusion by cross-modal contrastive learning. |
| Outcome: | The proposed framework integrates with the majority of existing models, resulting in improved navigation performance on various VLN benchmarks, including R2R, R4R, and CVDN. |
Instantly Learning Preference Alignment via In-context DPO (2025.naacl-long)
Copied to clipboard
| Challenge: | Presently, mainstream approaches to HPA heavily depend on fine-tuning . however, the huge computational and annotation costs of fine-timing are hard to ignore . |
| Approach: | They propose a tuning-free approach to HPA using LLMs' decoding . they first rethink the derivation procedures of DPO and build an instant scorer . |
| Outcome: | The proposed approach outperforms existing methods even with tuning-free baselines and an upgraded scorer. |
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory (2025.emnlp-main)
Copied to clipboard
Ming Li, Nan Zhang, Chenrui Fan, Hong Jiao, Yanbin Fu, Sydney Peters, Qingshu Xu, Robert Lissitz, Tianyi Zhou
| Challenge: | Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, but we lack a principled framework for understanding how these thoughts are structured. |
| Approach: | They propose a method to analyze the reasoning traces of Large Reasoning Models using Schoenfeld’s Episode Theory. |
| Outcome: | The proposed framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems. |
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference (2025.acl-long)
Copied to clipboard
Kunxi Li, Zhonghua Jiang, Zhouzhou Shen, ZhaodeWang ZhaodeWang, Chengfei Lv, Shengyu Zhang, Fan Wu, Fei Wu
| Challenge: | Existing KV cache eviction methods fail to capture modality-specific information, resulting in suboptimal performance. |
| Approach: | They propose a modality-adaptive key-value (KV) cache eviction strategy to enhance the efficiency of multimodal large language models in long-context inference. |
| Outcome: | The proposed method reduces the KV cache memory footprint and model inference latency while maintaining high accuracy across multimodal long-context tasks. |
RTCFake: Speech Deepfake Detection in Real-Time Communication (2026.findings-acl)
Copied to clipboard
Jun Xue, Zhuolin Yi, Yihuan Huang, Yanzhen Ren, Yujie Chen, Cunhang Fan, Zicheng Su, Yongcheng Zhang, Bo Cai
| Challenge: | Existing detection studies focus on offline simulations and struggle to cope with complex distortions introduced during RTC transmission. |
| Approach: | They propose a large-scale speech deepfake dataset tailored for RTC scenarios . the dataset is constructed by transmitting speech through multiple social media and conferencing platforms . |
| Outcome: | The proposed dataset is constructed by transmitting speech through multiple mainstream social media and conferencing platforms, enabling precise pairing between offline and online speech. |
A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding. |
| Approach: | They present a comprehensive review of multi-modal intent recognition . they provide a survey of the field covering textual, visual, and acoustic signals . |
| Outcome: | The present survey summarises the current state of multi-modal intent recognition . it includes a comprehensive taxonomy and advanced methods . |
Layer-wise Model Pruning based on Mutual Information (2021.emnlp-main)
Copied to clipboard
| Challenge: | In spite of impressive results of neural networks, the huge model size has hindered their applications in cases where computation and memory resources are limited. |
| Approach: | They propose a method for layer-wise pruning using mutual information based feature selection in SVMs and logistic regression. |
| Outcome: | The proposed pruning strategy offers greater speedup and higher performance than weight-based pruning methods. |
Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies address the problem of translating English data into other languages, but they are limited in form and scale. |
| Approach: | They propose a framework to unify cross-lingual and cross-modal pre-training by using English data. |
| Outcome: | The proposed framework unifies cross-lingual and cross-modal pre-training on different data. |
Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Using large language models, we generate code-tracing questions based on code snippets and descriptions. |
| Approach: | They propose to use large language models to generate code-tracing questions in introductory programming courses by using GPT4 prompts. |
| Outcome: | The proposed model generates code-tracing questions based on code snippets and descriptions. |
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)
Copied to clipboard
Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective. |
| Approach: | They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality. |
MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | a framework for constructing multi-turn Text-to-OverpassQL dialogue datasets is proposed . a dataset of over 7,800 dialogues contains more than 20,000 individual utterances . |
| Approach: | They propose a framework for constructing multi-turn Text-to-OverpassQL dialogue datasets . they convert Overpass queries into syntax trees using a custom parser based on OverpassQl . |
| Outcome: | The proposed dataset includes over 7,800 dialogues, each containing 2 to 4 user utterances . it is the first multi-turn Text-to-OverpassQL dataset built upon the OverpassNL corpus . |
RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms (2023.findings-emnlp)
Copied to clipboard
Enyu Zhou, Rui Zheng, Zhiheng Xi, Songyang Gao, Xiaoran Fan, Zichu Fei, Jingting Ye, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies on human-like behaviors in foundation models do not verify their faithfulness . a simple application of psychological tools cannot faithfully characterize all human-type behaviors . |
| Approach: | They propose a framework to characterize humanoid behaviors in foundation models . they argue that a simple application of psychological tools cannot faithfully characterize all human-like behaviors . |
| Outcome: | The proposed framework assesses the faithfulness of results based on reproducibility, internal consistency, and generalizability. |
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification (2025.acl-long)
Copied to clipboard
| Challenge: | MM-Verifier and MM Reasoner are a powerful multimodal reasoning model . large language models (LLMs) have demonstrated exceptional performance across tasks spanning myriad domains. |
| Approach: | They propose a method which combines tree search and verification to generate high-quality chain-of-thought data. |
| Outcome: | The proposed method outperforms all larger models on the MathCheck, MathVista, and MathVerse benchmarks. |
ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing models for text classification are not universally applicable and lack annotated data. |
| Approach: | They propose a framework for universal zero and few shot classification with supervised contrastive pretraining that can generalize to diverse classification tasks in both zero and many shot settings. |
| Outcome: | The proposed framework outperforms baseline models in zero and few shot settings. |
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have substantially expanded their applicability across diverse fields, such as personalized recommendations, health report analysis, and financial decision-making. |
| Approach: | They propose a generative transformation paradigm that obfuscates user data with linguistic and non-linguistic elements before submitting it to cloud-based LLMs. |
| Outcome: | The proposed paradigm obfuscates user private data while maintaining performance compared to the unobflated version. |
Sentence Similarity Based on Contexts (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing methods to measure sentence similarity face limited dataset size and training-test gap . existing methods lack large-scale labeled datasets with labeles that are labor-intensive and expensive . |
| Approach: | They propose a framework that measures sentence similarity by comparing probabilities of generating two sentences given the same context. |
| Outcome: | The proposed framework achieves significant performance boosts over baselines under supervised and unsupervised settings. |
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)
Copied to clipboard
Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan
| Challenge: | Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). |
| Approach: | They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge. |
| Outcome: | The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples. |
FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining (2022.acl-long)
Copied to clipboard
| Challenge: | Tables store rich numerical data, but numerical reasoning over tables is still a challenge. |
| Approach: | They propose a spreadsheet formula is a valuable supervision for numerical reasoning in tables. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three representative datasets of formula prediction, question answering, and cell type classification. |
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect text in training corpus are limited due to their low token probabilities. |
| Approach: | They propose a method to calibrate token probabilities for pretraining data detection by using a divergence-based calibration method. |
| Outcome: | The proposed method significantly outperforms existing methods on Chinese text on English-language benchmarks and patents. |
Reconstructing Capsule Networks for Zero-shot Intent Classification (D19-1)
Copied to clipboard
| Challenge: | Existing methods for intent classification are limited due to fast-emerging intents . a recent study shows that existing methods are not effective in recognizing unseen intents. |
| Approach: | They propose to reconstruct capsule networks for zero-shot intent classification by using latent information from labeled utterances. |
| Outcome: | The proposed method outperforms existing methods on two task-oriented dialogue datasets in different languages. |
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs (2026.findings-acl)
Copied to clipboard
Ru Peng, Tianyu Zhao, Xijun Gu, Zhiting Fan, Haokai Xu, Jinyang Zhang, Yawen Zeng, Yihong Zhuang, Kexin Yang, Junyang Lin, Dayiheng Liu, Junbo Zhao
| Challenge: | High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. |
| Approach: | They define the first HSS domain system covering 14 mainstream fields and introduce HSS-Synth. |
| Outcome: | the proposed pipeline outperforms 14 leading baselines on 16 benchmarks. |
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. |
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2026.findings-acl)
Copied to clipboard
Junjie Ye, Changhao Jiang, Zhengyin Du, Yufei Xu, Xuesong Yao, Zhiheng Xi, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang, Jiecao Chen
| Challenge: | Currently, there are no efficient reinforcement learning (RL) frameworks specifically designed for tool use. |
| Approach: | They propose an automated environment construction pipeline that incorporates scenario decomposition, document generation, function integration, complexity scaling, and localized deployment to enable high-quality training environments without external tools. |
| Outcome: | The proposed framework significantly improves the models’ tool-use performance without degrading their general capabilities. |
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics (2021.acl-long)
Copied to clipboard
Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang
| Challenge: | Existing automatic metrics are observed to correlate poorly with human evaluation. |
| Approach: | They propose to use OpenMEVA to evaluate open-ended story generation metrics. |
| Outcome: | The proposed test suite assesses the capabilities of open-ended story generation metrics on annotated stories and auto-constructed test examples. |
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Fine-tuning and in-context learning are two prevalent methods in imbuing large language models with task-specific knowledge. |
| Approach: | They propose to use a circuit shift theory to explain why in-context learning is superior to fine-tuning for tasks with implicit patterns. |
| Outcome: | The proposed method can grasp deep patterns and significantly improve accuracy on implicit patterns, compared with fine-tuning and in-context learning. |
Incorporating Object-Level Visual Context for Multimodal Fine-Grained Entity Typing (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that fine-grained entity typing is superior to text-based methods. |
| Approach: | They propose a task called fine-grained entity typing to classify entities . they propose combining textual and visual contexts to capture fine-granular semantic information . |
| Outcome: | The proposed approach achieves superior classification performance compared to previous text-based approaches. |
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Zelin Tan, Hejia Geng, Xiaohang Yu, Mulei Zhang, Guancheng Wan, Yifan Zhou, Qiang He, Xiangyuan Xue, Heng Zhou, Yutao Fan, Zhong-Zhi Li, Zaibin Zhang, Guibin Zhang, Chen Zhang, Zhenfei Yin, Philip Torr, Lei Bai
| Challenge: | elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored. |
| Approach: | They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency . |
| Outcome: | The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training. |
TeachMaster: Generative Teaching via Code (2026.acl-industry)
Copied to clipboard
Yuheng Wang, Runde Yang, Lin Wu, Jie Zhang, Jingru Fan, Tianle Zhou, Ruoyu Fu, Huatao Li, Ruijie Shi, Siheng Chen, Weinan E, Chen Qian
| Challenge: | Existing methods for creating video content are limited by high costs and slow update cycles. |
| Approach: | They propose a paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle execution. |
| Outcome: | The proposed framework reduces production costs to 0.3% of traditional course videos and provides a robust solution for scalable education. |
Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but this lacks exploration of needs in user consultations. |
| Approach: | They propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value. |
| Outcome: | The proposed model outperforms baselines on public and commercial datasets on both retrieval and ranking tasks. |
Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)
Copied to clipboard
Gongzheng Li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao
| Challenge: | Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application. |
| Approach: | They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model. |
| Outcome: | The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU. |
DrDiff: Dynamic Routing Diffusion with Hierarchical Attention for Breaking the Efficiency-Quality Trade-off (2025.emnlp-main)
Copied to clipboard
Jusheng Zhang, Yijia Fan, Kaitong Cai, Zimeng Huang, Xiaofei Sun, Jian Wang, Chengpei Tang, Keze Wang
| Challenge: | et al., 2019; Brown e.t al, 2023; Touvron e t al; 2024; OpenAI, 2024) Large Language Models (LLMs) have demonstrated remarkable capabilities in knowledge encoding and contextual understanding during their pretraining phase. |
| Approach: | They propose a dynamic expert scheduling mechanism that allocates computational resources based on text complexity and a hierarchical sparse attention mechanism that adjusts attention patterns according to a variety of input lengths. |
| Outcome: | The proposed framework overpowers existing methods on long-text generation benchmarks. |
PreGenie: An Agentic Framework for High-quality Visual Presentation Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Visual presentations are vital for effective communication, but they are limited by their complexity and lack of visual understanding. |
| Approach: | a new framework is proposed to generate high-quality visual presentations using multimodal large language models. |
| Outcome: | The proposed framework outperforms existing models in multimodal understanding and content consistency. |
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)
Copied to clipboard
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations. |
| Approach: | They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference. |
| Outcome: | The proposed method significantly mitigates object hallucinations across various model architectures. |
Distill Visual Chart Reasoning Ability from LLMs to MLLMs (2025.findings-emnlp)
Copied to clipboard
Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | a new method for generating chart annotations is proposed to improve visual reasoning in multimodal large language models. |
| Approach: | They propose a code-as-intermediary translation method for distilling visual reasoning abilities from LLMs to MLLMs. |
| Outcome: | The proposed method is cost-effective, efficient and scalable. |
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)
Copied to clipboard
Ki Sen Hung, Xi Yang, Chang Liu, Haoran Li, Kejiang Chen, Changxuan Fan, Tsun On Kwok, Weiming Zhang, Xiaomeng Li, Yangqiu Song
| Challenge: | a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes. |
| Approach: | They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries. |
| Outcome: | a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say . |
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)
Copied to clipboard
Ruizhe Chen, Tianze Luo, Zhiting Fan, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, Zhang Huaijian
| Challenge: | Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization. |
| Approach: | They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models. |
| Outcome: | The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios. |
Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)
Copied to clipboard
Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing . |
| Approach: | They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors . |
| Outcome: | The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors . |
SADA: Bridging In-Context Learning and Fine-Tuning via State-Aligned Distillation Adapters (2026.acl-long)
Copied to clipboard
| Challenge: | Prompt-based in-context learning and parameter fine-tuning are dominant paradigms for incorporating external information into large language models, but they incur high inference costs or require expensive retraining. |
| Approach: | They propose to convert prompts into temporary adapter weights to bridge this gap by converting prompts to temporary adapters. |
| Outcome: | The proposed model outperforms baselines on long-context language modeling and downstream NLU and summarization benchmarks while significantly reducing memory footprint and latency. |
A Survey on Foundation Language Models for Single-cell Biology (2025.acl-long)
Copied to clipboard
| Challenge: | Existing single-cell foundation language models are based on pre-trained and large language models. |
| Approach: | They review the development of single-cell foundation language models . they discuss data tokenization strategies and pre-training paradigms . |
| Outcome: | The proposed models have shown remarkable performance in a variety of single-cell data analysis tasks. |
VenusFactory: An Integrated System for Protein Engineering with Data Retrieval and Language Model Fine-Tuning (2025.acl-demo)
Copied to clipboard
Yang Tan, Chen Liu, Jingyuan Gao, Wu Banghao, Mingchen Li, Ruilin Wang, Lingrong Zhang, Huiqun Yu, Guisheng Fan, Liang Hong, Bingxin Zhou
| Challenge: | Pre-trained protein language models have been used in protein engineering, but their adoption is limited due to data collection, task benchmarking, and application challenges. |
| Approach: | They propose a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs. |
| Outcome: | The proposed engine integrates biological data retrieval, task benchmarking, and modular fine-tuning of PLMs. |
A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for hierarchical text classification struggle with fine-grained labels, leading to difficulties in accurate classification. |
| Approach: | They propose a hierarchical sequence ranking method for generating diverse negative samples using hierarchically structured hierarchic labels. |
| Outcome: | The proposed method achieves state-of-art (SOTA) on two datasets showing that it can distinguish between fine-grained labels and discriminate. |
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. |
Multi-grained Named Entity Recognition (P19-1)
Copied to clipboard
| Challenge: | Existing approaches treat Named Entity Recognition (NER) as a sequence labeling task. |
| Approach: | They propose a framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested. |
| Outcome: | The proposed framework outperforms current state-of-the-art frameworks by 4.4% in terms of the F1 score among nested/non-overlapping NER tasks. |
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)
Copied to clipboard
Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy . |
| Approach: | They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy. |
| Outcome: | The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training. |
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)
Copied to clipboard
Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen
| Challenge: | Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance. |
| Approach: | They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents. |
| Outcome: | The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain. |
Joint Slot Filling and Intent Detection via Capsule Neural Networks (P19-1)
Copied to clipboard
| Challenge: | Existing models that label slots and detect intent do not preserve hierarchical relationship between words, slots, and intents. |
| Approach: | They propose a capsule-based neural network model which performs slot filling and intent detection via a dynamic routing-by-agreement schema. |
| Outcome: | The proposed model performs better than existing models and existing models on real-world datasets. |
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods lack the capability for continuous learning and self-evolution from interactions, limiting the diversity and adaptability of attack strategies. |
| Approach: | They propose an automated framework capable of discovering, retrieving, and evolving attack strategies. |
| Outcome: | The proposed framework outperforms existing baselines in a black-box setting. |
IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpit (2025.findings-acl)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) is a key task in vehicular systems. |
| Approach: | They propose a benchmark that encompasses diverse automotive scenarios . they use images from front, side, and rear cameras, various road types, weather conditions, and interior views . |
| Outcome: | The proposed benchmark includes images from front, side, and rear cameras, various road types, weather conditions, and interior views. |
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies suggest that the order of training samples can affect model performance, but this is not the case. |
| Approach: | They propose to merge supervised fine-tuning models with different data orders to mitigate this imbalance by parameter merging. |
| Outcome: | The proposed method outperforms the weighted-average method on five datasets. |