Papers by Zhang Han

AFT-Tab: Adversarial Fine-Tuning for Tabular Data Synthesis with Long Text Columns (2026.acl-long)

Challenge:	On-policy distillation (OPD) requires expensive on-the-fly sampling of the student policy during training, which substantially increases training cost.
Approach:	They propose to use on-policy distillation to sample trajectories from student model . they propose to terminate the sampling early during distillation .
Outcome:	The proposed method matches the performance of full OPD in long reasoning outputs while reducing training FLOP by 2x–40x.

Copied to clipboard

Yuhao Zhang, Liang Yan, Shaoming Duan, Xinyu Zha, Jinhang Su, Peiyi Han, Chuanyi Liu

CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection (2021.findings-acl)

Challenge:	Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns.
Approach:	They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment.
Outcome:	The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility.

Copied to clipboard

Henry Weld, Guanghao Huang, Jean Lee, Tongshu Zhang, Kunze Wang, Xinghong Guo, Siqu Long, Josiah Poon, Caren Han

Challenge:	Existing toxic language detection models focus on the single utterance level without deeper understanding of context.
Approach:	They propose a dataset for in-game toxic language detection enabling joint intent classification and slot filling analysis, which is the core task of Natural Language Understanding (NLU).
Outcome:	The proposed framework handles utterance and token-level patterns, and rich contextual chatting history.

Copied to clipboard

Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown impressive language capabilities, but most of them have very unbalanced performance across different languages.
Approach:	They propose to use question translation data to enhance LLMs' multilingual capabilities by using mechanistic interpretability methods.
Outcome:	The proposed method improves multilingual alignment even with unannotated answers in English and a wide range of languages even with instruction-tuned LLMs.

Copied to clipboard

Peixuan Han, Cheng Qian, Xiusi Chen, Yuji Zhang, Heng Ji, Denghui Zhang

Encoding Spreadsheets for Large Language Models (2024.emnlp-main)

Challenge:	Existing safety mechanisms for large language models (LLMs) are inadequate to fully leverage their internal cognitive processes.
Approach:	They propose a framework that regulates unsafe outputs by utilizing the prober-based internal state monitor that actively detects harmful intentions.
Outcome:	The proposed framework reduces harmful outputs by approximately 80% while maintaining strong utility.

Copied to clipboard

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

Sequential LLM Framework for Fashion Recommendation (2024.emnlp-industry)

Challenge:	Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs).
Approach:	They propose a structural-anchor-based compression, inverse index translation, and data-format-aware aggregation module to compress spreadsheets effectively.
Outcome:	The proposed method outperforms the existing model in GPT4 and achieves a state-of-the-art 78.9% F1 score.

Copied to clipboard

Han Liu, Xianfeng Tang, Tianlang Chen, Jiapeng Liu, Indu Indu, Henry Zou, Peng Dai, Roberto Galan, Michael Porter, Dongmei Jia, Ning Zhang, Lian Xiong

ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)

Challenge:	Existing fashion recommendation systems struggle with the unique challenges of the fashion domain.
Approach:	They propose a sequential fashion recommendation framework that leverages a pre-trained large language model enhanced with recommendation-specific prompts.
Outcome:	The proposed framework significantly improves fashion recommendation performance on Amazon fashion.

Copied to clipboard

Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance (2024.emnlp-main)

Challenge:	Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited.
Approach:	They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm.
Outcome:	The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%.

Copied to clipboard

Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang

SHARP: Search-Based Adversarial Attack for Structured Prediction (2022.findings-naacl)

Challenge:	MLLMs are deployed on limited image-text pairs, which makes them more vulnerable to catastrophic forgetting of their original abilities during safety fine-tuning.
Approach:	They propose a plug-and-play strategy that detects harmful visual inputs and transforms harmful ones into harmless ones.
Outcome:	The proposed approach mitigates the risks posed by malicious visual inputs without compromising the original performance of MLLMs.

Copied to clipboard

Liwen Zhang, Zixia Jia, Wenjuan Han, Zilong Zheng, Kewei Tu

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Challenge:	SHARP is a new attack method for structured prediction models that solves several challenges.
Approach:	They propose a black-box adversarial attack method that uses a search-based optimization problem to attack adversarials.
Outcome:	The proposed method performs more potent attack than pioneer arts on two structured prediction tasks.

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

EmpathyEar: An Open-source Avatar Multimodal Empathetic Chatbot (2024.acl-demos)

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

Copied to clipboard

Hao Fei, Han Zhang, Bin Wang, Lizi Liao, Qian Liu, Erik Cambria

Morphology Matters: A Multilingual Language Modeling Analysis (2021.tacl-1)

Challenge:	EmpathyEar is an open-source, avatar-based multimodal empathetic chatbot . currently, ERG systems rely on text, sound, and vision .
Approach:	They propose an open-source, avatar-based multimodal empathetic chatbot to fill the gap in traditional text-only ERG systems.
Outcome:	The proposed system enables users to generate emotional responses to user queries . it can also generate avatars with talking faces and synchronized speeches .

Copied to clipboard

Hyunji Hayley Park, Katherine J. Zhang, Coleman Haley, Kenneth Steimel, Han Liu, Lane Schwartz

Syntactic Text Processing

Challenge:	Existing studies on inflectional morphology disagree on whether or not it makes languages harder to model.
Approach:	They propose to use a corpus of 145 Bible translations in 92 languages to investigate whether inflectional morphology makes languages harder to model.
Outcome:	The proposed model trains with linguistically motivated subword segmentation strategies and reduces the impact of morphology on language modeling.

Patton: Language Model Pretraining on Text-Rich Networks (2023.acl-long)

Copied to clipboard

Bowen Jin, Wentao Zhang, Yu Zhang, Yu Meng, Xinyang Zhang, Qi Zhu, Jiawei Han

FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

Challenge:	Existing models for text-rich networks do not take inter-document structure into account.
Approach:	They propose a pretraining framework for a text-rich network using a masked language model and a masking node prediction framework.
Outcome:	The proposed model outperforms baselines on four tasks in academic and e-commerce domains.

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

CamoQuery: Language-Guided Reasoning Camouflaged Object Segmentation (2026.acl-long)

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.

Copied to clipboard

Tianxin Han, Qing Dong, Xingwei Wang, Jie Jia, Gang Wu, Bowen Yang, Fu Zhang

TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora (2025.acl-long)

Challenge:	Existing methods for camouflaged object segmentation are limited to vision-only mask prediction under fixed task assumptions.
Approach:	They propose a language-guided reasoning camouflaged object segmentation task that generates an intent-consistent segmentation mask from an image and an implicit query text instruction.
Outcome:	The proposed task can generate an intent-consistent segmentation mask from a camouflaged image and an implicit query text instruction.

Copied to clipboard

Priyanka Kargupta, Nan Zhang, Yunyi Zhang, Rui Zhang, Prasenjit Mitra, Jiawei Han

Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems (2022.emnlp-main)

Challenge:	Recent automated taxonomies over-rely on a specific corpus, sacrificing generalizability, or depend heavily on the general knowledge of large language models (LLMs) .
Approach:	They propose a framework that dynamically adapts an LLM-generated taxonomy to a given corpus across multiple dimensions.
Outcome:	The proposed framework performs iterative hierarchical classification, expanding both the taxonomy width and depth based on corpus’ topical distribution.

Copied to clipboard

Jialiang Xu, Mengyu Zhou, Xinyi He, Shi Han, Dongmei Zhang

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)

Challenge:	Numerical Question Answering is the task of answering questions that require numerical capabilities.
Approach:	They propose to conduct numerical capability diagnosis on a series of Numerical Question Answering systems and datasets.
Outcome:	The proposed approach relieves existing systems’ lack of robust numerical capabilities.

Copied to clipboard

Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding (2025.findings-naacl)

Challenge:	Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy.
Approach:	They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses .
Outcome:	The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.

Copied to clipboard

Yuanyi Wang, Han Li, Haifeng Sun, Lei Zhang, Bo He, Wei Tang, Tianhao Yan, Qi Qi, Jingyu Wang

ProvBench: A Benchmark of Legal Provision Recommendation for Contract Auto-Reviewing (2025.acl-long)

Challenge:	Existing methods for integrating knowledge graphs rely on entity and relation embeddings . Fig. 1 shows how to decode knowledge graph in under 6 seconds .
Approach:	They propose a framework that only utilizes entity embeddings to decode knowledge graphs.
Outcome:	The proposed framework reconstructs KG representation by maximizing smoothness of entity embeddings.

Copied to clipboard

Xiuxuan Shen, Zhongyuan Jiang, Junsan Zhang, Junxiao Han, Yao Wan, Chengjie Guo, Bingcheng Liu, Jie Wu, Renxiang Li, Philip S. Yu

ALTER: Augmentation for Large-Table-Based Reasoning (2025.naacl-long)

Challenge:	Contract review is labor-intensive, time-consuming, and costly . a benchmark is proposed to detect potential legal conflicts .
Approach:	They propose a benchmark for legal provision recommendation and conflict detection for contract auto-reviewing which aims to recommend the legal provisions related to contract clauses and detect possible legal conflicts.
Outcome:	The proposed task recommends legal provisions related to contract clauses and detects legal conflicts.

Copied to clipboard

Han Zhang, Yuheng Ma, Hanfang Yang

Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)

Challenge:	Recent studies have focused on the use of large language models (LLMs) for table-based reasoning, but most approaches struggle with scalability when applied to large tables.
Approach:	They propose a framework to harness latent augmentation potential in tabular data . they use only a small subset of relevant data from the table to supplement it with schema .
Outcome:	The proposed framework outperforms all other approaches and exhibits robustness and efficiency against perturbations in large-table scenarios.

Copied to clipboard

Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

hyperdoc2vec: Distributed Representations of Hypertext Documents (P18-1)

Challenge:	Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges.
Approach:	They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments .
Outcome:	The proposed framework and evaluator are competitive in counter-argument generation tasks.

Copied to clipboard

Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, Haisong Zhang

Representation Learning

Challenge:	Conventional text embedding methods suffer from information loss if directly adapted to hyper-documents.
Approach:	They propose an embedding approach for hyper-documents that incorporates four criteria to preserve necessary information for embeddable models.
Outcome:	The proposed model outperforms several existing models on two tasks in the academic domain.

TensorOpera Router: A Multi-Model Router for Efficient LLM Inference (2024.emnlp-industry)

Copied to clipboard

Dimitris Stripelis, Zhaozhuo Xu, Zijian Hu, Alay Shah, Han Jin, Yuhang Yao, Jipeng Zhang, Tong Zhang, Salman Avestimehr, Chaoyang He

HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion (2023.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable performance across a diverse set of domain-specific tasks.
Approach:	They propose a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query’s requirements.
Outcome:	The proposed model improves query efficiency by 40% and costs by 30% while maintaining or enhancing model performance by 10%.

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.

ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws (2024.emnlp-main)

Copied to clipboard

Ruihang Li, Yixuan Wei, Miaosen Zhang, Nenghai Yu, Han Hu, Houwen Peng

MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning (2026.findings-acl)

Challenge:	Existing quality filtering methods rely on a high-quality dataset as reference . Existing methods introduce potential biases and compromise diversity .
Approach:	They propose a method that evaluates text quality based on the perplexity difference between two language models trained on the same data.
Outcome:	The proposed approach improves performance of pre-trained models without increasing training costs.

Copied to clipboard

Qianhao Yuan, Jie Lou, Zichao Li, Jiawei Chen, Yaojie Lu, Hongyu Lin, Le Sun, Debing Zhang, Xianpei Han

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching (2026.findings-acl)

Challenge:	Recent LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs and increasing compute cost and memory overhead.
Approach:	They propose an agent framework that maintains a compact memory during multi-turn interactions.
Outcome:	The proposed framework outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions.

Copied to clipboard

Han Zhu, Wei Kang, Liyong Guo, Zengwei Yao, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Dong Zhang, Xin Zhang, Xingchen Song, Lingxuan Ye, Long Lin, Daniel Povey

Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation (2023.acl-long)

Challenge:	Existing autoregressive models for dialogue generation suffer from high latency and stability issues.
Approach:	They propose a non-autoregressive (NAR) zero-shot spoken dialogue generation model based on flow-matching.
Outcome:	The proposed model outperforms existing models in speech generation due to poor speech intelligibility and turn-taking precision.

Copied to clipboard

Songming Zhang, Yunlong Liang, Shuaibo Wang, Yufeng Chen, Wenjuan Han, Jian Liu, Jinan Xu

SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation (2025.emnlp-main)

Challenge:	Existing knowledge distillation techniques for neural machine translation lack special treatment on the top-1 information, which is limiting the potential of KD.
Approach:	They propose a method to distill knowledge from top-1 predictions of teachers and a technique to infuse more additional knowledge by distilling on the data without ground-truth targets.
Outcome:	The proposed method outperforms the vanilla word-level KD and outperfies the existing methods on three different students with different capacity gaps.

Copied to clipboard

Boyu Guan, Chuang Han, Yining Zhang, Yupu Liang, Zhiyang Zhang, Yang Zhao, Chengqing Zong

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)

Challenge:	Video-guided machine translation (VMT) aims to improve translation quality by integrating contextual information from paired short video clips.
Approach:	They propose a plug-and-play framework for video-guided machine translation with multimodal large language models.
Outcome:	The proposed framework improves performance of MLLMs while reducing computational cost.

Copied to clipboard

Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds (2022.naacl-main)

Challenge:	Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored.
Approach:	They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs.
Outcome:	The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs.

Copied to clipboard

Yu Zhang, Yu Meng, Xuan Wang, Sheng Wang, Jiawei Han

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Challenge:	Existing topic models adopt a fully unsupervised setting and their discovered topics may not reflect user preferences well due to their unsupervised nature.
Approach:	They propose a framework that allows out-of-vocabulary seeds to be used to find latent topics from text corpora.
Outcome:	The proposed framework can find topics that are never seen in the corpus and can benefit from the general knowledge of pre-trained language models.

Copied to clipboard

Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

DetGPT: Detect What You Need via Reasoning (2023.emnlp-main)

Challenge:	Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach:	They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome:	The proposed framework reduces retrieval time while maintaining high model performance.

Copied to clipboard

Renjie Pi, Jiahui Gao, Shizhe Diao, Rui Pan, Hanze Dong, Jipeng Zhang, Lewei Yao, Jianhua Han, Hang Xu, Lingpeng Kong, Tong Zhang

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)

Challenge:	Recent advances in the field of computer vision have enabled more effective and sophisticated interactions between humans and machines.
Approach:	They propose a reasoning-based object detection paradigm that leverages state-of-the-art multi-modal models and open-vocabulary object detectors to perform reasoning within the context of the user’s instructions and the visual scene.
Outcome:	The proposed method enables users to interact with the system using natural language instructions, allowing for a higher level of interactivity.

Copied to clipboard

Yu Zhang, Xiusi Chen, Bowen Jin, Sheng Wang, Shuiwang Ji, Wei Wang, Jiawei Han

The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning (2026.acl-long)

Challenge:	Existing surveys on scientific LLMs focus on one or two fields or a single modality.
Approach:	They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures .
Outcome:	The proposed model architectures and evaluation techniques are used to improve scientific discovery.

Copied to clipboard

Renmiao Chen, Yida Lu, Shiyao Cui, Xuan Ouyang, Victor Shea-Jay Huang, Shumin Zhang, Chengwei Pan, Han Qiu, Minlie Huang

A Chinese Dataset for Evaluating the Safeguards in Large Language Models (2024.findings-acl)

Challenge:	Recent advances in multimodal reasoning may pose new safety risks . evaluators neglect reasoningbased safety, where harm emerges only through MLLMs .
Approach:	They introduce a benchmark for multi-image reasoning safety that includes 2,676 instances . they find that models with more advanced multi- image reasoning are more vulnerable .
Outcome:	The proposed benchmark consists of 2,676 instances covering 9 multi-image relations . the results show that models with more advanced multi- image reasoning are more vulnerable .

Copied to clipboard

Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han, Shom Lin, Zhenxuan Zhang, Angela Zhao, Preslav Nakov, Timothy Baldwin

Knowledge Inheritance for Pre-trained Language Models (2022.naacl-main)

Challenge:	a recent study has shown that large language models can produce harmful responses, exposing users to unexpected risks.
Approach:	They propose a dataset for the safety evaluation of Chinese LLMs in Mandarin Chinese . they extend the dataset to better identify false negative and false positive examples .
Outcome:	The proposed dataset is for the safety evaluation of Chinese LLMs, and is based on a Chinese dataset.

Copied to clipboard

Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)

Challenge:	Existing large-scale pre-trained language models are mainly trained from scratch individually, ignoring that many well-taught PLMs are available.
Approach:	They propose a pre-training framework called knowledge inheritance and propose auxiliary supervision to efficiently learn larger PLMs.
Outcome:	The proposed framework can be used to train large-scale language models with huge parameters and a large dataset can be adapted to domain adaptation and knowledge transfer.

Copied to clipboard

Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Challenge:	Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns.
Approach:	They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models.
Outcome:	The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts.

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario (2025.coling-main)

Copied to clipboard

Jiebin Zhang, Eugene J. Yu, Qinyu Chen, Chenhao Xiong, Dawei Zhu, Han Qian, Mingbo Song, Weimin Xiong, Xiaoguang Li, Qun Liu, Sujian Li

Layer-wise Fusion with Modality Independence Modeling for Multi-modal Emotion Recognition (2023.acl-long)

Challenge:	Existing efforts to generate Wikipedia articles for new events fall short of real-world application.
Approach:	They propose a benchmark to generate Wikipedia articles for new events under real-world scenarios . they use systematic metrics and LLM-based metrics to assess verifiability, organization, and other aspects aligned with real-life scenarios.
Outcome:	The proposed benchmarks show that hierarchical-based methods generate more comprehensive content while fine-tuned methods achieve better verifiability.

Copied to clipboard

Jun Sun, Shoukang Han, Yu-Ping Ruan, Xiaoning Zhang, Shu-Kai Zheng, Yulong Liu, Yuxin Huang, Taihao Li

Seq1F1B: Efficient Sequence-Level Pipeline Parallelism for Large Language Model Training (2025.naacl-long)

Challenge:	Existing studies focus on developing models that exploit the unification of multiple modalities.
Approach:	They propose to maintain modality independence by using a multi-modal transformer model that fuses all modalities.
Outcome:	The proposed model outperforms state-of-the-art models in multi-modal emotion recognition.

Copied to clipboard

Sun Ao, Weilin Zhao, Xu Han, Cheng Yang, Xinrong Zhang, Zhiyuan Liu, Chuan Shi, Maosong Sun

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Challenge:	Current PP methods face severe bottlenecks, including pipeline bubbles and memory footprint.
Approach:	They propose a sequence-level one-forward-one-backward (1F1B) PP method for training LLMs on long sequences with high throughput and memory efficiency.
Outcome:	The proposed method achieves 1.14X training throughput with half memory footprint compared to baseline methods . it trains an LLM with 30B parameters on sequences up to 64k tokens using 64X NVIDIA A100 GPUs .

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Language Model Pre-Training with Sparse Latent Typing (2022.emnlp-main)

Challenge:	Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach:	They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome:	The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.

Copied to clipboard

Liliang Ren, Zixuan Zhang, Han Wang, Clare Voss, ChengXiang Zhai, Heng Ji

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs (2024.emnlp-main)

Challenge:	Modern large-scale Pre-trained Language Models focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences.
Approach:	They propose a new pre-training objective that enables the model to learn latent types . the objective allows the model a self-supervised way to extract sentence-level keywords .
Outcome:	The proposed model learns interpretable latent type categories without external knowledge and improves downstream tasks.

Copied to clipboard

Tianyang Han, Qing Lian, Rui Pan, Renjie Pi, Jipeng Zhang, Shizhe Diao, Yong Lin, Tong Zhang

Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Challenge:	Existing multi-modal large language models (MLLMs) are able to process visual inputs by converting them into visual tokens that share the same latent space as language tokens in LLMs.
Approach:	They propose a benchmark that assesses the visual illusion level given spurious images and a pipeline that converts visual inputs into visual tokens.
Outcome:	The proposed benchmark shows that MLLMs suffer from an instinctive bias to varying degrees when presented with spurious images.

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

Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning (2023.findings-acl)

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.

Copied to clipboard

Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, Zhao Cao

Semantic Role Labeling Guided Multi-turn Dialogue ReWriter (2020.emnlp-main)

Challenge:	SylloBase is a benchmark for syllogistic reasoning, a critical capability widely required in natural language understanding tasks, such as text entailment and question answering.
Approach:	They propose to use a benchmark to learn syllogistic reasoning on a set of templates and to use them to generate and understand slogisms.
Outcome:	The proposed benchmark covers a complete taxonomy of syllogism reasoning patterns, and contains both automatically and manually constructed samples.

Copied to clipboard

Kun Xu, Haochen Tan, Linfeng Song, Han Wu, Haisong Zhang, Linqi Song, Dong Yu

Paraphrasing

Challenge:	Existing attentive models attend to all words without prior focus, which results in inaccurate concentration on some dispensable words.
Approach:	They propose to use semantic role labeling to provide additional guidance for multi-turn dialogue rewriting models.
Outcome:	The proposed model outperforms existing models on multi-turn dialogue rewriting tasks.

Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts (2023.emnlp-main)

Copied to clipboard

Haochen Tan, Han Wu, Wei Shao, Xinyun Zhang, Mingjie Zhan, Zhaohui Hou, Ding Liang, Linqi Song

Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values (2025.emnlp-main)

Challenge:	Existing approaches to meeting summarization are limited due to noise, lengthy transcripts, and scattered salient information.
Approach:	They propose a two-step framework for meeting summarization that leverages a self-supervised paradigm to reconstruct transcripts and a relative positional bucketing algorithm to equip models to generate the summary.
Outcome:	The proposed method significantly reduces memory consumption and processing time on two meeting summarization datasets.

Copied to clipboard

Hongbo Zhang, Han Cui, Guangsheng Bao, Linyi Yang, Jun Wang, Yue Zhang

LeakDojo: Decoding the Leakage Threats of RAG Systems (2026.findings-acl)

Challenge:	Existing offline preference optimization methods rely on preference labels to optimize large language models.
Approach:	They propose an offline method for enhancing large language models in reasoning tasks that utilizes value signals at individual reasoning steps.
Outcome:	The proposed framework outperforms offline preference optimization techniques by 4% to 6% on math reasoning, commonsense reasoning, and coding tasks.

Copied to clipboard

Maosen Zhang, Jianshuo Dong, Lu Boting, Li Wenyue, Xiaoping Zhang, Tianwei Zhang, Han Qiu

Text Style Transfer with Contrastive Transfer Pattern Mining (2023.acl-long)

Challenge:	Existing studies have failed to assess RAG leakage risks for large language models . constructing and maintaining highquality RAG knowledge databases has become increasingly costly .
Approach:	They propose a framework for controlled evaluation of RAG leakage using query generation and adversarial instructions.
Outcome:	The proposed framework compares six existing attacks across fourteen LLMs, four datasets, and diverse RAG systems.

Copied to clipboard

Jingxuan Han, Quan Wang, Licheng Zhang, Weidong Chen, Yan Song, Zhendong Mao

DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing (2026.findings-acl)

Challenge:	Existing methods for text style transfer only focus on the transformation between styles, yet they do not take into account that this transformation can be achieved via different hidden transfer patterns.
Approach:	They propose a novel approach which automatically mines hidden transfer patterns to improve TST . they use a clustering module to automatically discover hidden transfer pattern from the data .
Outcome:	The proposed method can be applied in a plug-and-play manner to enhance other methods to further improve their performance.

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

PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)

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 .

Copied to clipboard

Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum

DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)

Challenge:	Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window.
Approach:	They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window.
Outcome:	The proposed model scales to multi-million-token effective TTC without exceeding context limits.

Copied to clipboard

Bo Zhang, Jiawei Zhang, Cong Gao, Bingxu Han, Minghao Hu, Jun Zhang, Yunbo Cao, Zhunchen Luo, Wen Yao, Guotong Geng, Zhong Wang

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding (2021.acl-long)

Challenge:	Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored.
Approach:	They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator.
Outcome:	Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%.

Copied to clipboard

Shan Wu, Bo Chen, Chunlei Xin, Xianpei Han, Le Sun, Weipeng Zhang, Jiansong Chen, Fan Yang, Xunliang Cai

SEP-MLDC: A Simple and Effective Paradigm for Multi-Label Document Classification (2025.findings-naacl)

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.

Copied to clipboard

Han Liu, Shuqin Li, Xiaotong Zhang, Yuanyuan Wang, Feng Zhang, Hongyang Chen, Hong Yu

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)

Challenge:	Existing methods focus on optimizing document features, overlooking the potential of high-quality label features to enhance classification performance.
Approach:	They propose a multi-label document classification paradigm that utilizes large language models to expand the label content and generate pseudo-samples for the tail categories.
Outcome:	The proposed method significantly outperforms state-of-the-art models.

Copied to clipboard

Yuyou Zhang, Miao Li, William Han, Yihang Yao, Zhepeng Cen, Ding Zhao

Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment.
Approach:	They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses.
Outcome:	The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm.

Copied to clipboard

Xiao Wang, Tianze Chen, Qiming Ge, Han Xia, Rong Bao, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks.
Approach:	They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially.
Outcome:	The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks.

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification (2021.findings-acl)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Chengcheng Han, Zeqiu Fan, Dongxiang Zhang, Minghui Qiu, Ming Gao, Aoying Zhou

TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification (2025.acl-long)

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.

Copied to clipboard

Yindu Su, Huike Zou, Lin Sun, Ting Zhang, Haiyang Yang, Chen Li Yu, David Lo, Qingheng Zhang, Shuguang Han, Jufeng Chen

“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents (2025.emnlp-main)

Challenge:	Existing methods for product attribute value identification face critical challenges . seller-provided attribute values are often incomplete or inaccurate .
Approach:	They propose a retrieval-based method that uses taxonomy-aware contrastive learning . they use product profiles and candidate values to encode and retrieve attributes based on similarity .
Outcome:	The proposed method is based on a taxonomy-aware, hard negative sampling and adaptive inference with dynamic thresholds.

Copied to clipboard

Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Ke Xu, Minlie Huang, Chao Zhang, Han Qiu

pEBR: A Probabilistic Approach to Embedding Based Retrieval (2025.emnlp-industry)

Challenge:	Large language models (LLMs) exhibit prompt leakage vulnerabilities, raising intellectual property and confidentiality concerns.
Approach:	They use probing techniques to capture LLMs’ intent-related internal representations and show that they internalize prompt leakage intents in their hidden states before generating tokens.
Outcome:	The proposed probes achieve 90%+ AUROC across all tested models, even when applied to new system prompts and attacks.

Copied to clipboard

Han Zhang, Yunjiang Jiang, Mingming Li, Haowei Yuan, Yiming Qiu, Wen-Yun Yang

Why Does New Knowledge Create Messy Ripple Effects in LLMs? (2024.emnlp-main)

Challenge:	Existing embedding-based retrieval systems rely on heuristic and suboptimal cutoffs for item retrieval.
Approach:	They propose a probabilistic Embedding-Based Retrieval framework that learns a shared semantic representation space for both queries and items.
Outcome:	The proposed framework improves retrieval precision and recall, and ablation studies show it captures the differences between head-to-tail queries.

Copied to clipboard

Jiaxin Qin, Zixuan Zhang, Chi Han, Pengfei Yu, Manling Li, Heng Ji

Text Classification Using Label Names Only: A Language Model Self-Training Approach (2020.emnlp-main)

Challenge:	Existing research has focused on post-training knowledge editing (KE) for language models to ensure that knowledge remains accurate and up-to-date.
Approach:	They propose to use a GradSim indicator to detect when and why updated knowledge ripples in language models.
Outcome:	The proposed indicator GradSim shows that LMs that fail to handle ripple effects have low GradSIM.

Copied to clipboard

Yu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong, Heng Ji, Chao Zhang, Jiawei Han

EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models (2025.emnlp-main)

Challenge:	Current text classification methods require a large number of labeled documents as training data.
Approach:	They propose a model that uses only the label name of each class to train classification models on unlabeled data without using any labeled examples.
Outcome:	The proposed model achieves 90% accuracy on four benchmark datasets using label names as the only supervision .

Copied to clipboard

Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

Walking in Others’ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias (2024.emnlp-main)

Challenge:	Recurrent exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process.
Approach:	They propose a federated fine-tuning framework that uses a round-robin segment sharing scheme to reduce network bandwidth and adaptive sparsification methods tailored to LoRA’s training dynamics.
Outcome:	The proposed framework reduces communication overhead without compromising performance on question-answering and value-alignment tasks.

Copied to clipboard

Rongwu Xu, Zian Zhou, Tianwei Zhang, Zehan Qi, Su Yao, Ke Xu, Wei Xu, Han Qiu

SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection (2025.emnlp-main)

Challenge:	Existing prompting methods that require white-box access to the model or substantial training fail to simultaneously lessen toxicity and bias.
Approach:	They propose a strategy that encourages LLMs to integrate diverse human perspectives and self-regulate their responses by incorporating diverse human viewpoints.
Outcome:	The proposed approach can significantly diminish toxicity (up to 89%) and bias (up 73%) in LLMs’ responses.

Copied to clipboard

Qin Chen, Yuanyi Ren, Xiaojun Ma, Mugeng Liu, Shi Han, Dongmei Zhang

CaMML: Context-Aware Multimodal Learner for Large Models (2024.acl-long)

Challenge:	Existing automated layout models are ill-suited for spreadsheets, authors say . existing layout models treat components as rectangles with continuous coordinates . authors: spreadsheets are powerful tools for organizing and analyzing data .
Approach:	They formalize a spreadsheet layout generation task and introduce a framework for spreadsheet layouts . they use multimodal large language models to combine rule and vision reflection .
Outcome:	The proposed framework outperforms baselines in a spreadsheet layout generation task by 22.6%.

Copied to clipboard

Yixin Chen, Shuai Zhang, Boran Han, Tong He, Bo Li

Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs (2023.acl-long)

Challenge:	a lightweight module for tuning large multimodal models is introduced . CaMML integrates contextual samples into large models, enabling them to make inferences .
Approach:	They introduce a lightweight module for tuning large multimodal models . they have developed two models that have shown exceptional performance .
Outcome:	The proposed model outperforms LLaVA-1.5 on ten widely recognized datasets with a noticeable margin.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Meng Han, Zhihao Fan, Haijun Shan, Qi Zhang, Xuanjing Huang

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

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.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference (2024.findings-acl)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Dongjie Yang, Xiaodong Han, Yan Gao, Yao Hu, Shilin Zhang, Hai Zhao

Challenge:	Existing methods to reduce memory usage for large language models neglect inter-layer dependency between layers and huge memory consumption in pre-computation.
Approach:	They propose a method that compresses the KV cache by layer-wise retaining crucial context.
Outcome:	The proposed method reduces memory usage by layer-wise retaining crucial context . it can improve 2.2x throughput compared to Accelerate with over 54% memory reduction .

Beyond Human Labels: A Multi-Linguistic Auto-Generated Benchmark for Evaluating Large Language Models on Resume Parsing (2025.emnlp-main)

Copied to clipboard

Zijian Ling, Han Zhang, Jiahao Cui, Zhequn Wu, Xu Sun, Guohao Li, Xiangjian He

GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)

Challenge:	Efficient resume parsing is critical for global hiring, yet the lack of dedicated benchmarks for evaluating large language models (LLMs) on multilingual, structure-rich resumes hinders progress.
Approach:	They propose to use a human-in-the-loop pipeline to generate 2,500 synthetic resumes spanning 50 templates, 30 career fields, and 5 languages to evaluate large language models.
Outcome:	The proposed benchmarks show that the models perform poorly on multilingual resumes and lack of standardized templates.

Copied to clipboard

Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng

Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic (2025.findings-acl)

Challenge:	Structured product information is a major bottleneck for the efficiency of e-commerce platforms.
Approach:	They propose a data-driven approach to generate product structured representations using product metadata.
Outcome:	Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms.

Copied to clipboard

Xin Zheng, Jie Lou, Boxi Cao, Xueru Wen, Yuqiu Ji, Hongyu Lin, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun

LaTeX2Solver: a Hierarchical Semantic Parsing of LaTeX Document into Code for an Assistive Optimization Modeling Application (2023.acl-demo)

Challenge:	Existing approaches to improve the reasoning performance of large language models rely on intuitive instance-level feedback, which limits the reasoning capabilities.
Approach:	They propose a framework that pushes LLMs toward System-2-like critic capability by using a step-wise CoT reasoning paradigm and automatic construction of weak-supervision data without human annotation.
Outcome:	The proposed model significantly improves task-solving performance by filtering out invalid solutions or iterative refinement.

Copied to clipboard

Rindra Ramamonjison, Timothy Yu, Linzi Xing, Mahdi Mostajabdaveh, Xiaorui Li, Xiaojin Fu, Xiongwei Han, Yuanzhe Chen, Ren Li, Kun Mao, Yong Zhang

DIDS: Domain Impact-aware Data Sampling for Large Language Model Training (2025.emnlp-main)

Challenge:	Existing systems that translate optimization formulas manually are cumbersome and time-consuming.
Approach:	They propose a system that converts optimization formulas from TeX document to solver language.
Outcome:	The proposed system helps operations research practitioners convert optimization formulations into solver modeling languages.

Copied to clipboard

Weijie Shi, Jipeng Zhang, Yaguang Wu, Jingzhi Fang, Shibo Zhang, Yao Zhao, Hao Chen, Ruiyuan Zhang, Yue Cui, Jia Zhu, Sirui Han, Jiajie Xu, Xiaofang Zhou

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)

Challenge:	Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact.
Approach:	They propose to use a Fisher-Information Matrix-guided metric to measure domain impact to ensure intra-domain consistency and accuracy.
Outcome:	The proposed model achieves 3.4% higher average performance while maintaining comparable training efficiency.

Copied to clipboard

Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang

Challenge:	Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages.
Approach:	They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks.
Outcome:	The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B).

Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages (2025.acl-long)

Copied to clipboard

Zeli Su, Ziyin Zhang, Guixian Xu, Jianing Liu, Xu Han, Ting Zhang, Yushuang Dong

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection (2026.eacl-long)

Challenge:	XLM-R and mBART have advanced multilingualism in NLP, but low-resource languages such as Tibetan, Uyghur, Kazakh, and Mongolian are underserved.
Approach:	They propose a framework for adapting multilingual encoders to text generation in extremely low-resource languages by reusing the weights between the encoder and the decoder.
Outcome:	The proposed framework performs better on various downstream tasks even when compared with much larger models.

Copied to clipboard

Yuhang Liu, Pengxiang Li, Zishu Wei, Congkai Xie, Xueyu Hu, Xinchen Xu, Shengyu Zhang, Xiaotian Han, Hongxia Yang, Fei Wu

To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)

Challenge:	Existing GUI Agents face challenges in multi-step reasoning and reliance on textual annotations, limiting their effectiveness.
Approach:	They propose an MLLM-based GUI Agent with a two-stage supervised fine-tuning pipeline that enhances GUI understanding and grounding.
Outcome:	InfiGUIAgent achieves competitive performance on several GUI benchmarks, highlighting the impact of native reasoning skills in enhancing GUI interaction for automation tasks.

Copied to clipboard

Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie

Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference (2024.emnlp-main)

Challenge:	Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy.
Approach:	They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction.
Outcome:	The proposed model improves generalization ability and makes distant link prediction significantly easier.

Copied to clipboard

Jianxing Yu, Shiqi Wang, Han Yin, Zhenlong Sun, Ruobing Xie, Bo Zhang, Yanghui Rao

Representation Learning

Challenge:	a new method to detect clickbait posts on the Web is needed to detect such posts.
Approach:	They propose a method to detect clickbait posts on the Web using latent factors . they use features in multiple modalities to characterize the posts and causal inference to eliminate noise .
Outcome:	The proposed method can detect clickbait posts on popular social media platforms with good generalization ability.

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Copied to clipboard

Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025.emnlp-main)

Challenge:	Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach:	RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome:	RMTBench features 80 diverse characters and over 8,000 dialogue rounds.

Copied to clipboard

Benlu Wang, Iris Xia, Yifan Zhang, Junda Wang, null Feiyun Ouyang, Shuo Han, Arman Cohan, Hong Yu, Zonghai Yao

AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection (2025.acl-long)

Challenge:	Existing benchmarks assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments.
Approach:	They propose a new step-by-step evaluation pipeline that assesses formula selection, entity extraction, and arithmetic computation.
Outcome:	The proposed method improves the accuracy of large language models on medical benchmarks from 16.35% to 53.19%.

Copied to clipboard

Han Liu, Changya Li, Xiaotong Zhang, Feng Zhang, Fenglong Ma, Wei Wang, Hong Yu

DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models (2023.emnlp-main)

Challenge:	Increasing number of parameters can be challenging under resource-constrained environments.
Approach:	They propose a parameter-efficient fine-tuning method with fewer parameters and finer granularity that can adaptively select important parameters for each task.
Outcome:	The proposed method can fine-tune important parameters for each task, while maintaining the same weights.

Copied to clipboard

Chengcheng Han, Xiaowei Du, Che Zhang, Yixin Lian, Xiang Li, Ming Gao, Baoyuan Wang

Agent-in-the-Loop: A Data Flywheel for Continuous Improvement in LLM-based Customer Support (2025.emnlp-industry)

Challenge:	Chain-of-Thought prompting has improved the reasoning capabilities of Large Language Models (LLMs) but it is ineffective or detrimental to the performance on reasoning tasks in Smaller Language Model (SLMs) with less than 10 billion parameters.
Approach:	They propose a Dialogue-guided Chain-of-Thought method to improve the reasoning capabilities of Large Language Models (LLMs) by generating intermediate reasoning steps in a dialogue format to guide the model to the final answer.
Outcome:	The proposed method can achieve significant performance gains over state-of-the-art competitors on four arithmetic reasoning datasets.

Copied to clipboard

Cen Zhao, Tiantian Zhang, Hanchen Su, Yufeng Zhang, Shaowei Su, Mingzhi Xu, Yu Liu, Wei Han, Jeremy Werner, Claire Na Cheng, Yashar Mehdad

Challenge:	Existing offline approaches to improve an LLM-based customer support system rely on batch annotations.
Approach:	They propose an agent-in-the-loop framework that integrates four key types of annotations directly into live customer operations: (1) pairwise response preferences, (2) agent adoption and rationales, (3) knowledge relevance checks, and (4) identification of missing knowledge.
Outcome:	The proposed framework reduces retraining cycles from months to weeks by integrating four key types of annotations directly into live customer operations.

Multimodal, Multilingual Grapheme-to-Phoneme Conversion for Low-Resource Languages (D19-61)

Copied to clipboard

James Route, Steven Hillis, Isak Czeresnia Etinger, Han Zhang, Alan W Black

ProgressLM: Towards Progress Reasoning in Vision-Language Models (2026.acl-long)

Challenge:	Grapheme-to-phoneme conversion (g2p) is a task of predicting the pronunciation of words from their orthographic representation.
Approach:	They propose to leverage audio data as an auxiliary modality in a multi-task training process to learn a more optimal grapheme representation.
Outcome:	The proposed model reduces phoneme error rate to 2.46% on in-domain test set compared to unimodal spelling- pronunciation model.

Copied to clipboard

Jianshu Zhang, Chengxuan Qian, Haosen Sun, Haoran Lu, Dingcheng Wang, Letian Xue, Han Liu

ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code (2026.findings-acl)

Challenge:	Existing models for task progress estimation lack long-horizon and dynamic reasoning . estimating how much of a task has been completed requires long-term reasoning based on partial information.
Approach:	They propose a benchmark for evaluating progress reasoning from a single observation . they instantiate a two-stage paradigm that combines episodic retrieval with mental simulation .
Outcome:	The proposed benchmark improves on 14 VLMs on a small scale and shows common failure patterns.

Copied to clipboard

Jian Xie, Zhendong Chu, Aoxiao Zhong, Kai Zhang, Mingzhe Han, Xing Fan, Jialie Shen, Qingsong Wen

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)

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.

Copied to clipboard

Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)

Challenge:	Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools.
Approach:	They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment.
Outcome:	The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool.

Copied to clipboard

Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James Kwok, Yu Zhang

RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging (2025.emnlp-main)

Challenge:	Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality.
Approach:	They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data.
Outcome:	The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data.

Copied to clipboard

Bowen Wang, Haiyuan Wan, Liwen Shi, Chen Yang, Peng He, Yue Ma, Haochen Han, Wenhao Li, Tiao Tan, Yongjian Li, Fangming Liu, Gong Yifan, Sheng Zhang

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)

Challenge:	Existing models that require task labels or performance trade-offs are susceptible to catastrophic forgetting.
Approach:	They propose a representation-aware model merging framework for continual learning without access to historical data.
Outcome:	The proposed framework outperforms baselines in knowledge retention and generalization across five NLP tasks and multiple continual learning scenarios.

Copied to clipboard

Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

Challenge:	OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied.
Approach:	They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains .
Outcome:	The proposed method avoids narrowly enumerated rules and allows broader adaptability.

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

VideoPro: Adaptive Program Reasoning for Long Video Understanding (2026.acl-long)

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

Chenglin Li, Feng Han, Yikun Wang, Ruilin Li, Shuai Dong, Haowen Hou, Haitao Li, Qianglong Chen, Feng Tao, Jingqi Tong, Yin Zhang, Jiaqi Wang

Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (2024.lrec-main)

Challenge:	Existing methods for understanding long videos are limited due to the sparsity of visual evidence relevant to a given query.
Approach:	They propose a framework that enables VideoLLMs to reason over long videos and refine their predictions through executable programs.
Outcome:	The proposed framework outperforms existing methods across long-video understanding benchmarks.

Copied to clipboard

Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning (2025.emnlp-main)

Challenge:	Product review summarization aims to generate a concise summary based on product reviews . factual accuracy, aspect comprehensiveness, and content relevance are challenges .
Approach:	They propose an FB-Thinker framework to improve product review summarization ability . they propose two Chinese product review summary datasets for instruction-tuning and evaluation .
Outcome:	The proposed framework improves product review summarization with forward reasoning and backward refinement.

Copied to clipboard

Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri

Prompting ChatGPT in MNER: Enhanced Multimodal Named Entity Recognition with Auxiliary Refined Knowledge (2023.findings-emnlp)

Challenge:	Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks is suboptimal.
Approach:	They propose a generator-validator paradigm to iteratively generate-then-validate training data from language models to fine-tune stronger Table-Specialist models that can specialize in a given task, without using manually-labeled data.
Outcome:	The proposed model outperforms vanilla language models on diverse table tasks and can match or surpass GPT-4 level quality.

Copied to clipboard

Jinyuan Li, Han Li, Zhuo Pan, Di Sun, Jiahao Wang, Wenkun Zhang, Gang Pan

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)

Challenge:	Existing methods to enhance textual entity prediction neglect the need for external knowledge or encounter high redundancy in the retrieved knowledge.
Approach:	They propose a framework that leverages ChatGPT as an implicit knowledge base and heuristically generates auxiliary knowledge for more efficient entity prediction.
Outcome:	The proposed framework outperforms state-of-the-art methods on two classic datasets and exhibits a stronger robustness and generalization capability.

Copied to clipboard

Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang

PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (2022.findings-emnlp)

Challenge:	Existing monotonic scaling methods for large reasoning models are not reliable.
Approach:	They propose a universal framework for modulating reasoning progress in large reasoning models at test time.
Outcome:	The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation.

Copied to clipboard

Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song

Across Programming Language Silos: A Study on Cross-Lingual Retrieval-Augmented Code Generation (2026.findings-acl)

Challenge:	Pretrained language models (LMs) are a powerful transfer learning approach for knowledge graph (KG) completion.
Approach:	They propose a parameter-lite transfer learning approach for pretrained language models for knowledge graph (KG) completion.
Outcome:	The proposed model outperforms the state-of-the-art models on a knowledge graph completion benchmark by tuning 1% of the parameters.

Copied to clipboard

Qiming Zhu, Jialun Cao, Xuanang Chen, Weili Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Shing-Chi Cheung

PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation (2022.emnlp-main)

Challenge:	Current research on large language models with retrieval-augmented code generation (RACG) has focused on single-language settings, leaving their cross-lingual effectiveness underexplored.
Approach:	They construct a dataset covering 13 PLs with nearly 14K instances to study cross-lingual code knowledge transfer in RACG.
Outcome:	The proposed model shows unequal cross-lingual knowledge transfer even with direct injection and shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever.

Copied to clipboard

Ao Liu, Haoyu Dong, Naoaki Okazaki, Shi Han, Dongmei Zhang

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation (2025.findings-acl)

Challenge:	Logical table-to-text generation requires models to derive logical-level facts from table records via logical inference.
Approach:	They propose a pretrained logical form generator framework to improve generation fidelity . they use a dataset to test the logical inference accuracy of the framework .
Outcome:	The proposed framework outperforms baselines on LOGICNLG and CONTLOG on two benchmarks.

Copied to clipboard

Xueru Wen, Jie Lou, Xinyu Lu, Yuqiu Ji, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Debing Zhang, Le Sun

Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)

Challenge:	Large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.
Approach:	They propose a framework that allows large language models to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
Outcome:	The proposed framework enables LLMs to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.

Copied to clipboard

Guangfeng Yan, Lu Fan, Qimai Li, Han Liu, Xiaotong Zhang, Xiao-Ming Wu, Albert Y.S. Lam

Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference (2026.findings-eacl)

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.

Copied to clipboard

Han Yuan, Yue Zhao, Li Zhang, Wuqiong Luo, Zheng Ma

Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)

Challenge:	Prior studies have examined the impact of structured output on LLMs’ generation quality, often presenting one-way findings.
Approach:	They propose to derive five potential causal structures characterizing the influence of structured output on LLMs’ generation using one assumed and two guaranteed constraints.
Outcome:	The proposed pipeline can be extended to other modules and is not limited to structured output but can be used in industrial applications.

Copied to clipboard

Dongming Sheng, Kexin Han, Hao Li, Yan Zhang, Yucheng Huang, Jun Lang, Wenqiang Liu

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems.
Approach:	They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction.
Outcome:	The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets.

Copied to clipboard

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions (2023.emnlp-main)

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Copied to clipboard

Zhebin Zhang, Xinyu Zhang, Yuanhang Ren, Saijiang Shi, Meng Han, Yongkang Wu, Ruofei Lai, Zhao Cao

AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks (2023.findings-acl)

Challenge:	Existing approaches to QA using retrieval-augmented knowledge are limited by limited coverage and noisy information.
Approach:	They propose an induction-augmented generation framework that utilizes inductive knowledge along with retrieved documents for implicit reasoning.
Outcome:	The proposed framework outperforms RAG and ChatGPT on two Open-Domain QA tasks.

Copied to clipboard

Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, Dongmei Zhang

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning (2025.emnlp-main)

Challenge:	Tabular data analysis is performed everyday across various domains.
Approach:	They propose to use a dataset of 467k tables with supervision labels for four types of field metadata.
Outcome:	The proposed framework improves the understanding capability of tabular models by incorporating distribution and knowledge information.

Copied to clipboard

Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents (2025.acl-long)

Challenge:	Existing reward models assume a global reward function, limiting personalization and pluralistic alignment.
Approach:	They propose a framework that leverages binary preference datasets to enhance personalized preference learning.
Outcome:	The proposed framework captures diverse human preferences without fine-grained annotations and significantly improves personalized preference learning on downstream tasks.

Copied to clipboard

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (2024.emnlp-main)

Challenge:	Existing language model agents excel in planning and reasoning, but lack creativity in unfamiliar environments.
Approach:	They propose a benchmark suite of room escape game environments to challenge agents with creative reasoning, unconventional tool use and iterative problem-solving to uncover implicit goals.
Outcome:	The proposed framework can perform with 40% fewer steps and hints and performs robustly across difficulty levels.

Copied to clipboard

Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, Maosong Sun

Challenge:	Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) drafting efficiency has become a bottleneck in the final speedup of speculative drafting, therefore generating longer drafts at less cost can lead to better speedup.
Approach:	They propose a method that uses existing model to drafting and target LLM to verify draft in a low-cost parallel manner.
Outcome:	The proposed method can achieve speedups of up to 2.4 over speculative decoding and 3.9 over vanilla decoding without fine-tuning draft and target models.

Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Challenge:	Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach:	They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome:	The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language (2024.emnlp-main)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Shun Wang, Ge Zhang, Han Wu, Tyler Loakman, Wenhao Huang, Chenghua Lin

What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma (2025.acl-long)

Challenge:	Existing evaluation methods focus on fluency and factual reliability, while neglecting figurative quality.
Approach:	They propose a set of human evaluation metrics focused on the translation of figurative language and a parallel metaphor corpus generated by post-editing.
Outcome:	The proposed evaluation protocol estimates four aspects of MT: Metaphorical Equivalence, Emotion, Authenticity, and Quality.

Copied to clipboard

Han Meng, Yancan Chen, Yunan Li, Yitian Yang, Jungup Lee, Renwen Zhang, Yi-Chieh Lee

Linguistic Theories

Challenge:	Existing resources for training neural models to finely classify mental-health stigma are limited, relying primarily on social media or synthetic data without theoretical underpinnings.
Approach:	They propose to use an expert-annotated corpus of human-chatbot interviews to finely classify mental-health stigma.
Outcome:	The proposed corpus can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma.

SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction (2022.naacl-main)

Copied to clipboard

Yuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han

Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training (2025.findings-acl)

Challenge:	Existing methods for relation extraction only implicitly learn to model relevant contexts and entity types while being trained for RE.
Approach:	They propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for RE.
Outcome:	The proposed method outperforms the runner-up method on three benchmarks by 5.04% . textual contexts and entity types are the major information sources that lead to the success of previous approaches.

Copied to clipboard

Yihang Yao, Zhepeng Cen, Miao Li, William Han, Yuyou Zhang, Emerson Liu, Zuxin Liu, Chuang Gan, Ding Zhao

EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks.
Approach:	They propose a data-centric approach that enhances LLMs’ awareness of symmetry in query variations and propose syMmetry-ENhanceD (MEND) data augmentation.
Outcome:	Extensive experiments on logical and arithmetic reasoning tasks show that the proposed approach improves model robustness at the knowledge extraction stage through query augmentation.

Copied to clipboard

Jiamin Su, Yibo Yan, Fangteng Fu, Zhang Han, Jingheng Ye, Xiang Liu, Jiahao Huo, Huiyu Zhou, Xuming Hu

Pairwise Prompt-Based Tuning with Parameter Efficient Fast Adaptation for Generalized Zero-Shot Intent Detection (2025.findings-naacl)

Challenge:	Automated Essay Scoring (AES) systems face three major challenges: reliance on handcrafted features that limit generalizability, difficulty in capturing fine-grained traits like coherence and argumentation, and inability to handle multimodal contexts.
Approach:	They propose a multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.
Outcome:	The proposed system can evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.

Copied to clipboard

Xiaotong Zhang, Qianru Zhou, Han Liu, Hong Yu

Speculating LLMs’ Chinese Training Data Pollution from Their Tokens (2025.emnlp-main)

Challenge:	Existing methods to generalize from seen intents to unseen intents are not effective . Xian et al., 2019: a novel approach to generalized zero-shot intent detection is needed .
Approach:	They propose a pairwise prompt-based tuning model with parameter efficient fast adaptation . they leverage hybrid contrastive learning in discriminant space and masked language modeling .
Outcome:	The proposed model can generalize to unseen intents with the help of seen intents . the proposed model is based on a pairwise prompt-based tuning model with fast adaptation .

Copied to clipboard

Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu, Qi Li, Minlie Huang, Hewu Li, Han Qiu

CMHG: A Dataset and Benchmark for Headline Generation of Minority Languages in China (2025.emnlp-main)

Challenge:	Experiments on GPT and other 23 LLMs indicate that tokens widely exist while GPT’s vocabulary behaves the worst: more than 23% long Chinese tokens (i.e., a token with more than two Chinese characters) are either porn or online gambling.
Approach:	They propose to locate Polluted Chinese (PoC) tokens in LLMs and build a PoC token detector to label them in vocabularies by considering each token’s semantics and related contents from the search engines.
Outcome:	The proposed method predicts that the ratio of “*” related webpages in GPT-4o's training data is around 0.5%.

Copied to clipboard

Guixian Xu, Zeli Su, Ziyin Zhang, Jianing Liu, Xu Han, Ting Zhang, Yushuang Dong

Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)

Challenge:	Minority languages in China face significant challenges due to their unique writing systems, which differ from international standards.
Approach:	They propose a dataset specifically curated for headline generation tasks for minority languages in China . they propose 50,000 entries each for Uyghur and Mongolian, and a test set annotated by native speakers .
Outcome:	The proposed dataset will help improve headline generation in minority languages . it includes 100,000 entries for Tibetan, 50,000 entries each for Uyghur and Mongolian .

Copied to clipboard

Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu

The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) (2024.findings-acl)

Challenge:	Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs.
Approach:	They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents.
Outcome:	The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China .

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Yiding Liu, Yue Xing, Han Xu, Jie Ren, Yi Chang, Shuaiqiang Wang, Dawei Yin, Jiliang Tang

MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak (2026.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model generation with proprietary and private data, where data privacy is . a privacy issue that is currently under-explored, is posed by RAG.
Approach:	They propose to use retrieval-augmented generation (RAG) to facilitate language model generation with proprietary and private data where data privacy is a pivotal concern.
Outcome:	The proposed attack methods demonstrate that RAG can mitigate the old risks, i.e., leakage of the LLMs’ training data.

Copied to clipboard

Zhiheng Han, Yao Zhang, Jun Wang, Zhenglu Yang

SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read (2026.findings-acl)

Challenge:	Medical large language models exhibit high domain specificity and condensed semantics, making them vulnerable to diagnostic errors in real-world clinical settings.
Approach:	They propose a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues.
Outcome:	Experiments on chest X-ray-based multimodal medical dialogues show that MSIA outperforms existing jailbreak methods with an average success rate of 76.67%.

Copied to clipboard

Yibo Peng, Peng Xia, Ding Zhong, Kaide Zeng, Siwei Han, Yiyang Zhou, Jiaqi Liu, Ruiyi Zhang, Huaxiu Yao

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning (2026.acl-long)

Challenge:	MLLMs lack visual grounding mechanism to read text embedded in images, or rely on parametric shortcuts . despite strong OCR capabilities, models suffer performance degradation of 12.7% in the VQ setting .
Approach:	They propose a plug-and-play training strategy that invalidates shortcuts in text prompts . they propose 'vq' setting where text queries are rendered directly onto images .
Outcome:	The proposed training strategy surpasses the base model by 5.4% and GRPO based on original images by 2.7% on four representative OOD benchmarks.

Copied to clipboard

Hanbing Liu, Lang Cao, Yuanyi Ren, Mengyu Zhou, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang

Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)

Challenge:	Large language models (LLMs) often produce unnecessarily long explanations that reduce efficiency.
Approach:	They propose a length-aware reward that selectively penalizes insignificance tokens . they also propose 'dynamic length control' that encourages more detailed reasoning .
Outcome:	The proposed method reduces response length while maintaining correctness, the authors show . it selectively penalizes insignificance tokens while maintaining accuracy .

Copied to clipboard

Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen

A Coarse-to-Fine Prototype Learning Approach for Multi-Label Few-Shot Intent Detection (2024.findings-emnlp)

Challenge:	Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models.
Approach:	They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model.
Outcome:	The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD.

Copied to clipboard

Xiaotong Zhang, Xinyi Li, Feng Zhang, Zhiyi Wei, Junfeng Liu, Han Liu

COPR: Continual Human Preference Learning via Optimal Policy Regularization (2025.findings-acl)

Challenge:	Existing methods for few-shot intent detection are limited due to data scarcity and lack of information for unseen domains.
Approach:	They propose to enhance utterance representations with label synset augmentation and refine prototypes by distilling coarse domain knowledge from a universal teacher model.
Outcome:	The proposed approach outperforms existing methods in terms of accuracy and generalization across domains.

Copied to clipboard

Han Zhang, Lin Gui, Yu Lei, Yuanzhao Zhai, Yehong Zhang, Zhuo Zhang, Yulan He, Hui Wang, Yue Yu, Kam-Fai Wong, Bin Liang, Ruifeng Xu

From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models with human preferences, but its complex process limits its ability to continually learn human feedback.
Approach:	They propose a non-RL offline method to convert historical optimal policies into optimization constraints when continually learning new preferences.
Outcome:	The proposed method outperforms strong CL baselines in terms of reward-based evaluations and human assessment.

Copied to clipboard

Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong

MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)

Challenge:	Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages.
Approach:	They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English.
Outcome:	The proposed model outperforms open-source and Tibetan-focused models on diverse tasks.

Copied to clipboard

Qing Wang, Xue Han, Jiahui Wang, Lehao Xing, Qian Hu, Lianlian Zhang, Chao Deng, Junlan Feng

Grounding Agent Memory in Contextual Intent (2026.findings-acl)

Challenge:	MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code.
Approach:	They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels.
Outcome:	The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources.

Copied to clipboard

Ruozhen Yang, Yucheng Jiang, Yueqi Jiang, Priyanka Kargupta, Yunyi Zhang, Jiawei Han

Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection (2026.acl-long)

Challenge:	Large language models are deployed in long-horizon tasks that require agents to track interleaved goals, resolve references to prior information, and coordinate actions over extended trajectories.
Approach:	They propose an agentic memory system that indexes each trajectory step with a structured retrieval cue, contextual intent, and retrieves history by matching the current step’s intent.
Outcome:	The proposed system outperforms the strongest benchmark by 35.6%, with the largest gains as trajectory length increases.

Copied to clipboard

Yuchen Zhang, Yaxiong Wang, Kecheng Han, Yujiao Wu, Lianwei Wu, Li Zhu, Zhedong Zheng

JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling (2025.emnlp-main)

Challenge:	Existing methods for manipulation detection and grounding focus on manipulator type classification under result-oriented supervision.
Approach:	They propose a reasoning-driven framework that shifts learning from outcome fitting to process modeling.
Outcome:	The proposed framework achieves state-of-the-art with superior generalization on large-scale datasets.

Copied to clipboard

Jinwang Song, Hongying Zan, Kunli Zhang, Lingling Mu, Yingjie Han, Haobo Hua, Min Peng

Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced Calibration (2023.findings-acl)

Challenge:	Recent advances in Large Language Models have improved Text-to-SQL methods . however, they still face challenges such as complex multi-stage pipelines and poor robustness to noisy schema information.
Approach:	They propose a single-stage SFT framework that optimizes schema linking and SQL generation via a unified loss.
Outcome:	Experiments on the Spider and BIRD benchmarks show that JOLT-SQL achieves state-of-the-art execution accuracy among comparable-size open-source models.

Copied to clipboard

Dongkyu Lee, Gyeonghun Kim, Janghoon Han, Taesuk Hong, Yi-Reun Kim, Stanley Jungkyu Choi, Nevin L. Zhang

BCL: Bayesian In-Context Learning Framework for Information Extraction (2026.findings-acl)

Challenge:	Existing approaches to inference have been based on stochastic decoding but they sacrifice output quality due to randomness.
Approach:	They propose a deterministic decoding scheme, local temperature beam search, which reduces repetition while maintaining the level of coherence as in beam search.
Outcome:	The proposed inference scheme reduces repetition while maintaining coherence as in beam search.

Copied to clipboard

Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li

Mixture-of-LoRAs: An Efficient Multitask Tuning Method for Large Language Models (2024.lrec-main)

Challenge:	Existing information extraction (IE) tasks rely on in-context learning with large language models.
Approach:	They propose a Bayesian-based in-context learning framework that refines label representations across IE tasks using particle filtering and Bayes updates.
Outcome:	The proposed framework improves performance over existing methods (up to 30%) it underperforms one-shot prompting by a substantial margin on NER tasks and CodeIE fails on RE tasks with near-zero micro-F1.

Copied to clipboard

Wenfeng Feng, Chuzhan Hao, Yuewei Zhang, Yu Han, Hao Wang

MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)

Challenge:	Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models.
Approach:	They propose a mixture-of-LoRAs architecture which is a parameter-efficient tuning method designed for multi-task learning with LLMs.
Outcome:	The proposed method can be iteratively adapted to a new domain, enabling quick domain-specific adaptation.

Copied to clipboard

Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Challenge:	Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE.
Approach:	They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts.
Outcome:	Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%.

Copied to clipboard

Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)

Challenge:	prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach:	They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome:	The proposed model maintains safety while reducing over-refusal.

Copied to clipboard

Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu

Challenge:	Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols.
Approach:	They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations.
Outcome:	The proposed method reveals local knowledge conflicts invisible to existing benchmarks.

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models (2026.findings-acl)

Copied to clipboard

Yingzhi Mao, Chunkang Zhang, Junxiang Wang, Xinyan Guan, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling (2022.coling-1)

Challenge:	Existing methods often apply coarse-grained constraints over entire reasoning trajectories . Existing approaches often apply unsafe constraints, causing unsafe outputs .
Approach:	They propose a trajectory-level training framework that mitigates Self-Jailbreak . they propose 'chain-of-guardrail' to mitigate self-jailbreak by targeting step-level interventions .
Outcome:	The proposed framework mitigates Self-Jailbreak by targeting step-level interventions while maintaining reasoning ability.

Copied to clipboard

Yangjun Wu, Han Wang, Dongxiang Zhang, Gang Chen, Hao Zhang

PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving (2026.findings-acl)

Challenge:	Existing approaches to multiple intent detection and slot filling focus on task-specific components to capture the relationships between intents and slots.
Approach:	They propose a Unified Generative framework that captures the relationships between intents and slots in an utterance and formulates the task as a question-answering problem.
Outcome:	The proposed framework surpasses baselines on full-data and multi-intent benchmarks on 5-shot and 10-shot scenarios.

Copied to clipboard

Yuxuan Dong, Xinyu Zhang, Lingling Zhang, Han Lai, Pengyu Li, Bifan Wei, Yaqiang Wu, Jun Liu

FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan Generation (2025.acl-long)

Challenge:	Existing Large Language Models (LLMs) struggle with physics problem solving due to difficulties in decoding implicit constraints and maintaining physical consistency.
Approach:	They propose a Generative PRM that treats evaluation as a generative task . it produces fine-grained diagnoses comprising critiques, final judgments, and specific error types .
Outcome:	The proposed model improves performance across seven benchmarks in Best-of-N and critique refinement strategies.

Copied to clipboard

Jun Yin, Pengyu Zeng, Haoyuan Sun, Yuqin Dai, Han Zheng, Miao Zhang, Yachao Zhang, Shuai Lu

Challenge:	Existing evaluation methods for floor plan generation rely on statistical metrics like FID, GED, and PSNR, which fail to evaluate using domain knowledge.
Approach:	They propose to use a first floor plan dataset to train a floor plan generation model based on a multi-dimensional preference score and a textual analysis to integrate architects’ professional expertise and preferences.
Outcome:	The proposed model outperforms baseline models in text-conditional and class-condition tasks and is more rational and aligns better with human preferences.

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

VideoQA-TA: Temporal-Aware Multi-Modal Video Question Answering (2025.coling-main)

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

Copied to clipboard

Zhixuan Wu, Bo Cheng, Jiale Han, Jiabao Ma, Shuhao Zhang, Yuli Chen, Changbo Li

TLM: Token-Level Masking for Transformers (2023.emnlp-main)

Challenge:	Existing methods for video question answering align visual or textual features directly with large language models, limiting the deep semantic association between modalities and hindering a comprehensive understanding of interactions within spatial and temporal contexts.
Approach:	They propose a temporal-aware framework for multi-modal video question answering that aligns videos and questions at fine-grained levels.
Outcome:	The proposed framework improves reasoning ability and accuracy of videoQA by aligning videos and questions at fine-grained levels.

Copied to clipboard

Yangjun Wu, Kebin Fang, Dongxiang Zhang, Han Wang, Hao Zhang, Gang Chen

BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Challenge:	Structured dropout approaches have been investigated to regularize the multi-head attention mechanism in Transformers.
Approach:	They propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting by manipulating the connections between tokens in the multi-head attention via masking.
Outcome:	The proposed regularization scheme outperforms attention dropout and DropHead on 18 datasets and can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU).

Copied to clipboard

Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie Zhou, Jun Zhang, Jia Chao, Maosong Sun

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Challenge:	Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach:	They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome:	The proposed toolkit can support big model inference and tuning at extremely low computation cost.

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition (2025.emnlp-main)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Sina Semnani, Han Zhang, Xinyan He, Merve Tekgurler, Monica Lam

CAST: Achieving Stable LLM-based Text Analysis for Data Analytics (2026.findings-acl)

Challenge:	Existing vision-language models are not equipped to read diverse languages and scripts found in historical materials.
Approach:	They propose to train an open-weight vision-language model for historical text recognition on CHURRO-DS, the largest historical text-recognition dataset to date.
Outcome:	The proposed model outperforms existing vision-language models on CHURRO-DS, the largest historical text recognition dataset to date.

Copied to clipboard

Jinxiang Xie, Zihao Li, Wei He, Rui Ding, Shi Han, Dongmei Zhang

COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)

Challenge:	Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labeling.
Approach:	They propose a framework that enhances output stability by constraining the model’s latent reasoning trajectory.
Outcome:	The proposed framework improves stability by constraining the model's latent reasoning trajectory.

Copied to clipboard

Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Ranran Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed ELsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Challenge:	a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications .
Approach:	a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19.
Outcome:	a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing .

Copied to clipboard

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving (2024.findings-naacl)

Challenge:	Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach:	They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome:	The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.

Copied to clipboard

Pei Chen, Shuai Zhang, Boran Han

Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques.
Approach:	They propose a collaborative multi-agent, multi-reasoning-path prompting framework that prompts LLMs to play different roles in a problem-solving team and encourages different role-play agents to collaboratively solve the target task.
Outcome:	The proposed framework is applied to two college-level science problems over competitive baselines.

Copied to clipboard

Yujie Wang, Yunwei Zhao, Jing Yang, Han Han, Shiguang Shan, Jie Zhang

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization (2026.acl-long)

Challenge:	Digital media platforms often contribute to cognitive-behavioral fixation, a phenomenon in which users exhibit sustained and repetitive engagement with narrow content domains.
Approach:	They propose a multimodal topic extraction module and a cognitive-behavioral fixation quantification module that collaboratively enable adaptive, hierarchical, and interpretable assessment of user behavior.
Outcome:	The proposed framework lays the groundwork for scalable computational analysis of cognitive fixation.

Copied to clipboard

Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

RACE: Retrieval-augmented Commit Message Generation (2022.emnlp-main)

Challenge:	Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations.
Approach:	They analyze the current LLM learning paradigms to tackle four critical evaluation dimensions that have emerged as critical dimensions in recent studies.
Outcome:	The proposed models are able to interact with chemical spaces through natural language and symbolic notations, and have emerging extensions to incorporate multi-modal inputs.

Copied to clipboard

Ensheng Shi, Yanlin Wang, Wei Tao, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Hongbin Sun

AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)

Challenge:	Existing approaches to automatically generate commit messages are repetitive or redundant.
Approach:	They propose a retrieval-augmented neural commit message generation method which treats the retrieved similar commit as an exemplar and leverages it to generate an accurate commit message.
Outcome:	The proposed method outperforms baselines on a large dataset with five programming languages and can boost existing Seq2Seq models in commit message generation.

Copied to clipboard

Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Guozhi Wang, Dingyu Zhang, Shuai Ren, Hongsheng Li

Challenge:	a new dataset is being developed to improve the capabilities of mobile GUI-control agents.
Approach:	They propose a dataset designed for generalist mobile GUI-control agents . they use screenshots from popular mobile applications to create a detailed GUI-annotated dataset .
Outcome:	The Android Multi-annotation EXpo (AMEX) is a large-scale dataset for generalist mobile GUI-control agents . it includes screenshots from popular mobile applications, which are annotated at multiple levels .

Taxonomy-guided Semantic Indexing for Academic Paper Search (2024.emnlp-main)

Copied to clipboard

SeongKu Kang, Yunyi Zhang, Pengcheng Jiang, Dongha Lee, Jiawei Han, Hwanjo Yu

Adversarial Attack against Cross-lingual Knowledge Graph Alignment (2021.emnlp-main)

Challenge:	Academic paper search often struggles to match underlying academic concepts between queries and documents.
Approach:	They propose a framework that extracts key concepts from papers and organizes them as a semantic index guided by an academic taxonomy.
Outcome:	The proposed framework can be flexibly employed to enhance existing retrieval frameworks.

Copied to clipboard

Zeru Zhang, Zijie Zhang, Yang Zhou, Lingfei Wu, Sixing Wu, Xiaoying Han, Dejing Dou, Tianshi Che, Da Yan

Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking (2025.findings-emnlp)

Challenge:	Existing studies on cross-lingual entity alignment under adversarial attacks have not been conducted.
Approach:	They propose to use adversarial attack techniques to perturb cross-lingual entity alignment under adversarials.
Outcome:	The proposed model hides the attacked entities in dense regions in two KGs, and reduces the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness.

Copied to clipboard

Yunyi Zhang, Ruozhen Yang, Siqi Jiao, SeongKu Kang, Jiawei Han

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)

Challenge:	Recent studies also use large language models (LLMs) for query understanding, but these methods lack grounding in corpus-specific knowledge and may generate unreliable or unfaithful content.
Approach:	They propose a paper retrieval framework that combines large language models (LLMs) with a concept-based semantic index to capture scientific concepts.
Outcome:	The proposed framework improves the performance of various base retrievers, surpasses strong existing LLM-based baselines, and remains highly efficient.

Copied to clipboard

Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong

Open Hierarchical Relation Extraction (2021.naacl-main)

Challenge:	Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models.
Approach:	They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training.
Outcome:	The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance.

Copied to clipboard

Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

FocusLLM: Precise Understanding of Long Context by Dynamic Condensing (2025.acl-long)

Challenge:	Existing OpenRE methods cast different relation types in isolation without considering their hierarchical dependency.
Approach:	They propose a framework to establish bidirectional connections between OpenRE and relation hierarchies by integrating hierarchy information into relation representations.
Outcome:	The proposed framework outperforms state-of-the-art models on relation clustering and hierarchy expansion.

Copied to clipboard

Zhenyu Li, Yike Zhang, Tengyu Pan, Yutao Sun, Zhichao Duan, Junjie Fang, Rong Han, Zixuan Wang, Jianyong Wang

Challenge:	Existing context condensing methods cannot accurately understand the full context, as there is a considerable amount of information loss in the condensed process.
Approach:	They propose a framework to extend the fixed context length of any decoder-only LLM by distilling crucial information from long sequences.
Outcome:	The proposed framework extends the fixed context length of any decoder-only LLM, allowing it to focus on relevant information from very long sequences.

UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)

Copied to clipboard

Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph (2020.emnlp-main)

Challenge:	Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs .
Approach:	They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities.
Outcome:	The proposed method outperforms existing methods for benchmarking the uncertainty of large language models.

Copied to clipboard

Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei Zhang, Yichi Zhang, Hao Kong, Suhui Wu

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)

Challenge:	Existing reasoning methods for sparse KGs are incomplete and lack of evidential paths to target entities makes multi-hop reasoning difficult.
Approach:	They propose a multi-hop reasoning model over sparse KGs to solve this problem . they use latent prediction of embedding-based models to make the model perform more potential path search over sparses .
Outcome:	The proposed method outperforms state-of-the-art models on five datasets from Freebase, NELL and Wikidata.

Copied to clipboard

Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)

Challenge:	Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models.
Approach:	They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression.
Outcome:	Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution.

Copied to clipboard

Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, Tong Zhang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences.
Approach:	They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles.
Outcome:	The proposed method improves performance across reward objectives and targets.

A Quality-based Syntactic Template Retriever for Syntactically-Controlled Paraphrase Generation (2023.emnlp-main)

Copied to clipboard

Xue Zhang, Songming Zhang, Yunlong Liang, Yufeng Chen, Jian Liu, Wenjuan Han, Jinan Xu

EventKE: Event-Enhanced Knowledge Graph Embedding (2021.findings-emnlp)

Challenge:	Existing syntactically-controlled paraphrase generation models perform well with human-annotated or well-chosen syntaktic templates.
Approach:	They propose a quality-based Syntactic Template Retriever to retrieve templates based on the quality of the to-be-generated paraphrases.
Outcome:	The proposed algorithm can generate high-quality paraphrases without sacrificing quality.

Copied to clipboard

Zixuan Zhang, Hongwei Wang, Han Zhao, Hanghang Tong, Heng Ji

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)

Challenge:	Experimental results show that events can greatly improve the quality of KG embeddings on multiple downstream tasks.
Approach:	They propose an event-enhanced KG embedding model that incorporates events into KGs . they first incorporate event nodes by building a heterogeneous network with event argument links .
Outcome:	The proposed model incorporates event nodes into the original knowledge graphs . it can be used to fuse event information into the KG embeddings on multiple tasks .

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage (2026.acl-long)

Challenge:	Recent studies have discussed its capability to assist language models for various applications.
Approach:	They propose a structure to organize arguments using the Hierarchical Argumentation Graph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information.
Outcome:	The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models.

Copied to clipboard

Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Challenge:	Efficient reproduction of research papers requires deep domain expertise.
Approach:	They propose a framework that systematically mines implicit knowledge from the cited literature to reproduce experimental code in a complete, end-to-end manner.
Outcome:	The proposed framework surpasses baselines across all metrics and reproduces experimental code in a complete, end-to-end manner.

Ask Question First for Enhancing Lifelong Language Learning (2022.coling-1)

Copied to clipboard

Han Wang, Ruiliu Fu, Xuejun Zhang, Jun Zhou, Qingwei Zhao

Challenge:	Existing approaches to stream learning NLP tasks suffer from catastrophic forgetting and are exacerbated when the previous task’s pseudo data is insufficient.
Approach:	They propose to use a new data format to train pseudo questions of previous tasks to stream learning NLP tasks while retaining knowledge of previous ones.
Outcome:	The proposed model is more robust to sufficient and insufficient pseudo-data when the task boundary is both clear and unclear.

Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models (2026.acl-long)

Copied to clipboard

Boyan Han, Yiwei Wang, Yi Song, Yujun Cai, Chi Zhang

RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor (2023.emnlp-demo)

Challenge:	Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation . fixed anchors can enforce constraints, but they often impose rigid spans, leading to truncated reasoning .
Approach:	They propose a method that dynamically estimates end-anchor positions to adjust generation length before iterative infilling.
Outcome:	The proposed method improves format compliance and answer accuracy on GSM8K and MATH.

Copied to clipboard

Khanh Duy Nguyen, Zixuan Zhang, Reece Suchocki, Sha Li, Martha Palmer, Susan Windisch Brown, Jiawei Han, Heng Ji

Robust and Scalable Model Editing for Large Language Models (2024.lrec-main)

Challenge:	Existing IE tools for atomic events are limited when applied to such complex events.
Approach:	They propose to use event schemas to guide the organization of complex events and to edit hierarchical graphs.
Outcome:	The proposed tool outperforms existing IE visualization tools in both IE result analysis and general model improvements.

Copied to clipboard

Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun

TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data (2022.emnlp-main)

Challenge:	Existing methods that ignore contextual knowledge fail to reliably fall back to parametric knowledge when presented with irrelevant context.
Approach:	They propose to use contextual knowledge to update and correct LLMs' knowledge by in-context editing instead of retraining.
Outcome:	The proposed method outperforms current state-of-the-art methods by a large margin on a dataset that contains irrelevant questions.

Copied to clipboard

Fan Zhou, Mengkang Hu, Haoyu Dong, Zhoujun Cheng, Fan Cheng, Shi Han, Dongmei Zhang

A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)

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.

Copied to clipboard

Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li

Improving Model Factuality with Fine-grained Critique-based Evaluator (2025.acl-long)

Challenge:	Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps.
Approach:	They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement.
Outcome:	The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps.

Copied to clipboard

Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang

Multi 3 WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (2023.tacl-1)

Challenge:	Factuality evaluation aims to detect factual errors produced by language models and guide the development of more factual models.
Approach:	They propose a framework that leverages FenCE to improve the factuality of LM generators by constructing training data.
Outcome:	The proposed framework improves the factuality of LM generators by enhancing their training data.

Copied to clipboard

Songbo Hu, Han Zhou, Mete Hergul, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Ivan Vulić, Anna Korhonen

LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)

Challenge:	Task-oriented dialog (TOD) is one of the central objectives, hallmarks, and applications of machine intelligence.
Approach:	They propose a multilingual, multi-domain, multiparallele ToD dataset that offers culturally adapted dialogs in 4 languages for training and evaluation of multilingual and cross-lingual systems.
Outcome:	The proposed dataset is large-scale and culturally adapted to enable training and evaluation of multilingual and cross-lingual ToD systems.

Copied to clipboard

Kaibo Liu, Zhenpeng Chen, Yiyang Liu, Jie M. Zhang, Mark Harman, Yudong Han, Yun Ma, Yihong Dong, Ge Li, Gang Huang

Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events (2025.acl-long)

Challenge:	TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites .
Approach:	They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs .
Outcome:	The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification .

Copied to clipboard

Priyanka Kargupta, Yunyi Zhang, Yizhu Jiao, Siru Ouyang, Jiawei Han

DSQG-Syn: Synthesizing High-quality Data for Text-to-SQL Parsing by Domain Specific Question Generation (2025.findings-naacl)

Challenge:	State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events.
Approach:	They propose a task which identifies episodes within a news corpus of key event articles.
Outcome:	The proposed framework achieves 59.2% gain across all metrics compared to baselines.

Copied to clipboard

Shaoming Duan, Youxuan Wu, Chuanyi Liu, Yuhao Zhang, Zirui Wang, Peiyi Han, Shengyuan Yu, Liang Yan, Yingwei Liang

PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study (2024.emnlp-main)

Challenge:	Existing methods for generating SQL queries using natural language questions produce inconsistent NLQ-SQL pairs.
Approach:	They propose a text-to-SQL data synthesis framework that generates domain-relevant questions . they synthesize NLQ-SqL pairs that are domain-specific and intent-consistent .
Outcome:	The proposed method outperforms closed-source LLMs on the Text-to-SQL task.

Copied to clipboard

Yuqing Zhang, Baoyi He, Yihan Chen, Hangqi Li, Han Yue, Shengyu Zhang, Huaiyong Dou, Junchi Yan, Zemin Liu, Yongquan Zhang, Fei Wu

A Teacher-Student Framework for Maintainable Dialog Manager (D18-1)

Challenge:	philology requires years of professional training in extensive knowledge memorization and manual textual retrieval.
Approach:	They curated the PhiloCorpus-ZH, a rich collec-tion of ancient Chinese texts spanning a millennium with 30 diverse topics, including firsthand folk copies.
Outcome:	The PhiloCorpus-ZH corpus facilitated the development of the first LLM tailored for discovering ancient Chinese manuscripts.

Copied to clipboard

Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Chengqing Zong, Zhifei Li

Natural Language Interfaces

Challenge:	Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems . but extending RL-based systems to handle new intents and slots requires a system redesign .
Approach:	They propose a teacher-student framework to extend RL-based dialog systems . they propose to specify constraints held in the new dialog manager .
Outcome:	The proposed framework makes no assumption about unsupported intents and slots, making it possible to improve RL-based systems incrementally.

TopViewRS: Vision-Language Models as Top-View Spatial Reasoners (2024.emnlp-main)

Copied to clipboard

Chengzu Li, Caiqi Zhang, Han Zhou, Nigel Collier, Anna Korhonen, Ivan Vulić

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Challenge:	Top-view perspective is a typical way in which humans read and reason over different types of maps, but spatial reasoning capabilities of modern VLMs in this setup remain unattested and underexplored.
Approach:	They introduce a top-view spatial reasoning dataset and use it to evaluate VLMs across 4 perception and reasoning tasks with different levels of complexity.
Outcome:	The proposed model can understand and reason over spatial relations from the top view and can be controlled at different granularities of spatial reasoning.

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)

Copied to clipboard

Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, Tong Zhang

Explainability & Interpretability in NLP

Challenge:	Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences.
Approach:	They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data.
Outcome:	The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark .

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Jiahuan Zhang, Shunwen Bai, Tianheng Wang, KaiWen Guo, Zijia Song, Hanqing WU, Guozheng Rao, Kai Han, Kaicheng Yu

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026.findings-acl)

Challenge:	Existing benchmarks explore aspects of threedimensional spatial reasoning and visual-language reasoning in dynamic environments, but they are unable to perform well on 3D spatial deformation reasoning.
Approach:	They propose to use a ladder competition format to assess the model's spatial deformation reasoning abilities to determine its performance.
Outcome:	The proposed framework assesses the performance of Vision-Language Models in spatial deformation reasoning tasks.

Copied to clipboard

Jiaqi Weng, Han Zheng, Hanyu Zhang, Ej Zhou, Qinqin He, Jialing Tao, Hui Xue, Zhixuan Chu, Xiting Wang

Explainability & Interpretability in NLP

Challenge:	Existing studies on how SAEs derive most fine-grained latent features for safety remain unexplored.
Approach:	They propose a framework for interpreting SAE features in safety-critical domains . they train a suite of SAEs with human-readable explanations and systematic evaluations based on pornography, politics, violence, and terror .
Outcome:	The proposed framework reduces interpretation cost by 55% and improves safety-critical features.

Understanding the Dark Side of LLMs’ Intrinsic Self-Correction (2025.acl-long)

Copied to clipboard

Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang, Ke Xu, Hewu Li, Liu Yan, Han Qiu

Challenge:	Recent studies show that LLMs’ intrinsic self-correction fails without oracle labels as feedback.
Approach:	They propose to use one simple task and three complex tasks with state-of-the-art LLMs like ChatGPT, Llama, and DeepSeek to interpret LLM's intrinsic self-correction.
Outcome:	The proposed methods reveal the dark side of LLMs’ intrinsic self-correction for different tasks, especially for those failure cases.

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Copied to clipboard

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu

FTibSuite: A Comprehensive Resource Suite for Tibetan Vision–Language Modeling (2026.findings-acl)

Challenge:	Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach:	They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome:	a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .

Copied to clipboard

Guixian Xu, Yide Liang, Zeli Su, Xuexian Song, Ziyin Zhang, Yushuang Dong, Ting Zhang, Xu Han

Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Challenge:	FTibSuite provides an end-to-end training-and-evaluation workflow for vision–language models . Tibetan is underserved due to the lack of infrastructure for reproducible training and evaluation.
Approach:	They propose a resource-centric workflow for Tibetan VLMs that provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.
Outcome:	FTibSuite provides an end-to-end training-and-evaluation workflow and human-verified multimodal annotations.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach:	They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome:	The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

Visual Question Decomposition on Multimodal Large Language Models (2024.findings-emnlp)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Haowei Zhang, Jianzhe Liu, Zhen Han, Shuo Chen, Bailan He, Volker Tresp, Zhiqiang Xu, Jindong Gu

Quantize What Counts: More for Keys, Less for Values (2026.findings-acl)

Challenge:	Existing methods for question decomposition focus on unimodal language models, but question decomposing capability of Multimodal Large Language Models (MLLMs) has yet to be explored.
Approach:	They propose a finetuning dataset and a training objective for selective decomposition to enhance the model's question decomposing capability.
Outcome:	The proposed dataset shows that existing models struggle to produce high-quality sub-questions.

Copied to clipboard

Mohsen Hariri, Alan Luo, Weicong Chen, Tianyi Zhang, Qifan Wang, Xiaotian Han, Vipin Chaudhary

Challenge:	Empirical evaluations across various prominent LLMs and benchmarks show that key-favored allocations retain up to 98.3% accuracy compared to uniform allocations (e.g., 4-bit keys, 2-bit values).
Approach:	They propose two theorems that anchor mixed-precision KV quantization in the intrinsic geometry of Transformer models.
Outcome:	Empirical evaluations show that key-favored allocations retain up to 98.3% accuracy while conserving memory.

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Copied to clipboard

Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding. (2026.findings-acl)

Challenge:	Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach:	They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome:	The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Copied to clipboard

ZhaoYang Han, Qihan Lin, Hao Liang, Bowen Chen, Zhou Liu, Wentao Zhang

Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia (2025.acl-long)

Challenge:	LongInsightBench is the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements.
Approach:	They propose a benchmark to assess models’ ability to understand long videos with a focus on human language, viewpoints, actions, and other contextual elements.
Outcome:	The proposed model excels in three key areas: a) long-duration, human-centric videos; b) diversifying and challenging task scenarios; c) quality assurance pipeline; and d) reliability.

Copied to clipboard

Samuel Cahyawijaya, Holy Lovenia, Joel Ruben Antony Moniz, Tack Hwa Wong, Mohammad Rifqi Farhansyah, Thant Thiri Maung, Frederikus Hudi, David Anugraha, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Amit Agarwal, Joseph Marvin Imperial, Hitesh Laxmichand Patel, Vicky Feliren, Bahrul Ilmi Nasution, Manuel Antonio Rufino, Genta Indra Winata, Rian Adam Rajagede, Carlos Rafael Catalan, Mohamed Fazli Mohamed Imam, Priyaranjan Pattnayak, Salsabila Zahirah Pranida, Kevin Pratama, Yeshil Bangera, Adisai Na-Thalang, Patricia Nicole Monderin, Yueqi Song, Christian Simon, Lynnette Hui Xian Ng, Richardy Lobo Sapan, Taki Hasan Rafi, Bin Wang, null Supryadi, Kanyakorn Veerakanjana, Piyalitt Ittichaiwong, Matthew Theodore Roque, Karissa Vincentio, Takdanai Kreangphet, Phakphum Artkaew, Kadek Hendrawan Palgunadi, Yanzhi Yu, Rochana Prih Hastuti, William Nixon, Mithil Bangera, Adrian Xuan Wei Lim, Aye Hninn Khine, Hanif Muhammad Zhafran, Teddy Ferdinan, Audra Aurora Izzani, Ayushman Singh, Evan Evan, Jauza Akbar Krito, Michael Anugraha, Fenal Ashokbhai Ilasariya, Haochen Li, John Amadeo Daniswara, Filbert Aurelian Tjiaranata, Eryawan Presma Yulianrifat, Can Udomcharoenchaikit, Fadil Risdian Ansori, Mahardika Krisna Ihsani, Giang Nguyen, Anab Maulana Barik, Dan John Velasco, Rifo Ahmad Genadi, Saptarshi Saha, Chengwei Wei, Isaiah Edri W. Flores, Kenneth Chen Ko Han, Anjela Gail D. Santos, Wan Shen Lim, Kaung Si Phyo, Tim Santos, Meisyarah Dwiastuti, Jiayun Luo, Jan Christian Blaise Cruz, Ming Shan Hee, Ikhlasul Akmal Hanif, M.Alif Al Hakim, Muhammad Rizky Sya’ban, Kun Kerdthaisong, Lester James Validad Miranda, Fajri Koto, Tirana Noor Fatyanosa, Alham Fikri Aji, Jostin Jerico Rosal, Jun Kevin, Robert Wijaya, Onno P. Kampman, Ruochen Zhang, Börje F. Karlsson, Peerat Limkonchotiwat

Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable (2021.findings-emnlp)

Challenge:	Southeast Asia is underrepresented in vision-language research . SEA-VL is an open-source initiative dedicated to developing culturally relevant datasets for SEA languages.
Approach:	They propose to use crowdsourced, automated image crawling and synthetic image generation to develop culturally relevant datasets for SEA languages.
Outcome:	The proposed datasets capture SEA cultural nuances and contexts better than existing datasets.

Copied to clipboard

Ruiliu Fu, Han Wang, Xuejun Zhang, Jun Zhou, Yonghong Yan

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the reasoning process.
Approach:	They propose a three-stage framework based on complex question decomposition that decomposes the complex question, then reads the sub-questions and then performs numerical comparison to get the final answer.
Outcome:	The proposed framework achieves state-of-the-art in the 2WikiMultiHopQA dataset, with a winning joint F1 score of 53.58 on the leaderboard.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

Chem-FINESE: Validating Fine-Grained Few-shot Entity Extraction through Text Reconstruction (2024.findings-eacl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Qingyun Wang, Zixuan Zhang, Hongxiang Li, Xuan Liu, Jiawei Han, Huimin Zhao, Heng Ji

MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages (2026.findings-acl)

Challenge:	Existing frameworks for fine-grained few-shot entity extraction are difficult to implement in the chemical domain due to the information overload of scientific papers.
Approach:	They propose a sequence-to-sequence based few-shot entity extraction approach . it uses a seq2seq entity extractor and a self-validation module to reconstruct original input sentence .
Outcome:	The proposed framework achieves 8.26% and 6.84% performance gains on two datasets.

Copied to clipboard

Wenhan Han, Yifan Zhang, Zhixun Chen, null Binbinliu, Mykola Pechenizkiy, Meng Fang, Yin Zheng

BMCook: A Task-agnostic Compression Toolkit for Big Models (2022.emnlp-demos)

Challenge:	Existing evaluation datasets lack cross-lingual alignment, leaving assessments of multilingual capabilities fragmented in both language and skill coverage.
Approach:	They propose to use multilingual consistency as a complementary metric to assess performance bottlenecks and guide model improvement.
Outcome:	The proposed model lacks cross-lingual alignment and language coverage gaps between state-of-the-art models.

Copied to clipboard

Zhengyan Zhang, Baitao Gong, Yingfa Chen, Xu Han, Guoyang Zeng, Weilin Zhao, Yanxu Chen, Zhiyuan Liu, Maosong Sun

LawBench: Benchmarking Legal Knowledge of Large Language Models (2024.emnlp-main)

Challenge:	Existing efforts to compress medium-sized models for specific tasks have limited results.
Approach:	They propose a task-agnostic compression toolkit for big models that implements quantization, pruning, distillation and MoEfication methods.
Outcome:	The proposed tool improves performance on a model with 3 billion parameters by 12x . it also outperforms the original model on three typical NLP benchmarks.

Copied to clipboard

Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Alan Huang, Songyang Zhang, Kai Chen, Zhixin Yin, Zongwen Shen, Jidong Ge, Vincent Ng

NAT: Enhancing Agent Tuning with Negative Samples (2025.naacl-long)

Challenge:	LegalBench evaluated 20 LLMs in 162 legal tasks in 20 countries and jurisdictions.
Approach:	They present a comprehensive evaluation of 21 popular Large Language Models and the first comparative analysis of the empirical results.
Outcome:	The proposed benchmarks are based on the Bloom’s cognitive taxonomy and are compared to 21 popular LLMs.

Copied to clipboard

Renxi Wang, Xudong Han, Yixuan Zhang, Timothy Baldwin, Haonan Li

Challenge:	Existing methods for fine-tuning and reinforcement learning use only positive examples, limiting their efficiency in low-resource scenarios.
Approach:	They propose a method that leverages both successful and failed trajectories for fine-tuning, maximizing the utility of limited resources.
Outcome:	The proposed method surpasses existing methods, including SFT, DPO, and PPO, across various tasks.

Empower Entity Set Expansion via Language Model Probing (2020.acl-main)

Copied to clipboard

Yunyi Zhang, Jiaming Shen, Jingbo Shang, Jiawei Han

HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation (2022.acl-long)

Challenge:	Existing methods for expanding seed entities with new entities belong to the same semantic class are difficult to implement and can lead to accumulative errors.
Approach:	They propose an iterative set expansion framework that leverages automatically generated class names to address the semantic drift issue.
Outcome:	The proposed framework generates high-quality class names and outperforms state-of-the-art methods significantly.

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, Dongmei Zhang

Natural Language Interfaces

Challenge:	Existing studies on table reasoning focus on flat tables and hierarchical tables . a new dataset, HiTab, aims to examine numerical reasoning over hierarchic tables based on hierarchically structured tables - a strong challenge for existing baselines and a valuable benchmark for future research.
Approach:	They propose a hierarchical question answering and natural language generation dataset to study hierarchic tables.
Outcome:	The proposed model shows that it is effective in QA and natural language generation over hierarchical tables.

ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2025.findings-acl)

Copied to clipboard

Xin Men, Mingyu Xu, Qingyu Zhang, Qianhao Yuan, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, Weipeng Chen

When Audio and Text Disagree: Revealing Text Bias in Large Audio-Language Models (2025.emnlp-main)

Challenge:	Recent studies have identified significant redundancy in large language models . quantization and pruning are two methods that reduce computational resources .
Approach:	They propose simple pruning methods that prune redundant layers based on their BI scores.
Outcome:	The proposed pruning methods demonstrate superior performance over previous pruning methods.

Copied to clipboard

Cheng Wang, Gelei Deng, Xianglin Yang, Han Qiu, Tianwei Zhang

Fair-CCD: Mitigating Bias in Large Language Models for Tabular Classification Through Context-Contrastive Decoding (2026.acl-long)

Challenge:	Large Audio-Language Models (LALMs) are augmented with the ability to perceive audio, but their reliability when faced with conflicting inputs remains largely unexplored.
Approach:	They examine how LALMs prioritize information when presented with inconsistent audio-text pairs.
Outcome:	The proposed models display a significant bias toward textual input when presented with inconsistent audio-text pairs.

Copied to clipboard

Donghan Liu, Han Sun, Zhaohui Wang, Qin Li, Min Zhang

PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models (2026.findings-acl)

Challenge:	Prior work to mitigate fairness issues often employs subjective demonstration selection, leading to low controllability and limited stability across different models and tasks.
Approach:	They propose to use in-context learning to insert social biases into large language models to create a structured and controllable representation of the relationship between sensitive attributes and predicted labels.
Outcome:	Extensive experiments show that Fair-CCD consistently improves fairness metrics without degrading task accuracy.

Copied to clipboard

Han Bao, Penghao Zhang, Yue Huang, Zhengqing Yuan, Yanchi Ru, SU Rui, Yujun Zhou, Xiangqi Wang, Kehan Guo, Nitesh V Chawla, Yanfang Ye, Xiangliang Zhang

CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) are increasingly integrated into real-world decision-making, but their ability to comprehend and reason about policy-related content remains underexplored.
Approach:	They propose a bilingual benchmark evaluating policy comprehension comprising 21K cases across a broad spectrum of policy areas.
Outcome:	The proposed model shows stronger performance on application-oriented policy tasks than on memorization or conceptual understanding, and yields the highest accuracy on structured reasoning tasks.

Copied to clipboard

Ensheng Shi, Yanlin Wang, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Hongbin Sun

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing (2024.emnlp-main)

Challenge:	Existing methods for code summarization do not capture rich information in ASTs . existing methods are labor-intensive and time-consuming to document code with good summaries manually.
Approach:	They propose a model that hierarchically splits and reconstructs ASTs by a neural network . they propose to use AST embeddings and a vanilla code token encoder to generate the model .
Outcome:	The proposed model splits and reconstructs ASTs into subtrees and then aggregates embeddings of subtreas to get the complete AST.

Copied to clipboard

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang

Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)

Challenge:	Existing methods to improve code generation from natural language descriptions are difficult due to complex structure, subtle bugs, and lack of supplementary contents.
Approach:	They propose a framework that enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement.
Outcome:	The proposed framework improves the quality of complex code generation on the DS-1000 and ClassEval datasets.

Copied to clipboard

Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning (2024.findings-emnlp)

Challenge:	Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability.
Approach:	They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain.
Outcome:	The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset.

Copied to clipboard

Jiaru Zou, Mengyu Zhou, Tao Li, Shi Han, Dongmei Zhang

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture (2025.naacl-long)

Challenge:	Recent advances in fine-tuning large language models have greatly enhanced their usage in domain-specific tasks.
Approach:	They propose a method which internalizes prompt knowledge during model fine-tuning to achieve efficient inference and save costs.
Outcome:	The proposed approach reduces input tokens by 90%, accelerates inference by 4.2 times, and reduces monetary inference costs by 88.3%.

Copied to clipboard

Jiayi Han, Liang Du, Hongwei Du, Xiangguo Zhou, Yiwen Wu, Yuanfang Zhang, Weibo Zheng, Donghong Han

PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)

Challenge:	balancing the training budget, downstream performance, and general capabilities of large language models remains a challenge in many applications.
Approach:	They propose a mixture of expert framework based on Soft LoRA and Identity Mixture . SLIM allows dynamic routing between LoRA adapters and identity layers .
Outcome:	The proposed framework reduces training cost while maintaining general capabilities . it can be open-sourced upon publication.

Copied to clipboard

Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Haorui Wang, Zhen Qin, Feng Han, Jialu Liu, Simon Baumgartner, Michael Bendersky, Chao Zhang

Accelerating Code Search with Deep Hashing and Code Classification (2022.acl-long)

Challenge:	Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs.
Approach:	They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
Outcome:	The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.

Copied to clipboard

Wenchao Gu, Yanlin Wang, Lun Du, Hongyu Zhang, Shi Han, Dongmei Zhang, Michael Lyu

Hypernymy Detection for Low-Resource Languages via Meta Learning (2020.acl-main)

Challenge:	Code search is to search reusable code snippets from source code corpus based on natural languages queries.
Approach:	They propose a method to accelerate code search with deep hashing and code classification by using deep hashes and code hash.
Outcome:	The proposed method can save 90% of retrieval time while preserving at least 99% of retrievals accuracy.

Copied to clipboard

Changlong Yu, Jialong Han, Haisong Zhang, Wilfred Ng

TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models (2025.acl-long)

Challenge:	Existing studies focus on monolingual hypernymy detection on high-resource languages, but few investigate low-resourced scenarios.
Approach:	They propose to combine high-resource languages to solve low-resourced hypernymy detection problem . they extensively compare three joint training paradigms and propose meta learning .
Outcome:	The proposed method significantly improves performance of extremely low-resource languages by preventing over-fitting on small datasets.

Copied to clipboard

Xinyi He, Yihao Liu, Mengyu Zhou, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang

AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Challenge:	Tabular data are crucial in many fields and their understanding by large language models (LLMs) under high parameter efficiency paradigm is important.
Approach:	They propose a module that uses 2D LoRA to encode low-rank information on cell positions to improve table serialization and representation of two-dimensional structured information within a one-dimensional sequence.
Outcome:	Experiments on four tabular-related datasets show that TableLoRA outperforms vanilla LoRA and surpasses table encoding methods tested in control.

Copied to clipboard

Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han

Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification (2026.findings-acl)

Challenge:	Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach:	They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome:	The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.

Copied to clipboard

Han Liu, Jiaqing Zhan, Zhichao Chen, Qin Zhang

Deep Reinforcement Learning for Entity Alignment (2022.findings-acl)

Challenge:	Existing models for text classification are based on encoder-only transformers and generative pre-trained transformers.
Approach:	They propose an uncertainty-aware contrastive sentence embedding approach that addresses language ambiguity and inter-class separability for a text classification task.
Outcome:	The proposed approach improves classification accuracy on public datasets compared with state-of-the-art methods.

Copied to clipboard

Lingbing Guo, Yuqiang Han, Qiang Zhang, Huajun Chen

Representation Learning

Challenge:	Entity alignment (EA) methods identify the aligned entities based on cosine similarity, ignoring the semantics underlying the embeddings themselves.
Approach:	They propose to model entity alignment as a sequential decision-making task where an agent sequentially decides whether two entities are matched or mismatched based on representation vectors.
Outcome:	The proposed framework consistently advances the performance of several state-of-the-art methods, with a maximum improvement of 31.1% on Hits@1.

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

Copied to clipboard

Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

Can LLM Graph Reasoning Generalize beyond Pattern Memorization? (2024.findings-emnlp)

Challenge:	Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach:	They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome:	The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.

Copied to clipboard

Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, Yulia Tsvetkov

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Challenge:	Existing studies seek to enhance the graph reasoning capabilities of Large Language Models (LLMs) by specialized instruction tuning.
Approach:	They propose to evaluate LLM graph reasoning generalization using in-distribution settings . they propose to use three strategies to improve LLM generalization .
Outcome:	The proposed benchmark evaluates LLM graph reasoning generalization with in-distribution settings only . it shows that LLMs struggle to generalize across reasoning and real-world patterns .

Copied to clipboard

Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

VIEWS: Entity-Aware News Video Captioning (2024.emnlp-main)

Challenge:	Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach:	They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome:	The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.

Copied to clipboard

Hammad Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin, Mingda Zhang, Anurag Arnab, Feng Han, Yukun Zhu, Xuande Feng, Kevin Zhang, Jialu Liu, Shih-Fu Chang

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing video captioning benchmarks and models produce generic captions for videos that lack specific identification of individuals, locations, or organizations.
Approach:	They propose a task of directly summarizing news videos into captions that are entity-aware . they validate the effectiveness of their approach across three video captioning models .
Outcome:	The proposed approach is effective across three video captioning models.

Copied to clipboard

Dezhang Kong, Hujin Peng, Yilun Zhang, Lele Zhao, Zhenhua Xu, Shi Lin, Changting Lin, Meng Han

An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling (2021.findings-emnlp)

Challenge:	Large Language Model (LLM)-driven multi-agent systems (MAS) are rapidly gaining popularity, and its inherent security risks are rapidly becoming a concern.
Approach:	They propose a novel attack manipulating unique structures of web links to deceive MAS by using homoglyph deception, sub-directory nesting, and parameter obfuscation.
Outcome:	The proposed attacks exploit unique structures of web links to deceive MAS . they exhibit significant destructive potential across different MAS architectures .

Copied to clipboard

Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao, Xianchao Zhang

TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval (2026.acl-long)

Challenge:	Intent classification and slot filling are key building blocks in task-oriented dialogue systems.
Approach:	They propose an explicit-joint and supervised-contrastive learning framework for few-shot intent classification and slot filling.
Outcome:	The proposed model extracts intent and slot representations via bidirectional interactions and extends prototypical network to achieve explicit-joint learning.

Copied to clipboard

Yuhang Zhang, Keyan Ding, Peilin Chen, Han Liu, Can Lin, Ruixi Chen, Shiqi Wang, Qi Song

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)

Challenge:	Existing approaches to enzyme–reaction retrieval suffer from poor generalization across tasks and distributions . TIGER is a text-informed generalized enzyme-reaction retrieval framework that bridges enzymes and biochemical reactions.
Approach:	They propose a text-informed generalized enzyme-reaction retrieval framework that leverages protein-to-text generation models to distill textual knowledge from enzyme sequences.
Outcome:	The proposed framework outperforms state-of-the-art methods in enzyme–reaction retrieval tasks and distributions.

Copied to clipboard

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models (2024.emnlp-main)

Challenge:	Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization.
Approach:	They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative.
Outcome:	The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains.

Copied to clipboard

Xinrong Zhang, Yingfa Chen, Shengding Hu, Xu Han, Zihang Xu, Yuanwei Xu, Weilin Zhao, Maosong Sun, Zhiyuan Liu

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024.findings-acl)

Challenge:	Large language models (LLMs) are increasingly permeating daily lives and require real-time interactions that mirror human conversations.
Approach:	They propose to use time-division-multiplexing to process queries and responses pseudo-simultaneously.
Outcome:	The proposed model can listen to users while generating output and adjust to provide instant feedback.

Copied to clipboard

Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han

Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing studies suggest augmenting LLMs with external text corpora to alleviate hallucination problems.
Approach:	They propose to augment large language models with text units retrieved from external knowledge corpora to alleviate the issue.
Outcome:	The proposed framework outperforms baselines on GRBench with three LLMs and shows that iterative reasoning outperformed the baselines.

Copied to clipboard

Yan Liu, Feng Zhang, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Han Liu, Yangdong Deng

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder (2022.emnlp-main)

Challenge:	Existing approaches to mitigate inference inefficiency and optimization difficulty are fragmented and constrained by inherent trade-offs.
Approach:	They propose a framework that reconceptualizes discrete reasoning steps as a continuous probabilistic flow, quantifying the contribution of each step toward the ground-truth answer.
Outcome:	The proposed framework achieves a superior balance between inference efficiency and reasoning performance on challenging benchmarks.

Copied to clipboard

Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua Li

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Challenge:	Existing work reserves the principle dimensions of query and document embeddings for building more efficient retrieval systems.
Approach:	They propose to use Conditional Autoencoder to compress high-dimensional embeddings to maintain the same embeddable distribution and better recover ranking features.
Outcome:	The proposed algorithm achieves comparable ranking performance with its teacher model and makes the retrieval system more efficient.

Copied to clipboard

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs (2024.acl-demos)

Challenge:	Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach:	They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome:	The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.

Copied to clipboard

Chaoqun He, Renjie Luo, Shengding Hu, Ranchi Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Is Compound Aspect-Based Sentiment Analysis Addressed by LLMs? (2024.findings-emnlp)

Challenge:	Existing evaluation platforms are complex and poorly modularized, hindering seamless incorporation into researcher’s workflows.
Approach:	They propose a lightweight evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency that integrates models, data, and metrics into a unified evaluation workflow.
Outcome:	The proposed evaluation framework is lightweight, comprehensive, modular, and efficient.

Copied to clipboard

Yinhao Bai, Zhixin Han, Yuhua Zhao, Hang Gao, Zhuowei Zhang, Xunzhi Wang, Mengting Hu

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) aims to predict aspect-based elements from text . large language models (LLMs) have impressive abilities in handling human instructions .
Approach:	They propose a framework to evaluate LLMs' ability to handle complex ABSA tasks . they use constrained prompts to automatically organize the returned predictions .
Outcome:	The proposed framework outperforms supervised methods in some cases, but it is still lacking in other areas.

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)

Copied to clipboard

Han Xia, Songyang Gao, Qiming Ge, Zhiheng Xi, Qi Zhang, Xuanjing Huang

Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability.
Approach:	They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses.
Outcome:	The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences.

Copied to clipboard

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Challenge:	Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models.
Approach:	This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy .
Outcome:	The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications.

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules (2023.findings-emnlp)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

Chaojun Xiao, Yuqi Luo, Wenbin Zhang, Pengle Zhang, Xu Han, Yankai Lin, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

A Unified Taxonomy-Guided Instruction Tuning Framework for Entity Set Expansion and Taxonomy Expansion (2025.findings-acl)

Challenge:	Large language models (LLMs) have been successful on NLP tasks but require huge parameter sizes and computational resources.
Approach:	They propose a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins.
Outcome:	The proposed method saves 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%.

Copied to clipboard

Yanzhen Shen, Yu Zhang, Yunyi Zhang, Jiawei Han

CloneMem: Benchmarking Long-Term Memory for AI Clones (2026.acl-long)

Challenge:	Existing studies view entity set expansion, taxonomy expansion, and seed-guided taxonomies as three separate tasks.
Approach:	They propose a taxonomy-guided instruction tuning framework to teach a large language model to generate siblings and parents for query entities.
Outcome:	The proposed framework outperforms baselines on multiple benchmark datasets.

Copied to clipboard

Sen Hu, Zhiyu Zhang, Yuxiang Wei, Xueran Han, Zhenheng Tang, Ronghao Chen, Huacan Wang

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning (2025.acl-long)

Challenge:	Existing memory benchmarks rely on user–agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories.
Approach:	They propose a benchmark for evaluating long-term memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years.
Outcome:	Experiments show that existing memory benchmarks struggle in this setting, highlighting open challenges for life-grounded personalized AI.

Copied to clipboard

Weijie Shi, Han Zhu, Jiaming Ji, Mengze Li, Jipeng Zhang, Ruiyuan Zhang, Jia Zhu, Jiajie Xu, Sirui Han, Yike Guo

Effective Long-Context Scaling of Foundation Models (2024.naacl-long)

Challenge:	Existing legal judgment prediction methods struggle with logical errors when conducting complex legal reasoning.
Approach:	They propose a method which enhances LJP reliability through step-wise verification and correction of the reasoning process.
Outcome:	The proposed model significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B.

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

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

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.

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context (2026.acl-long)

Challenge:	Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates.
Approach:	They propose a ranking-oriented induction model to learn personalized mapping function for each word.
Outcome:	The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages.

Copied to clipboard

Guangya Wan, Mingyang Ling, Xiaoqi Ren, Rujun Han, Sheng Li, Zizhao Zhang

Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)

Challenge:	Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents.
Approach:	They propose a framework that separates tactical execution, strategic oversight, and context organization into three specialized components.
Outcome:	The proposed framework improves accuracy by 20% relative to baselines on GAIA, BrowseComp, and Humanity’s Last Exam tasks.

Copied to clipboard

Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang

RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025.acl-long)

Challenge:	Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process.
Approach:	They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.
Outcome:	The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing.

Copied to clipboard

Hieu Tran, Zonghai Yao, Zhichao Yang, Junda Wang, Yifan Zhang, Shuo Han, null Feiyun Ouyang, Hong Yu

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Challenge:	Existing work aims to improve reasoning accuracy and factual integrity across large language models for knowledge-intensive tasks such as medical and commonsense reasoning.
Approach:	They propose a versatile extension to the mutual reasoning framework (rStar) that enhances reasoning accuracy and factual integrity across large language models.
Outcome:	The proposed extension to the mutual reasoning framework improves reasoning accuracy and factual integrity across large language models for complex, knowledge-intensive tasks.

Copied to clipboard

Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models (2025.coling-main)

Challenge:	Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach:	They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome:	The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .

Copied to clipboard

Han Han, Tong Zhu, Xiang Zhang, MengSong Wu, Xiong Hao, Wenliang Chen

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidance (2025.findings-emnlp)

Challenge:	Existing benchmarks on nested tool learning are lacking relevant data instances.
Approach:	They propose a method to construct large-scale nested tool calls with different nesting structures using a large-quality dataset.
Outcome:	The proposed method can be used to evaluate the nested tool learning abilities of large language models (LLMs) in real-world applications.

Copied to clipboard

Jingxian Xu, Mengyu Zhou, Weichang Liu, Hanbing Liu, Shi Han, Dongmei Zhang

Explanation Graph Generation via Generative Pre-training over Synthetic Graphs (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes, but this enhanced reasoning capability results in an increased number of output tokens during inference, leading to higher computational costs.
Approach:	They propose a method that internalizes explicit reasoning into the model’s habitual behavior through a Teacher-Guided compression strategy inspired by human cognition.
Outcome:	The proposed method reduces inference-time costs while maintaining high performance while preserving high quality and diversity of the distillation dataset.

Copied to clipboard

Han Cui, Shangzhan Li, Yu Zhang, Qi Shi

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Existing frameworks for explanation graph generation are limited due to the large number of datasets available.
Approach:	They propose a text-to-graph generative task to pre-train a model to bridge the text-graph gap.
Outcome:	The proposed framework surpasses all baseline systems with remarkable margins on ExplaGraphs and CommonsenseQA.

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data (2025.emnlp-main)

Copied to clipboard

Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang

Revisiting the Reliability of Language Models in Instruction-Following (2026.acl-long)

Challenge:	Existing literature suggests that RAG systems may face privacy issues when the retrieval process involves private data.
Approach:	They propose a two-stage synthetic data generation paradigm that uses attributes to preserve contextual information from the original data.
Outcome:	The proposed approach preserves key contextual information from the original data while reducing privacy risks.

Copied to clipboard

Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Chao Zhang, Han Qiu

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models (2025.acl-long)

Challenge:	Several benchmarks have been proposed to measure instruction-following accuracy, but these scores do not translate to reliable services in real-world use.
Approach:	They propose a new metric reliable@k and develop an automated pipeline to generate cousin prompts.
Outcome:	The proposed model can be instantiated with cousin prompts and generates high-quality cousin prompt data.

Copied to clipboard

Jingxuan Zhang, Zhenhua Xu, Rui Hu, Wenpeng Xing, Xuhong Zhang, Meng Han

On the Zero-Shot Generalization of Machine-Generated Text Detectors (2023.findings-emnlp)

Challenge:	Large Language Models (LLMs) have raised critical concerns about model ownership and intellectual property protection.
Approach:	They propose a method for effectively removing backdoor-based fingerprints from LLMs . they propose deleting backdoor fingerprints using a transferable erasure mechanism .
Outcome:	The proposed method removes backdoor-based fingerprints while maintaining model performance.

Copied to clipboard

Xiao Pu, Jingyu Zhang, Xiaochuang Han, Yulia Tsvetkov, Tianxing He

KET-QA: A Dataset for Knowledge Enhanced Table Question Answering (2024.lrec-main)

Challenge:	rampant proliferation of large language models generates text indistinguishable from human-written language.
Approach:	They train neural detectors on outputs of a new generator and test their performance on held-out generators.
Outcome:	The proposed detectors can be built on training data from medium-sized models.

Copied to clipboard

Mengkang Hu, Haoyu Dong, Ping Luo, Shi Han, Dongmei Zhang

Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training (2024.lrec-main)

Challenge:	Existing datasets that ignore the challenge of missing knowledge in TableQA are limited in their use.
Approach:	They propose to use a knowledge base as the external knowledge source for TableQA and construct a dataset with fine-grained gold evidence annotation.
Outcome:	The proposed model achieves remarkable performance improvements on three different settings, but still lags behind the human-level performance.

Copied to clipboard

Chaojun Xiao, Yutao Sun, Yuan Yao, Xu Han, Wenbin Zhang, Zhiyuan Liu, Maosong Sun

A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems (2023.emnlp-main)

Challenge:	Current methods conceptualize LAE as a supervised sentence-pair classification problem and necessitate extensive manual annotations.
Approach:	They propose a model that focuses on fine-grained alignment of argument pairs building upon coarse-grain complaint-defense pairs.
Outcome:	The proposed model outperforms baseline models by 3.7 and 2.4 points on average.

Copied to clipboard

Songbo Hu, Han Zhou, Moy Yuan, Milan Gritta, Guchun Zhang, Ignacio Iacobacci, Anna Korhonen, Ivan Vulić

Natural Language Interfaces

Challenge:	Existing systems trained for Arabic or Turkish using annotated data fully parallel to English ToD data still exhibit diminished ToD task performance.
Approach:	They define new quantitative measures of absolute and relative equivalence in system performance, capturing disparities across languages and within individual languages.
Outcome:	The proposed measures capture disparities across languages and within individual languages.

Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing (2021.acl-long)

Copied to clipboard

Liwen Zhang, Ge Wang, Wenjuan Han, Kewei Tu

LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition (2024.findings-acl)

Challenge:	Discourse dependency parsing is a task that requires a large amount of training data, but there is little research on it.
Approach:	They propose to adapt unsupervised syntactic dependency parsing methods for unsupervised discourse dependency parses using unlabeled training data.
Outcome:	The proposed methods outperform existing methods in semi-supervised and supervised settings and outperformed existing methods.

Copied to clipboard

Jinyuan Li, Han Li, Di Sun, Jiahao Wang, Wenkun Zhang, Zan Wang, Gang Pan

UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data (2026.acl-long)

Challenge:	Existing methods for Grounded Multimodal Named Entity Recognition (GMNER) lack a strong correlation between image-text pairs and is ungroundable.
Approach:	They propose a framework that reformulates GMNER into a joint MNER-VE-VG task by leveraging large language models as a connecting bridge.
Outcome:	The proposed framework outperforms state-of-the-art methods on the existing GMNER dataset and achieves absolute leads of 10.65%, 6.21%, and 8.83% in all three subtasks.

Copied to clipboard

Han Weng, Zhou Liu, Yuanfeng Song, Xiaoming Yin, Xing Chen, Wentao Zhang

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention (2026.acl-long)

Challenge:	Existing benchmarks do not assess agents’ capabilities across data types . Existing tools only evaluate agents' ability to extract reasonable insights across data formats.
Approach:	They propose a multi-source benchmark to evaluate the performance of data analytics agents in handling diverse data sources.
Outcome:	The proposed agent performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights.

Copied to clipboard

Ruizi Han, Miao Zhang, Ziyue Qiao, Liqiang Nie

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning (2024.findings-emnlp)

Challenge:	Efficient long-context inference remains a major challenge for large language models (LLMs), as the cost of attention computation during auto-regressive decoding grows linearly with the context length.
Approach:	They propose to model token importance as a dynamic process that evolves over decoding steps and propagates through model layers.
Outcome:	The proposed method outperforms baseline sparse attention methods and achieves speedups of up to 5.36 for attention latency and 2.33 for end-to-end decoding.

Copied to clipboard

Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He, Lun Du, Shi Han, Dongmei Zhang

RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions (2024.lrec-main)

Challenge:	Existing solutions for table reasoning tasks are mainly tested on small tables and face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections.
Approach:	They propose a table reasoning pre-processor suite that can be used to leverage large language models (LLMs) in table-based tasks.
Outcome:	The proposed method improves LLMs’ reasoning capabilities in various tabular tasks and enhances interaction between LLM and tabular data by employing effective pre-processing.

Copied to clipboard

Yuansen Zhang, Xiao Wang, Zhiheng Xi, Han Xia, Tao Gui, Qi Zhang, Xuanjing Huang

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in following human instructions and solving NLU tasks.
Approach:	They propose to use code style instructions to replace typically natural language instructions to provide more precise instructions and strengthen the robustness of LLMs.
Outcome:	The proposed method outperforms natural language models on eight robustness datasets and achieves an improvement of 5.68% in test set accuracy and a reduction of 5.66 points in Attack Success Rate (ASR).

Copied to clipboard

Siyu Yan, Long Zeng, Xuecheng Wu, Chengcheng Han, Kongcheng Zhang, Chong Peng, Xuezhi Cao, Xunliang Cai, Chenjuan Guo

LLM-Friendly Knowledge Representation for Customer Support (2025.coling-industry)

Challenge:	Existing defenses target single-turn attacks, but real-world usage involves multi-turn dialogues, exposing models to attacks that exploit conversational context to bypass safety measures.
Approach:	They propose a framework that tackles multi-turn jailbreaks from both attack and defense angles.
Outcome:	Experiments on large language models show that MUSE effectively mitigates multi-turn jailbreaks.

Copied to clipboard

Hanchen Su, Wei Luo, Yashar Mehdad, Wei Han, Elaine Liu, Wayne Zhang, Mia Zhao, Joy Zhang

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	a new approach to customer support is proposed to integrate large language models with a framework designed to navigate the complexities of Airbnb customer support operations.
Approach:	They propose a method for integrating Large Language Models with a framework designed to navigate the complexities of Airbnb customer support operations.
Outcome:	The proposed approach is cost-effective and improves customer support performance . it also allows human agents to focus on more complex issues, the authors show .

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing (2024.emnlp-industry)

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Copied to clipboard

Kang Chen, Qing Zhang, Chengbao Lian, Yixin Ji, Xuwei Liu, Shuguang Han, Guoqiang Wu, Fei Huang, Jufeng Chen

SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Challenge:	Unlike professional Business-to-Consumer (B2C) e-commerce platforms, consumer-to consumer (C2C), is mainly targeting individual sellers.
Approach:	They develop an intelligent product listing tool that generates product descriptions using various product attributes such as category, brand, color, condition, etc.
Outcome:	The proposed tool outperforms the base model in domain-specific tasks while producing less hallucination.

Copied to clipboard

Bo Zhang, Cong Gao, Linkang Yang, Bingxu Han, Minghao Hu, Zhunchen Luo, Guotong Geng, Xiaoying Bai, Jun Zhang, Wen Yao, Zhong Wang

Corpus-based Open-Domain Event Type Induction (2021.emnlp-main)

Challenge:	Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach:	They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome:	The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.

Copied to clipboard

Jiaming Shen, Yunyi Zhang, Heng Ji, Jiawei Han

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models (2025.findings-acl)

Challenge:	Existing event extraction methods require predefined event types and their annotations to learn event extractors.
Approach:	They propose to represent each event type as a cluster of predicate sense, object head> pairs.
Outcome:	The proposed method can discover salient and high-quality event types on three datasets from different domains.

Copied to clipboard

Yifu Qiu, Varun R. Embar, Yizhe Zhang, Navdeep Jaitly, Shay B Cohen, Benjamin Han

How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors (2026.findings-acl)

Challenge:	Existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts.
Approach:	They propose to use retrieval-attention-probing to filter and de-noise long contexts during decoding and joint retrieval head training alongside the generation head to improve LCLM performance.
Outcome:	The proposed approach outperforms RAG and GPT-4-Turbo on most tasks despite being a much smaller model.

Copied to clipboard

Kuai Yu, Naicheng Yu, Han Wang, Rui Yang, Huan Zhang

Complete Chess Games Enable LLM Become A Chess Master (2025.naacl-short)

Challenge:	Existing studies on the effect of environmental variation on web agents have focused on robustness to adversarial attacks with less attention to agents’ preferences in benign scenarios.
Approach:	They propose a controlled evaluation pipeline to quantify how visual attributes influence web-agent decision-making by comparing variants and browsing interactions.
Outcome:	Extensive experiments on 8 variant families, 5 real-world websites and 4 representative web agents show that background color contrast, item size, position, and card clarity have a strong influence on agents’ actions, whereas font styling, text color, and item image clarity exhibit minor effects.

Copied to clipboard

Yinqi Zhang, Xintian Han, Haolong Li, Kedi Chen, Shaohui Lin

Pru-CoT: Towards Efficient Reasoning Distillation via Pruning Chain-of-Thought (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown remarkable abilities in text generation, question answering, language translation, reasoning and many other tasks.
Approach:	They propose a Large language model that can play chess games by transforming a game into a textual format with the best move represented in the Forsyth-Edwards Notation.
Outcome:	The proposed model achieves professional-level Elo rating of 1788 in matches against the standard Elo-rated Stockfish when permitted to sample 10 times.

Copied to clipboard

Han Liu, Shuotian Ma, Hui Li, Xiaotong Zhang, Fenglong Ma, Hong Yu

SynthAgent: Adapting Web Agents with Synthetic Supervision (2026.acl-long)

Challenge:	Existing heuristics fail to capture global causal logic due to rigid rules and limited search spaces.
Approach:	They propose a framework that extracts the essential logical structure from reasoning chains.
Outcome:	Experiments show that Pru-CoT models generate more compact reasoning paths compared to models trained on verbose data.

Copied to clipboard

Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao

SQLAgent: Learning to Explore Before Generating as a Data Engineer (2026.findings-acl)

Challenge:	Existing studies have focused on synthetic supervision but have encountered data quality issues.
Approach:	They propose a fully synthetic supervision framework that aims at improving data quality via dual refinement of both tasks and trajectories.
Outcome:	The proposed framework outperforms existing methods on standardized benchmarks and shows promising results on a standardized test.

Copied to clipboard

Wenjia Jiang, Yiwei Wang, Boyan Han, Joey Tianyi Zhou, Chi Zhang

Adversarial Attack and Defense of Structured Prediction Models (2020.emnlp-main)

Challenge:	Existing approaches to large language models fail to generalize in complex, real-world settings due to database-specific nature of SQL reasoning.
Approach:	They propose a two-stage LLM-based framework that decouples knowledge acquisition from query generation.
Outcome:	The proposed framework significantly improves accuracy over baselines on large-scale benchmarks.

Copied to clipboard

Wenjuan Han, Liwen Zhang, Yong Jiang, Kewei Tu

A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows (2026.acl-industry)

Challenge:	Existing approaches to building effective adversarial attackers focus on classification problems.
Approach:	They propose a framework that learns to attack a structured prediction model with feedbacks from multiple reference models.
Outcome:	The proposed framework is able to attack state-of-the-art models and boost them with training . it is based on a sequence-to-sequence model with feedbacks from multiple reference models .

Copied to clipboard

Han Yuxuan, Yuanxing Zhang, Yushuo Wang, Yichao Jin

Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM (2024.findings-acl)

Challenge:	Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows.
Approach:	They propose a framework for structured information extraction from long, multilingual scanned financial documents . they combine image preprocessing, multilinguistic OCR, hybrid page-level retrieval and VLMs .
Outcome:	The proposed pipeline outperforms direct PDF-to-VLM baselines on 120 production KYC documents.

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Challenge:	Recent studies have focused on short dialogues, but mainly on short debates.
Approach:	They propose to use Large Language Models to construct an automated debate judge to evaluate multi-turn debates.
Outcome:	The proposed system improves on the PanelBench benchmark, which compares its performance to actual debate outcomes.

PIEClass: Weakly-Supervised Text Classification with Prompting and Noise-Robust Iterative Ensemble Training (2023.emnlp-main)

Copied to clipboard

Yunyi Zhang, Minhao Jiang, Yu Meng, Yu Zhang, Jiawei Han

Zero-Shot Open-Schema Entity Structure Discovery (2026.eacl-long)

Challenge:	Existing methods for text classification use label names of target classes as the only supervision.
Approach:	They propose a method that uses keyword-based keyword matching to generate pseudo labels . they propose 'pieclass' module that iteratively trains classifiers and updates pseudo labels.
Outcome:	The proposed method achieves better performance than existing strong baselines on seven benchmark datasets and similar performance to fully-supervised classifiers on sentiment classification tasks.

Copied to clipboard

Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth De Mel, Jiawei Han

New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)

Challenge:	Existing methods based on large language models (LLMs) rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results.
Approach:	They propose a novel approach to entity structure extraction that does not require any schema or annotated datasets.
Outcome:	Experiments show that ZOES improves LLMs’ ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method.

Copied to clipboard

Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang

Domain-Adaptive Pretraining Methods for Dialogue Understanding (2021.acl-short)

Challenge:	Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms.
Approach:	They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection .
Outcome:	The proposed framework outperforms large-scale models in detecting neologism toxicity.

Copied to clipboard

Han Wu, Kun Xu, Linfeng Song, Lifeng Jin, Haisong Zhang, Linqi Song

Enhancing Generalization in Natural Language Inference by Syntax (2020.findings-emnlp)

Challenge:	Recent advances in pretraining methods have achieved promising results on NLP tasks . however, it is unclear which pretraining objective is the most effective for each downstream task .
Approach:	They evaluate the effectiveness of domain-adaptive pretraining objectives on downstream tasks . they use open-domain data to pretrain language models like BERT and SpanBERT .
Outcome:	The proposed model improves on two dialogue understanding tasks with domain-adaptive pretraining objectives.

Copied to clipboard

Qi He, Han Wang, Yue Zhang

Multi-modal Action Chain Abductive Reasoning (2023.acl-long)

Challenge:	Pre-trained language models such as BERT have the state-of-the-art performance on natural language inference (NLI).
Approach:	They propose to use dependency trees to enhance generalization of BERT in a natural language inference task by leveraging on a graph convolutional network to represent a syntax-based matching graph with heterogeneous matching patterns.
Outcome:	The proposed method makes BERT more robust on syntactic changes.

Copied to clipboard

Mengze Li, Tianbao Wang, Jiahe Xu, Kairong Han, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Shiliang Pu, Fei Wu

InstructEd: Soft-Instruction Tuning for Model Editing with Hops (2024.findings-acl)

Challenge:	Existing models for Abductive Reasoning are limited in their ability to infer the most plausible explanation of incomplete known phenomena.
Approach:	They propose a vision-language task that aims to imagine the most plausible event by spatio-temporal grounding in past video and infer the hypothesis of subsequent action chain layer by layer.
Outcome:	The proposed model outperforms existing video-language models in terms of effectiveness on the proposed dataset.

Copied to clipboard

XiaoQi Han, Ru Li, Xiaoli Li, Jiye Liang, Zifang Zhang, Jeff Pan

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

Challenge:	Existing methods for model editing are limited due to excessive memorization and knowledge conflict issues.
Approach:	They propose to insert soft instructions into the attention module to facilitate interactions between instructions and questions and to understand and utilize new facts.
Outcome:	The proposed method achieves 10% improvement in one-hop (multi-hop) model editing on three datasets with LLaMAs and GPT2 .

Copied to clipboard

Xueru Wen, Jie Lou, Zichao Li, Yaojie Lu, XingYu XingYu, Yuqiu Ji, Guohai Xu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Debing Zhang

Challenge:	Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
Approach:	They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
Outcome:	The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)

Copied to clipboard

Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment (2026.findings-acl)

Challenge:	Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals.
Approach:	They propose a benchmark that simulates the dynamic evolution of memory in real-world projects.
Outcome:	The proposed benchmarks simulate the dynamic evolution of memory in real-world projects.

Copied to clipboard

Zhixue Song, Boyan Han, Yiwei Wang, Chi Zhang

Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets (2025.emnlp-main)

Challenge:	Recent advances in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images.
Approach:	They propose a strategy that decouples visual transcription from safety auditing by enforcing a serialized pipeline to decouple visual transcription and safety assessment.
Outcome:	The proposed strategy decouples visual transcription from safety auditing to reduce the risk of jailbreaking.

Copied to clipboard

Chenlin Liu, Minghui Fang, Patrick Zhang, Wei Zhou, Jie Gao, Jiqing Han

A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check (D18-1)

Challenge:	Existing mitigation strategies for Text-to-Speech systems require excessive training resources or inference latency.
Approach:	They propose a GFlOwNet-guided distribution AlignmenT framework that mitigates hallucinations without relying on massive resources or inference latency.
Outcome:	The proposed framework reduces over 50% character error rates and lowers uncertainty by up to 58% on challenging test cases.

Copied to clipboard

Dingmin Wang, Yan Song, Jing Li, Jialong Han, Haisong Zhang

Challenge:	Chinese spelling check (CSC) is a challenging but meaningful task that serves as a preprocessing in many natural language processing(NLP) applications.
Approach:	They propose to construct Chinese spelling check corpus with automatically generated spelling errors, which are either visually or phonologically resembled characters, corresponding to OCR- and ASR-based methods. Experimental results demonstrate the effectiveness of the approach.
Outcome:	The proposed method is based on visual or phonologically similar spelling errors, and is validated with respect to three standard test sets.

Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)

Copied to clipboard

Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang

Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers (2026.findings-acl)

Challenge:	Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs .
Approach:	They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful.
Outcome:	The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data.

Copied to clipboard

Zhiyang Zhang, Junda She, Kuo Cai, Bo Chen, Shiyao Wang, Xinchen Luo, Qiang Luo, Ruiming Tang, Han Li, Kun Gai, Guorui Zhou

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)

Challenge:	Existing methods for constructing item identifiers face bottlenecks due to their large output space and expensive vocabulary expansion and alignment training.
Approach:	They propose to use Large Language Models to develop general-purpose, semantically-aware recommender systems that can be generalized and reusable.
Outcome:	Experiments on real-world datasets show that GRAM outperforms baselines and significantly outperformed baselines.

Copied to clipboard

Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang

Experience-Driven Multi-Agent Optimization for Black-Box Jailbreak Attacks on Large Language Models (2026.findings-acl)

Challenge:	Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive.
Approach:	They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory .
Outcome:	The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient.

Copied to clipboard

Zhaoyang Han, Yihe Liu, Kai Zhang, Ping Li

MedINST: Meta Dataset of Biomedical Instructions (2024.findings-emnlp)

Challenge:	Existing methods for jailbreak have poor transferability and high sensitivity to preprocessing . EMJO provides an effective and scalable paradigm for systematic jailbreak optimization .
Approach:	They propose a model that couples agents into a closed-loop "probe–evaluate–revise” process . they propose EMJO, which can be query-efficient and transferable, under black-box access.
Outcome:	a new approach outperforms existing jailbreak baselines on diverse LLMs . it achieves up to 11% improvement in attack success rate while reducing query cost .

Copied to clipboard

Wenhan Han, Meng Fang, Zihan Zhang, Yu Yin, Zirui Song, Ling Chen, Mykola Pechenizkiy, Qingyu Chen

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining (2022.acl-long)

Challenge:	Medical data and tasks require extensive preprocessing and standardization for effective use in training LLMs.
Approach:	They propose to use MedINST as a meta-dataset to evaluate LLMs' generalization ability.
Outcome:	The meta-dataset of biomedical instruction measures the generalization ability of LLMs across multiple open-domain tasks.

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Ran Jia, Pengfei Wu, Shi Han, Fan Cheng, Dongmei Zhang

ECOLA: Enhancing Temporal Knowledge Embeddings with Contextualized Language Representations (2023.findings-acl)

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.

Copied to clipboard

Zhen Han, Ruotong Liao, Jindong Gu, Yao Zhang, Zifeng Ding, Yujia Gu, Heinz Koeppl, Hinrich Schütze, Volker Tresp

Reconstructing Capsule Networks for Zero-shot Intent Classification (D19-1)

Challenge:	Existing enhancement approaches cannot be applied to temporal knowledge graphs (tKGs) existing enhancement approaches assume knowledge embedding is time-independent, whereas entity embedded in tKG models evolves .
Approach:	They propose to use textual data to enhance temporal knowledge embedding by Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations (ECOLA) to evaluate ECOLA, they introduce three new datasets for training and evaluation.
Outcome:	The proposed model significantly improves Hits@1 on the link prediction task.

Copied to clipboard

Han Liu, Xiaotong Zhang, Lu Fan, Xuandi Fu, Qimai Li, Xiao-Ming Wu, Albert Y.S. Lam

TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models (2025.acl-industry)

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.

Copied to clipboard

Deyin Yi, Yihao Liu, Lang Cao, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang

When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models (2020.emnlp-main)

Challenge:	Tabular data analysis is crucial in many scenarios, yet its complexity and density can make it challenging to determine the most appropriate analysis operations for a new table.
Approach:	They propose a tabular data analysis framework that recommends query-code-result triplets for new tables . they propose Rec-Align, a method to further improve recommendation quality .
Outcome:	The proposed framework achieves 77.0% top-5 recommendation recall on a dataset designed for tabular data analysis recommendation.

Copied to clipboard

Changlong Yu, Jialong Han, Peifeng Wang, Yangqiu Song, Hongming Zhang, Wilfred Ng, Shuming Shi

The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucination (2025.findings-acl)

Challenge:	a taxonomy is a semantic hierarchy of words or concepts organized w.r.t. their hypernymy relationships.
Approach:	They propose a framework for hypernymy detection using large textual corpora . they quantify the non-negligible existence of specific sparsity cases .
Outcome:	The proposed framework quantifies the non-negligible existence of specific sparsity cases on several benchmark datasets.

Copied to clipboard

Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi R. Fung, Kathleen McKeown, ChengXiang Zhai, Manling Li, Heng Ji

Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models (2026.findings-acl)

Challenge:	Hallucination is a persistent challenge in large language models where even with rigorous quality control, models often generate distorted facts.
Approach:	They propose a new framework to quantify factual hallucinations by modeling knowledge overshadowing.
Outcome:	The proposed framework improves model factuality on Overshadow (27.9%), MemoTrap (13.1%) and NQ-Swap (18.3%).

Copied to clipboard

Shuhao Zhang, Yuli Chen, Jiale Han, Bo Cheng, Jiabao Ma

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models (2025.coling-main)

Challenge:	Existing detection methods for large language models rely on fixed strategies to steal watermarks.
Approach:	They propose a novel steal-based watermark algorithm that derives watermark information from watermarked texts to craft highly targeted adversarial attacks.
Outcome:	The proposed system significantly increases steal efficiency against target watermarks under identical conditions.

Copied to clipboard

Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, Changshui Zhang

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation (2022.findings-emnlp)

Challenge:	Existing large language models (LLMs) fail due to lack of knowledge or incorrect knowledge application.
Approach:	They propose a knowledge-augmented framework that constructs a formula set to provide explicit physics knowledge and utilizes checklists to guide effective knowledge application.
Outcome:	The proposed framework achieves state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.

Copied to clipboard

Han Zhang, Sheng Zhang, Yang Xiang, Bin Liang, Jinsong Su, Zhongjian Miao, Hui Wang, Ruifeng Xu

Defending Jailbreak Prompts via In-Context Adversarial Game (2024.emnlp-main)

Challenge:	Existing benchmarks for Continual Language Learning (CLL) are limited due to the complexity of the task and the lack of unified benchmarks.
Approach:	They propose a Continual Language Learning Evaluation benchmark CLLE in multilingual translation.
Outcome:	The proposed method is effective when compared with other strong benchmarks.

Copied to clipboard

Yujun Zhou, Yufei Han, Haomin Zhuang, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization (2026.acl-long)

Challenge:	Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications, but concerns regarding their security persist.
Approach:	They propose an adversarial game that leverages agent learning to extend knowledge to defend against jailbreaks.
Outcome:	The proposed game shows that LLMs safeguarded by ICAG exhibit significantly reduced jailbreak success rates across various attack scenarios.

Copied to clipboard

Weixu Zhang, Ye Yuan, Changjiang Han, Yuxing Tian, Zipeng Sun, Linfeng Du, Jikun Kang, Hong Kang, Xue Liu, Haolun Wu

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (2025.emnlp-main)

Challenge:	Large Language Models exhibit strong implicit personalization ability, but most approaches treat this behavior as a black box.
Approach:	They propose a mechanistic interpretation perspective and propose 'sparse' set of Preference Heads . they compute a Preference Contribution Score for each attention head and compare their predictions .
Outcome:	The proposed framework computes a Preference Contribution Score (PCS) for each attention head and measures its causal impact on user aligned outputs.

Copied to clipboard

Yan Li, Tianyi Zhang, Zechuan Li, Caren Han

Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation (2023.emnlp-main)

Challenge:	Existing solutions to problem of positional out-of-distribution (O.O.D.) are inefficient, redundant, and lack local positional information.
Approach:	They propose a training-free method that greedily reuses pretrained positional intervals and interpolates attention logits to eliminate outliers.
Outcome:	The proposed method achieves stable and superior performance across long-context tasks without requiring input-length-specific tuning.

Copied to clipboard

Tianqi Zhong, Quan Wang, Jingxuan Han, Yongdong Zhang, Zhendong Mao

MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning (2025.acl-long)

Challenge:	Controllable text generation (CTG) aims to generate text with desired attributes, but current methods lack high levels of controllability.
Approach:	They propose a lightweight decoding framework that reconstructs attribute distributions to balance the weights between attribute words and non-attribute words to generate more fluent text.
Outcome:	The proposed framework achieves state-of-the-art control performance on multiple CTG tasks.

Copied to clipboard

Chanwoo Park, Seungju Han, Xingzhi Guo, Asuman E. Ozdaglar, Kaiqing Zhang, Joo-Kyung Kim

Unsupervised Multi-Granularity Summarization (2022.findings-emnlp)

Challenge:	Existing studies focus on prompting and developing workflows with frozen LLMs.
Approach:	They propose a multi-agentic framework for collaborative LLMs with reinforcement learning that leverages multi-gendered frameworks to enhance collaboration.
Outcome:	The proposed model improves collaboration performance across multiple datasets with generalization to unseen domains compared to existing models.

Copied to clipboard

Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han

Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)

Challenge:	Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines.
Approach:	They propose to rank events by their salience and annotate a benchmark for GranuSum that contains multiple summaries at different granularities for each document cluster.
Outcome:	The proposed framework is capable of producing multi-granular summaries in unsupervised manner over strong baselines.

Copied to clipboard

Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Nullspace Disentanglement for Red Teaming Language Models (2025.emnlp-main)

Challenge:	Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings.
Approach:	They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings.
Outcome:	The proposed method consistently improves retrieval performance across multiple datasets.

Copied to clipboard

Yi Han, Yuanxing Liu, Weinan Zhang, Ting Liu

Demystifying Instruction Mixing for Fine-tuning Large Language Models (2024.acl-srw)

Challenge:	Existing work mainly leverages crowd workers to construct test cases.
Approach:	They propose a black-box approach that exploits the unique properties of the nullspace to disentangle and regulate the crucial success information within test cases.
Outcome:	The proposed approach outperforms baseline methods regarding the attack success rate and excels in aspects of diversity and fluency.

Copied to clipboard

Renxi Wang, Haonan Li, Minghao Wu, Yuxia Wang, Xudong Han, Chiyu Zhang, Timothy Baldwin

ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding (2021.naacl-main)

Challenge:	Instruction tuning is effective for aligning large language models with human instructions, but the procedure to optimizing the mixing of instruction datasets is still unclear.
Approach:	They categorize instructions into three primary types: NLP downstream tasks, coding, and general chat.
Outcome:	The proposed method improves performance of large language models (LLMs) but it is difficult to combine different instruction datasets to optimize overall performance.

Copied to clipboard

Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

Benchmarking Multi-National Value Alignment for Large Language Models (2025.findings-acl)

Challenge:	Existing methods to model coarse-grained linguistic information do not integrate coarse-gram information into pre-training.
Approach:	They propose an explicitly n-gram masking method to enhance integration of coarse-grained linguistic information into pre-training.
Outcome:	The proposed method outperforms existing models on English and Chinese text corpora and fine-tunes on 19 downstream tasks.

Copied to clipboard

Chengyi Ju, Weijie Shi, Chengzhong Liu, Jiaming Ji, Jipeng Zhang, Ruiyuan Zhang, Jiajie Xu, Yaodong Yang, Sirui Han, Yike Guo

Exploring and Distilling Multi-Dimensional Clues for Interpretable Social Bot Detection (2026.acl-long)

Challenge:	Existing studies on large language models focus on ethical reviews, failing to capture the diversity of national values.
Approach:	They propose a national value extraction pipeline to efficiently construct value assessment datasets and a model-based model with instruction tagging to process raw data sources.
Outcome:	The proposed benchmark evaluates the alignment of LLMs with the values of five major nations: China, the United States, the UK, France, and Germany.

Copied to clipboard

Yi Han, Haiqi Lu, Lizi Liao, Shuhan Zhou, Yuanxing Liu, Weinan Zhang, Ting Liu

Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression (2026.findings-acl)

Challenge:	Existing research on social bot detection results directly without corresponding supportive explanations, making it difficult to assess the extent to which such predictions are trustworthy.
Approach:	They propose a four-dimensional clue framework that uses outcome-reward reinforcement learning to train inspectors to generate faithful, grounded clues from user information, semantic features, interactive situation, and behavioral pattern.
Outcome:	The proposed framework outperforms baselines in detection performance and significantly improves the performance of large language models.

Copied to clipboard

Haiyang Sun, Chenyang Le, Wei Wang, Leying Zhang, Chuang Li, Bing Han, Chenda Li, Mengxiao Bi, Yanmin Qian

A Knowledge-Guided Framework for Frame Identification (2021.acl-long)

Challenge:	Existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect.
Approach:	They propose to use a large-scale, context-aware speech corpus derived from multi-speaker audiobooks to generate a speech that is human-like.
Outcome:	The proposed model outperforms existing methods in terms of emotional expression accuracy and naturalness.

Copied to clipboard

Xuefeng Su, Ru Li, Xiaoli Li, Jeff Z. Pan, Hu Zhang, Qinghua Chai, Xiaoqi Han

Plug-and-Play Document Modules for Pre-trained Models (2023.acl-long)

Challenge:	Existing frameworks for frame identification are limited to only a few types of frame knowledge.
Approach:	They propose a Knowledge-Guided Frame Identification framework that integrates frame knowledge to learn better frame representation.
Outcome:	The proposed framework outperforms the state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Chaojun Xiao, Zhengyan Zhang, Xu Han, Chi-Min Chan, Yankai Lin, Zhiyuan Liu, Xiangyang Li, Zhonghua Li, Zhao Cao, Maosong Sun

SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery (2025.emnlp-main)

Challenge:	Large-scale pre-trained models have been widely adopted for document-oriented NLP tasks, such as question answering.
Approach:	They propose to decouple document encoding from downstream tasks by introducing a document plugin into the backbone of a PTM.
Outcome:	The proposed model can encode documents once and for all across different scenarios.

Copied to clipboard

Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Yue Su, Haofei Yu, Jiaxuan You

StructEval: Deepen and Broaden Large Language Model Assessment via Structured Evaluation (2024.findings-acl)

Challenge:	Recent advances in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet raised critical ethical and safety concerns.
Approach:	They propose a framework to enhance safety and ethical responsibility in AI-driven scientific exploration.
Outcome:	The proposed framework significantly improves safety performance by 35% compared to traditional frameworks.

Copied to clipboard

Boxi Cao, Mengjie Ren, Hongyu Lin, Xianpei Han, Feng Zhang, Junfeng Zhan, Le Sun

ERNIE: Enhanced Language Representation with Informative Entities (P19-1)

Challenge:	Current evaluations for large language models use a single-item assessment paradigm . current evaluations struggle to discern whether a model possesses the required capabilities or merely memorizes/guesses the answers to specific questions.
Approach:	They propose a framework to evaluate large language models using atomic test objectives.
Outcome:	The proposed evaluation framework resists data contamination and reduces interference of potential biases, and sheds light on the design of future principled and trustworthy LLM evaluation protocols.

Copied to clipboard

Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang, Maosong Sun, Qun Liu

CmEAA: Cross-modal Enhancement and Alignment Adapter for Radiology Report Generation (2025.coling-main)

Challenge:	Existing pre-trained language models rarely consider incorporating knowledge graphs (KGs) Existing models capture rich semantic patterns from plain text and can be fine-tuned to improve performance of NLP tasks.
Approach:	They propose to incorporate knowledge graphs into pre-trained language models to enhance language representation with external knowledge.
Outcome:	The proposed model can take full advantage of lexical, syntactic, and knowledge information simultaneously.

Copied to clipboard

Xiyang Huang, Yingjie Han, Yx L, Runzhi Li, Pengcheng Wu, Kunli Zhang

SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification (2024.findings-acl)

Challenge:	Existing methods for automatic radiology report generation suffer from data bias.
Approach:	They propose a method that connects a vision encoder with a frozen large language model by using a cross-modal enhancement and alignment adapter.
Outcome:	The proposed model outperforms existing state-of-the-art methods on IU X-Ray and MIMIC-CXR datasets.

Copied to clipboard

Wenxin Liang, Tingyu Zhang, Han Liu, Feng Zhang

ToolDNA: Autonomous Evolution of Tool Metadata for Robust Dialogue Agents (2026.findings-acl)

Challenge:	Existing methods for few-shot text classification focus on enhancing separation of prototypes without taking semantic relationships into account.
Approach:	They propose to utilize semantically enhanced labels to calibrate class Prototypes . they propose a center loss method to enhance intra-class compactness .
Outcome:	The proposed method outperforms baseline methods on eight few-shot text classification datasets.

Copied to clipboard

Qiuyuan Ai, Cong Wang, Jiaqi Zhang, Zengxin Han, Jie Song

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)

Challenge:	Task-oriented dialogue systems face labor-intensive manual metadata tuning and sparse reinforcement learning (RL) rewards that fail to diagnose invocation errors.
Approach:	They propose a framework that enables auto-evolution of policy networks and tool metadata via RL . a tool metadata loop coordinates metadata through policy-generated candidates during rollouts .
Outcome:	The proposed framework achieves +11% problem resolution and +54% accuracy over commercial LLMs with prompt engineering and +25%/+35% over supervised fine-tuning.

Copied to clipboard

Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo

InsightPilot: An LLM-Empowered Automated Data Exploration System (2023.emnlp-demo)

Challenge:	Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain.
Approach:	They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators.
Outcome:	The proposed model performs better than state-of-the-art models, highlighting its challenging nature.

Copied to clipboard

Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, Dongmei Zhang

Challenge:	InsightPilot is an LLM-based, automated data exploration system designed to simplify the data exploration process.
Approach:	They propose an LLM-based, automated data exploration system that streamlines the data exploration process.
Outcome:	InsightPilot is an LLM-based, automated data exploration system . it can help users gain valuable insights from their datasets, in a case study and in nl .

LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)

Copied to clipboard

Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training (2021.emnlp-main)

Challenge:	Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs.
Approach:	They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal .
Outcome:	The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts.

Copied to clipboard

Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji, Jiawei Han

Named Entity Recognition

Challenge:	Named entity recognition models require abundant high-quality annotations to train . distant supervision may induce incomplete and noisy labels, making supervised learning ineffective.
Approach:	They propose a noise-robust learning scheme for training named entity recognition models using only distantly-labeled data and a self-training method that uses contextualized augmentations created by pre-trained language models.
Outcome:	The proposed method outperforms existing supervised NER models on three datasets by significant margins.

Forward-Backward Reasoning in Large Language Models for Mathematical Verification (2024.findings-acl)

Copied to clipboard

Weisen Jiang, Han Shi, Longhui Yu, Zhengying Liu, Yu Zhang, Zhenguo Li, James Kwok

Synergistic Weak-Strong Collaboration by Aligning Preferences (2025.acl-long)

Challenge:	Extensive experiments on six standard mathematical data sets and three LLMs show that FOBAR achieves state-of-the-art performance.
Approach:	They propose to combine forward and backward reasoning to verify candidate answers . they propose to use a template to mask a number and ask the LLM to answer a backward question .
Outcome:	Experiments on mathematical data show that proposed backward reasoning outperforms Self-Consistency.

Copied to clipboard

Yizhu Jiao, Xuchao Zhang, Zhaoyang Wang, Yubo Ma, Zhun Deng, Rujia Wang, Chetan Bansal, Saravan Rajmohan, Jiawei Han, Huaxiu Yao

FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information (2022.emnlp-main)

Challenge:	Current Large Language Models excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge.
Approach:	They propose a collaborative framework that pairs a specialized weak model with a general strong model to optimize collaboration.
Outcome:	The proposed framework outperforms each model alone by leveraging complementary strengths.

Copied to clipboard

Yijia Shao, Mengyu Zhou, Yifan Zhong, Tao Wu, Hongwei Han, Shi Han, Gideon Huang, Dongmei Zhang

ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web (2026.acl-long)

Challenge:	FormLM is a pre-trained language model for creating semi-structured forms where questions and descriptions are organized by predefined structures.
Approach:	They propose to enhance pre-trained language model with form structural information to model online forms and recommend form creation ideas.
Outcome:	The proposed model outperforms general-purpose language models on all tasks, with an improvement by 4.71 on Question Recommendation and 10.6 on Block Type Suggestion in terms of ROUGE-1 and Macro-F1, respectively.

Copied to clipboard

Zhiyuan Yao, Zishan Xu, Yifu Guo, Zhiguang Han, Cheng Yang, Shuo Zhang, Weinan Zhang, Xingshan Zeng, Weiwen Liu

Challenge:	Existing routers that use hardcoded tools are limited by scalability and generality bottlenecks.
Approach:	They propose a pipeline for training history-aware routers to empower precise navigation in large-scale ecosystems.
Outcome:	The proposed pipeline can train routers with dynamic context understanding to create the plug-and-play Light Routing Agent.

ChildEval:WHEN LARGE LANGUAGE MODELS MEET CHILDREN’S PERSONALITIES (2026.findings-acl)

Copied to clipboard

Yanyan Luo, Xue Han, Chunxu Zhao, Ruiqiao Bai, Yaxing Zhang, Qian Hu, Lijun Mei, Junlan Feng

Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) have achieved remarkable success in effectively understanding and generating human language, leading to a revolutionary era in LLMs.
Approach:	They propose a benchmark to evaluate LLMs' ability to infer and follow child-centered preferences in long-context conversations.
Outcome:	The proposed benchmark spans five top-level and fourteen sub-level categories covering children’s daily lives and development.

Copied to clipboard

Zhen Han, Gengyuan Zhang, Yunpu Ma, Volker Tresp

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)

Challenge:	Various temporal knowledge graph (KG) completion models have been proposed . knowledge graphs are typically static and store facts in their current state .
Approach:	They propose to use temporal embeddings and a score function to model temporal knowledge graphs . they classify the temporal embedded methods into two classes: timestamp and time-dependent .
Outcome:	The proposed models outperform current models on ICEWS datasets with 3000 experiments and 13159 GPU hours.

Copied to clipboard

Chenyang Song, Xu Han, Zhengyan Zhang, Shengding Hu, Xiyu Shi, Kuai Li, Chen Chen, Zhiyuan Liu, Guangli Li, Tao Yang, Maosong Sun

SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuning (2025.findings-emnlp)

Challenge:	Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance .
Approach:	They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization .
Outcome:	The proposed method achieves high activation sparsity and comparable model performance.

Copied to clipboard

Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han

Efficient Table Retrieval and Understanding with Multimodal Large Language Models (2026.findings-eacl)

Challenge:	Existing methods for self-play fine-tuning do not generate new information and the large number of correct SQL queries produced by the opponent model reduces the main model’s ability to generate accurate SQL queries.
Approach:	They propose a self-play fine-tuning method tailored for the Text-to-SQL task that synthesizes high-quality fine- tuning data iteratively based on the database schema and validation feedback to enhance model performance.
Outcome:	The proposed method outperforms existing state-of-the-art methods on six open-source LLMs and five widely used benchmarks.

Copied to clipboard

Zhuoyan Xu, Haoyang Fang, Boran Han, Bonan Min, Bernie Wang, Cuixiong Hu, Shuai Zhang