Papers by Pan Zhang

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)

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

Xiang Cheng, Chengyan Pan, Minjun Zhao, Deyang Li, Fangchao Liu, Xinyu Zhang, Xiao Zhang, Yong Liu

DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)

Challenge:	In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs).
Approach:	They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks.
Outcome:	The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1.

Copied to clipboard

Jiabao Pan, Yan Zhang, Chen Zhang, Zuozhu Liu, Hongwei Wang, Haizhou Li

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation (2025.findings-acl)

Challenge:	Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text.
Approach:	They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting .
Outcome:	The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks.

Copied to clipboard

Wenxiang Guo, Yu Zhang, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, ZheTao Chen, Wenhao Xu, Fei Wu, Zhou Zhao

Speech & Audio in NLP

Challenge:	Existing automated singing annotation (ASA) methods tackle isolated aspects of the annotation pipeline.
Approach:	They propose a framework that addresses transcription, alignment, and refined style annotations.
Outcome:	The proposed framework delivers comprehensive multi-level annotations encompassing: (1) precise phoneme-audio alignment, (2) robust note transcription and temporal localization, (3) expressive vocal technique identification, and (4) global stylistic characterization including emotion and pace.

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders (2021.emnlp-main)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Li Dong, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

Multilinguality

Challenge:	Existing work on improving cross-lingual transferability of NMT model is under-explored.
Approach:	They propose a model that leverages a multilingual pretrained encoder to improve cross-lingual transferability.
Outcome:	The proposed model outperforms mBART and m2m-100 on a zero-shot cross-lingual transfer task.

The TechQA Dataset (2020.acl-main)

Copied to clipboard

Vittorio Castelli, Rishav Chakravarti, Saswati Dana, Anthony Ferritto, Radu Florian, Martin Franz, Dinesh Garg, Dinesh Khandelwal, Scott McCarley, Michael McCawley, Mohamed Nasr, Lin Pan, Cezar Pendus, John Pitrelli, Saurabh Pujar, Salim Roukos, Andrzej Sakrajda, Avi Sil, Rosario Uceda-Sosa, Todd Ward, Rong Zhang

Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models (2024.findings-acl)

Challenge:	TECHQA is a domain-adaptation question answering dataset for the technical support domain.
Approach:	They propose a domain-adaptation question-answering dataset for the technical support domain that contains actual questions posed by users on a technical forum .
Outcome:	The TECHQA dataset highlights two real-world issues from the automated customer support domain.

Copied to clipboard

Xinran Zhao, Hongming Zhang, Xiaoman Pan, Wenlin Yao, Dong Yu, Tongshuang Wu, Jianshu Chen

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Challenge:	Existing studies on the confidence calibration of LLMs have not explored the effects of different prompting strategies on LLM performance.
Approach:	They propose Fact-and-Reflection prompting which improves LLM confidence calibration . they propose to use human cognition to elicit known "facts" and ask model to "reflect" over them .
Outcome:	The proposed method lowers the expected calibration error by 23.5% on multi-purpose QA tasks.

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning (2025.findings-acl)

Challenge:	Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty.
Approach:	They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples.
Outcome:	The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance.

Copied to clipboard

Xinghao Chen, Zhijing Sun, Guo Wenjin, Miaoran Zhang, Yanjun Chen, Yirong Sun, Hui Su, Yijie Pan, Dietrich Klakow, Wenjie Li, Xiaoyu Shen

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

Challenge:	Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought prompting.
Approach:	They examine the factors influencing CoT distillation including granularity, format and teacher model.
Outcome:	The proposed model is based on four teacher models and seven student models across seven mathematical and commonsense reasoning datasets.

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

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

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

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

DANLI: Deliberative Agent for Following Natural Language Instructions (2022.emnlp-main)

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

Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Ziqiao Ma, Keunwoo Yu, Yuwei Bao, Joyce Chai

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Challenge:	Recent work on embodied AI agents that can perform tasks by following human language instructions is limited by reactive methods, which are insufficient for long-horizon complex tasks.
Approach:	They propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience.
Outcome:	The proposed agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark.

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

AutoMixAlign: Adaptive Data Mixing for Multi-Task Preference Optimization in LLMs (2025.acl-long)

Copied to clipboard

Nicholas E. Corrado, Julian Katz-Samuels, Adithya M Devraj, Hyokun Yun, Chao Zhang, Yi Xu, Yi Pan, Bing Yin, Trishul Chilimbi

How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)

Challenge:	Existing approaches to align large language models rely on large ablation studies, heuristics, or human intuition to produce models with strong performance across tasks.
Approach:	They propose an algorithm that mixes datasets during LLM training to balance performance across multiple tasks.
Outcome:	The proposed algorithm outperforms existing methods on multitask alignment setups and achieves convergence rate of O(1/T) in the convex case.

Copied to clipboard

Wenlin Yao, Lifeng Jin, Hongming Zhang, Xiaoman Pan, Kaiqiang Song, Dian Yu, Dong Yu, Jianshu Chen

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence.
Approach:	They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation.
Outcome:	The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

Noise-powered Multi-modal Knowledge Graph Representation Framework (2025.coling-main)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Zhuo Chen, Yin Fang, Yichi Zhang, Lingbing Guo, Jiaoyan Chen, Jeff Z. Pan, Huajun Chen, Wen Zhang

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification (2026.findings-acl)

Challenge:	Current efforts to integrate MMKG with pretraining are scarce.
Approach:	They propose a method that integrates multi-modal entity features into MMKGs using a Transformer-based architecture equipped with modality-level noise masking.
Outcome:	The proposed method achieves SOTA performance across ten datasets.

Copied to clipboard

Wangjie Gan, Miao Pan, Linbo Xi, Wenqi Zhang, Jintao Chen, Jianwei Yin, Xuhong Zhang

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

Challenge:	Existing studies have demonstrated that supervised fine-tuning and reinforcement learning are effective in integrating knowledge injection with robust generalization.
Approach:	They propose a unified post-training framework that addresses intrinsic limitations of supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training.

Copied to clipboard

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

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition (2025.acl-long)

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

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)

Challenge:	Creating lyrics and melodies in symbolic format requires expert knowledge of melody and an advanced understanding of lyrics.
Approach:	They introduce SongComposer, a music-specialized large language model that can create symbolic lyrics and melodies following instructions.
Outcome:	The proposed model outperforms existing models in symbolic song composition tasks.

Copied to clipboard

Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen

AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens.
Approach:	They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method.
Outcome:	The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs.

Copied to clipboard

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures (2026.acl-long)

Challenge:	Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach:	They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome:	The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.

Copied to clipboard

Yi Hu, Jiaqi Gu, Ruxin Wang, Zijun Yao, Hao Peng, Xiaobao Wu, Jianhui Chen, Muhan Zhang, Liangming Pan

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

Challenge:	Recent research has shown that reinforcement learning can elicit intriguing emergent reasoning behaviors.
Approach:	They propose a comprehensive survey of the mechanistic understanding of large reasoning models . they organize findings into three core dimensions: 1) training dynamics, 2) reasoning mechanisms, and 3) unintended behaviors.
Outcome:	This paper synthesizes the mechanistic understanding of large reasoning models into three dimensions . authors outline a roadmap for future studies including improved interpretability and methodologies .

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

Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)

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

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Intent-Aware and Hate-Mitigating Counterspeech Generation via Dual-Discriminator Guided LLMs (2024.lrec-main)

Challenge:	In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations.
Approach:	They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention .
Outcome:	The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Copied to clipboard

Haiyang Wang, Zhiliang Tian, Xin Song, Yue Zhang, Yuchen Pan, Hongkui Tu, Minlie Huang, Bin Zhou

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Challenge:	Hate speech is an aggressive expression that incites hatred towards specific groups based on their group identity.
Approach:	They propose an LLMs-based framework for counterspeech generation that uses intent-aware discriminators to decode intents of LLM models.
Outcome:	The proposed framework matches intents with hate mitigation intents and performs well.

Copied to clipboard

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

Copied to clipboard

Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan

Challenge:	Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction.
Approach:	They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process.
Outcome:	The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process .

DART: Open-Domain Structured Data Record to Text Generation (2021.naacl-main)

Copied to clipboard

Linyong Nan, Dragomir Radev, Rui Zhang, Amrit Rau, Abhinand Sivaprasad, Chiachun Hsieh, Xiangru Tang, Aadit Vyas, Neha Verma, Pranav Krishna, Yangxiaokang Liu, Nadia Irwanto, Jessica Pan, Faiaz Rahman, Ahmad Zaidi, Mutethia Mutuma, Yasin Tarabar, Ankit Gupta, Tao Yu, Yi Chern Tan, Xi Victoria Lin, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani

SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents (2024.emnlp-main)

Challenge:	Data-to-text annotations can be costly when dealing with tables with nontrivial structures.
Approach:	They propose a procedure for extracting semantic triples from tables that encodes their structures by exploiting table headers and table title.
Outcome:	The proposed method exploits the semantic dependencies between table headers and title to extract semantic triples from tables.

Copied to clipboard

Qi Zhang, Zhijia Chen, Huitong Pan, Cornelia Caragea, Longin Latecki, Eduard Dragut

ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System (N18-5)

Challenge:	Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data.
Approach:	They propose to use a scientific entity and relation extraction dataset to capture interactions between entities in full texts.
Outcome:	The proposed dataset captures the intricate use and interactions among entities in full texts and provides an out-of-distribution test set to offer a more realistic evaluation.

Copied to clipboard

Boliang Zhang, Ying Lin, Xiaoman Pan, Di Lu, Jonathan May, Kevin Knight, Heng Ji

AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search (2026.findings-acl)

Challenge:	ELISA-EDL is a cross-lingual entity extraction, linking and localization system for Wikipedia languages.
Approach:	They propose a cross-lingual entity extraction, linking and localization system for English speakers . it extracts entities from unstructured text in any of 282 Wikipedia languages and links them to English knowledge bases .
Outcome:	The proposed system extracts entity mentions from Wikipedia and links them to English knowledge bases and visualizes locations related to disaster topics on a world heatmap.

Copied to clipboard

Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao, Hangting Ye, Shufei Zhang, Jian Tang, Tianshu Yu

MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)

Challenge:	Experimental evaluation shows that AOT* achieves competitive solve rates using 3-5 fewer iterations than existing LLM-based approaches.
Approach:	They propose a framework that integrates LLM-generated chemical synthesis pathways with systematic AND-OR tree search.
Outcome:	Experimental results show that AOT* improves search efficiency and solves faster than existing approaches.

Copied to clipboard

Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu

Natural Language Interfaces

Challenge:	Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios.
Approach:	They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity.
Outcome:	The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues.

Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge (2026.acl-industry)

Copied to clipboard

Junjie Wu, Xuan Kan, Zihao He, Shunwen Tan, Bo Pan, Kaitai Zhang

Token-level Inference-Time Alignment for Vision-Language Models (2026.findings-acl)

Challenge:	Existing MLLMs are optimized for single-task scenarios and struggle to generalize to diverse contexts.
Approach:	They propose a framework that integrates multitask reinforcement learning and generalization capabilities of MLLMs to optimize the judge model across multiple tasks.
Outcome:	The proposed framework outperforms baseline models in judgment consistency and correlation with human preferences.

Copied to clipboard

Kejia Chen, Junjun Zheng, Jiawen Zhang, Manxi Lin, Xiao Pan, Jiacong Hu, Jian Lou, Zunlei Feng, Mingli Song

TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control (2024.emnlp-main)

Challenge:	Vision-Language Models (VLMs) often prioritize linguistic fluency over visual fidelity . despite widespread adoption, VLMs often exhibit a critical failure mode: hallucination .
Approach:	They propose a framework for Token-level Inference-Time Alignment that steers the decoding process without updating the base model parameters.
Outcome:	The proposed framework improves performance on 13 benchmarks across architectures . it boosts LLaVA-1.5-7B by 8.6% on MMVet and achieves a 74.0 MMStar score .

Copied to clipboard

Yu Zhang, Ziyue Jiang, Ruiqi Li, Changhao Pan, Jinzheng He, Rongjie Huang, Chuxin Wang, Zhou Zhao

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities (2025.acl-long)

Challenge:	Existing models fail to generate singing voices rich in stylistic nuances for unseen singers due to multifaceted nature of singing styles.
Approach:	They propose a zero-shot SVS model for style transfer across cross-lingual speech and singing styles and multi-level style control.
Outcome:	Experimental results show that TCSinger outperforms baseline models in synthesis quality, singer similarity, and style controllability.

Copied to clipboard

Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, Fei Liu

Challenge:	Existing studies have focused on developing LLMs to automate complex planning tasks.
Approach:	They propose to provide a comprehensive overview of current LLM planners to fill this gap . they examine performance criteria including completeness, executability, optimality, representation, generalization, and efficiency .
Outcome:	The proposed survey examines performance criteria for LLM planners and highlights their strengths and weaknesses.

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

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

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Copied to clipboard

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

GUIDE: Towards Scalable Advising for Research Ideas (2026.acl-long)

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

Yaowenqi Liu, BingXu Meng, Rui Pan, Yuxing Liu, Jerry Huang, Jiaxuan You, Tong Zhang

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Challenge:	Existing systems that provide detailed, constructive feedback on academic papers struggle with review fidelity.
Approach:	They explore factors that underlie the development of robust advising systems . large language models have shown remarkable progress in tasks from text generation to code synthesis .
Outcome:	The proposed model outperforms general-purpose language models in acceptance rates for self-ranked top-30% submissions to ICLR 2025.

Copied to clipboard

Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, Kai Chen, Dahua Lin, Jiaqi Wang

DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition (2025.findings-naacl)

Challenge:	Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach:	They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome:	The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.

Copied to clipboard

Qi Zhang, Huitong Pan, Zhijia Chen, Longin Jan Latecki, Cornelia Caragea, Eduard Dragut

Active Prompting with Chain-of-Thought for Large Language Models (2024.acl-long)

Challenge:	Existing methods to identify entities using distant annotations are expensive and time-consuming.
Approach:	They propose a training dynamics-based label cleaning approach to characterize distant annotations and an automatic threshold estimation strategy to locate errors in distant labels.
Outcome:	The proposed method outperforms several advanced DS-NER approaches across four datasets.

Copied to clipboard

Shizhe Diao, Pengcheng Wang, Yong Lin, Rui Pan, Xiang Liu, Tong Zhang

ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval (2025.findings-emnlp)

Challenge:	Existing methods to annotate large language models rely on a fixed set of human-annotated exemplars, which are not always the most effective for different tasks.
Approach:	They propose a method to adapt large language models to different tasks with task-specific example prompts (annotated with human-designed CoT reasoning) they introduce several metrics to characterize uncertainty so as to select the most uncertain questions for annotation.
Outcome:	The proposed method significantly improves performance on eight complex reasoning tasks.

Copied to clipboard

Yi Pan, Yujia Zhang, Michael Kampffmeyer, Xiaoguang Zhao

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

Challenge:	Existing models for PRVR use unimodal features, but powerful pretrained vision-language models like CLIP are underexplored.
Approach:	ProPy is a model with systematic architectural adaptation of CLIP specifically designed for PRVR.
Outcome:	ProPy outperforms existing models on three public datasets in terms of performance on the 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

Visual Data in NLP

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.

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

Copied to clipboard

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

Towards Provably Secure Generative AI: Reliable Consensus Sampling (2026.findings-acl)

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

Yu Cui, Hang Fu, Sicheng Pan, Zhuoyu Sun, Yifei Liu, Yuhong Nie, Bo Ran, Baohan Huang, Xufeng Zhang, Haibin Zhang, Cong Zuo, Licheng Wang

Plum: Prompt Learning using Metaheuristics (2024.findings-acl)

Challenge:	Existing research on generative AI security is driven by mutually reinforcing attack and defense methodologies grounded in empirical experience.
Approach:	They propose a new algorithm that uses a random sampling algorithm to control risk.
Outcome:	The proposed algorithm improves robustness and utility while maintaining latency comparable to existing algorithms.

Copied to clipboard

Rui Pan, Shuo Xing, Shizhe Diao, Wenhe Sun, Xiang Liu, KaShun Shum, Jipeng Zhang, Renjie Pi, Tong Zhang

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)

Challenge:	Recent advances in prompt learning have led to a need for general prompt optimization methods.
Approach:	They propose a branch of discrete non-convex optimization methods with over 100 options as a promising approach to prompt learning.
Outcome:	The proposed methods can be used to discover more human-understandable prompts that were previously unknown in reasoning and image generation tasks.

Copied to clipboard

Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu

Challenge:	Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves.
Approach:	They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop.
Outcome:	The proposed framework yields more stable training and higher long-horizon task success across open-world environments.

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Copied to clipboard

Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

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

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

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

A Survey on Training-free Alignment of Large Language Models (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

Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian

OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)

Challenge:	a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms.
Approach:	They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration .
Outcome:	The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining .

Copied to clipboard

Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu

ELAD: Explanation-Guided Large Language Models Active Distillation (2024.findings-acl)

Challenge:	Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet.
Approach:	They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details.
Outcome:	The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata .

Copied to clipboard

Yifei Zhang, Bo Pan, Chen Ling, Yuntong Hu, Liang Zhao

BLADE: Benchmarking Language Model Agents for Data-Driven Science (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) are hindered by their memory inefficiency, computational demands, and the high costs of API inferences.
Approach:	They propose an Explanation-Guided LLMs Active Distillation framework that employs an active learning strategy to optimize the balance between annotation costs and model performance.
Outcome:	The proposed framework significantly improves the efficiency of LLMs knowledge distillation.

Copied to clipboard

Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu, Yue Mao, Youran Pan, Teng Wu, Jiaqian Yu, Yikun Zhang, Tianmai Zhang, Lanyi Zhu, Mike Merrill, Jeffrey Heer, Tim Althoff

Dual-Channel Span for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Challenge:	Language model-based agents can be used to conduct and support data-driven science, but evaluating them on open-ended tasks is challenging due to multiple valid approaches, partially correct steps, and different ways to express the same decisions.
Approach:	They propose a benchmark to automatically evaluate agents’ multifaceted approaches to open-ended research questions.
Outcome:	BLADE evaluates agents’ multifaceted approaches to open-ended research questions using data from 12 datasets and research questions drawn from existing scientific literature.

Copied to clipboard

Pan Li, Ping Li, Kai Zhang

Sentiment Analysis

Challenge:	Existing approaches to extract sentiment triplets are too noisy and enumerate all possible spans.
Approach:	They propose a dual-channel span generation method to constrain the search space of span candidates.
Outcome:	The proposed method reduces span enumeration by nearly half on two versions of public datasets.

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

TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems (2026.findings-acl)

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

Rui Sun, Jie Ding, Chenghua Gong, Tianjun Gu, Yihang Jiang, Juyuan Zhang, Liming Pan, Linyuan Lü

GroundingGPT: Language Enhanced Multi-modal Grounding Model (2024.acl-long)

Challenge:	Existing communication topologies rely on spatio-temporal dialogues, which incur high latency and computation.
Approach:	They propose a framework for one-shot Topology generation with Diverse Interaction Modes that enables agents to construct heterogeneous communication without iterative coordination.
Outcome:	The proposed framework reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods.

Copied to clipboard

Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, YiQing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Vu Tu, Zhida Huang, Tao Wang

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary (2025.emnlp-main)

Challenge:	Existing multi-modal large language models focus on capturing global information while neglecting the fine-grained local information in multimodal inputs.
Approach:	They propose an end-to-end language enhanced multi-modal grounding model that performs fine-grained grounding tasks for image, video and audio.
Outcome:	The proposed model achieves impressive fine-grained understanding of multi-modal inputs while maintaining or improving its global comprehension capabilities.

Copied to clipboard

Licheng Pan, Yongqi Tong, Xin Zhang, Xiaolu Zhang, Jun Zhou, Zhixuan Chu

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts (2024.emnlp-main)

Challenge:	Large language models (LLMs) often refuse to answer legitimate queries, causing models to treat many reasonable prompts as potentially risky.
Approach:	They propose a framework that automatically generates and selects overrefusal prompts near the safety boundary.
Outcome:	The proposed framework identifies and curates boundary-aligned prompts, enabling more effective and targeted mitigation of overrefusal.

Copied to clipboard

Ruida Wang, Jipeng Zhang, Yizhen Jia, Rui Pan, Shizhe Diao, Renjie Pi, Tong Zhang

LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models (2024.naacl-demo)

Challenge:	a framework for formal proof writing using formal languages like Lean4 is needed to prove mathematical theorems using formal language.
Approach:	They propose a framework that trains a general-purpose LLM to be a Lean4 expert.
Outcome:	The proposed framework achieves cumulative accuracies of 36.48% and 33.61% on MiniF2F-Valid and Test datasets.

Copied to clipboard

Shizhe Diao, Rui Pan, Hanze Dong, KaShun Shum, Jipeng Zhang, Wei Xiong, Tong Zhang

Think Faster Than Words: Efficient LLM Chain-of-Thought Reasoning via Dynamic Shortcut Decoding (2026.acl-long)

Challenge:	Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches.
Approach:	They propose a toolkit to simplify the finetuning of general foundation models.
Outcome:	The proposed toolkit simplifies the domain- and task-aware finetuning of general foundation models with limited computing resources.

Copied to clipboard

Fan Liu, Yanhao Wang, Min Zhang, Zhikang Chen, Zeyuan Li, Lewei He, Jiahui Pan

CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models (2025.coling-main)

Challenge:	Existing methods that prune or employ early stopping to reduce latency often compromise reasoning reliability.
Approach:	They propose a shortcut decoding framework that integrates probes over internal hidden states with step-level entropy to detect convergence of reasoning during generation and adaptively selects between a fast-exit path and a stability-verified path to remove redundant steps while preserving answer correctness.
Outcome:	The proposed framework reduces token usage by approximately 35% and maintains accuracy comparable to full CoT decoding.

Copied to clipboard

Zhongzhi Li, Ming-Liang Zhang, Pei-Jie Wang, Jian Xu, Rui-Song Zhang, Yin Fei, Zhi-Long Ji, Jin-Feng Bai, Zhen-Ru Pan, Jiaxin Zhang, Cheng-Lin Liu

Numerical Reasoning

Challenge:	Large language models excel in various language tasks, while large multimodal models effectively handle visual-language problems.
Approach:	They propose to use a multimodal multimodal model evaluation benchmark to evaluate model performance in Chinese K12 classrooms.
Outcome:	The proposed model evaluation tool is integrated with the CMMaTH dataset.

d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Leyi Pan, Shuchang Tao, Yunpeng Zhai, Zheyu Fu, Liancheng Fang, Minghua He, Lingzhe Zhang, Zhaoyang Liu, Bolin Ding, Aiwei Liu, Lijie Wen

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

Challenge:	Existing RL methods suffer from reliability bottlenecks due to reward sparsity and intractable computations . d-TreeRPO provides fine-grained and verifiable step-wise reward signals .
Approach:	They propose a reliable reinforcement learning framework for diffusion large language models that leverages tree-structured rollouts and bottom-up advantage computation based on verifiable outcome rewards.
Outcome:	The proposed framework outperforms baseline models and achieves significant improvements across reasoning benchmarks.

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.

SlowBERT: Slow-down Attacks on Input-adaptive Multi-exit BERT (2023.findings-acl)

Copied to clipboard

Shengyao Zhang, Xudong Pan, Mi Zhang, Min Yang

G-HiRel: Enhancing the Adaption to Knowledge Updating for Large Language Model Reasoning (2026.findings-acl)

Challenge:	Pre-trained language models such as Google’s BERT have been gaining significant improvements to various down-stream applications, but the enormous training and inference cost severely hinders its practice on real-time applications and hardwareconstrained edge devices.
Approach:	They propose a slow-down attack on input-adaptive multi-exit BERT where the adversary imperceptibly modifies the input texts to drastically increase the inference cost.
Outcome:	The proposed attack on input-adaptive multi-exit BERT dramatically increases the average inference cost by 4.57, which would hurt the service quality of multi-extit BRT in practice, e.g., increasing the real-time cloud services’ response times for online users.

Copied to clipboard

Yudai Pan, Jiajie Hong, Tianzhe Zhao, Lingyun Song, Lingling Zhang, Yixin Chen, Xuequn Shang

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

Challenge:	Large language models (LLMs) have good performance in multiple reasoning tasks, but are limited to adapt the rapid knowledge updates in the real-world scenario.
Approach:	They propose an LLM reasoning framework with hierarchical relational retrieval for large-scale knowledge updating, named G-HiRel.
Outcome:	The proposed framework achieves superiority in terms of accuracy and interpretability on three benchmarks.

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

Don’t Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction (2026.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

Yuzhe Zhang, Xianwei Xue, Xingyong Wu, Mengke Chen, Chen Liu, Xinran He, Run Shao, Feiran Liu, Huanmin Xu, Qiutong Pan, Haiwei Wang

CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models (2026.findings-acl)

Challenge:	Existing GUI agents assume deterministic environment responses, generating actions without verifying whether previous operations succeeded.
Approach:	They propose a GUI agent that explicitly models action outcomes and recovery under noisy environments.
Outcome:	The proposed agent reduces failure loops and improves recovery success in noisy environments while maintaining competitive standard task performance.

Copied to clipboard

Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Wang Zhen, Yongjie Wang, Yao Pan

Taxonomy-Driven Knowledge Graph Construction for Domain-Specific Scientific Applications (2025.findings-acl)

Challenge:	Existing classification-based methods capture noise and spurious correlations while overlooking the underlying causal mechanisms.
Approach:	They propose a hallucination detection framework based on structural causal models that captures static and passive signals from internal states and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise.
Outcome:	Experiments on four datasets and three widely used LLMs show that the proposed framework improves AUROC and interpretability.

Copied to clipboard

Huitong Pan, Qi Zhang, Mustapha Adamu, Eduard Dragut, Longin Jan Latecki

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Challenge:	Existing methods for constructing domain-specific knowledge graphs neglect curated taxonomies and LLMs fail to extract KGs in specialized domains.
Approach:	They propose a taxonomy-driven framework for constructing domain-specific knowledge graphs . they use structured taxonomies, Large Language Models and Retrieval-Augmented Generation .
Outcome:	The proposed framework can be adapted for other specialized domains.

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling (2025.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Shiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan, Weicheng Ma, Hefan Zhang, Sophia Pan, Ming Cheng, Shubham Mohole, Saeed Hassanpour, Soroush Vosoughi, Michael Macy

Challenge:	Rhetorical strategies are important to persuasive communication, but their analysis relies on human annotation, which is costly, inconsistent and difficult to scale.
Approach:	They propose a framework that leverages large language models to generate and label debate data . they fine-tune transformer-based classifiers on this dataset and validate it against human data a .
Outcome:	The proposed model achieves high performance and strong generalization across topical domains.

Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information (2025.findings-emnlp)

Copied to clipboard

Weicheng Ma, Hefan Zhang, Shiyu Ji, Farnoosh Hashemi, Qichao Wang, Ivory Yang, Joice Chen, Juanwen Pan, Michael Macy, Saeed Hassanpour, Soroush Vosoughi

GOBench: Stage-Wise Diagnostics and the Visual Paradox in Multimodal Graph Optimization (2026.findings-acl)

Challenge:	Existing approaches to persuasive dialogue generation suffer from stance oscillation and low informativeness.
Approach:	They propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation.
Outcome:	The proposed method ensures speaker characteristics guide all stages of dialogue generation and aligns language use with speakers’ native languages to better capture cultural nuances.

Copied to clipboard

Yinghao Chen, Wantong Xie, Shuli Zeng, Sijia Zhang, Xiaotian Pan, Feng Wu, Xiangyang Li

AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs (2026.acl-long)

Challenge:	Existing benchmarks fail to represent multimodal problem specifications, score outcomes only and cannot localize where failures occur along the modeling pipeline.
Approach:	They propose a Graph Optimization benchmark that aligns multiple modalities with solver-derived oracles and a diagnostic protocol that evaluates intermediate artifacts as well as end results.
Outcome:	Graph Optimization benchmark (GOBench) evaluates intermediate artifacts as well as end results . vision reliably increases inference cost, while reliability impact is regime-dependent . current benchmarks fail to represent multimodal problem specifications, fail to localize failures .

Copied to clipboard

Xuanwen Ding, Chengjun Pan, Zejun Li, Jiwen Zhang, Siyuan Wang, Zhongyu Wei

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy (2026.findings-eacl)

Challenge:	Evaluating multimodal large language models (MLLMs) is becoming increasingly expensive as benchmarks grow in scale and cross-modality complexity.
Approach:	They propose an adaptive evaluation framework for efficient benchmarking that treats evaluation as an interview-like process by keeping a hypothesized ability structure of the evaluated model and actively selecting the informative questions.
Outcome:	Experiments on four representative multimodal benchmarks show that **A2-Judger significantly improves sample efficiency while maintaining reliable evaluation results.

Copied to clipboard

Yu Cui, Sicheng Pan, Yifei Liu, Haibin Zhang, Cong Zuo

Bridge-Coder: Transferring Model Capabilities from High-Resource to Low-Resource Programming Language (2025.findings-acl)

Challenge:	Large language models (LLMs) have been widely deployed in Conversational AIs . however, the methods proposed in the study rely on a white-box setting .
Approach:	They propose an indirect prompt injection attack that induces privacy extraction in LLMs . they use token-efficient data containing false memories to inject LLM data .
Outcome:	The proposed method outperforms baselines and achieves state-of-the-art performance.

Copied to clipboard

Jipeng Zhang, Jianshu Zhang, Yuanzhe Li, Renjie Pi, Rui Pan, Runtao Liu, Zheng Ziqiang, Tong Zhang

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data (2025.findings-naacl)

Challenge:	Large Language Models (LLMs) excel at generating code for high-resource programming languages (HRPLs) however, they struggle significantly with low-resourced programming languages such as D, exacerbating the digital divide.
Approach:	They propose a method to generate LRPL data using LLM's general knowledge, HRPL proficiency, and in-context learning capabilities.
Outcome:	The proposed method improves on R, D, Racket, and Bash, while maintaining the same quality.

Copied to clipboard

Jipeng Zhang, Yaxuan Qin, Renjie Pi, Weizhong Zhang, Rui Pan, Tong Zhang

Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification (2022.coling-1)

Challenge:	Existing methods for instruction tuning are limited due to the increasing volume of instruction datasets and the increased computational costs.
Approach:	They propose to extract a small and highly informative subset of training samples from a large dataset that achieves comparable performance to the full dataset.
Outcome:	The proposed algorithm outperforms other unsupervised methods and achieves comparable performance to the full dataset.

Copied to clipboard

Wei Huang, Chen Liu, Bo Xiao, Yihua Zhao, Zhaoming Pan, Zhimin Zhang, Xinyun Yang, Guiquan Liu

Text Classification

Challenge:	Existing methods for hierarchical text classification are lacking in the field of natural language processing.
Approach:	They propose a hierarchy-aware T5 model with path-adaptive attention mechanism to exploit hierarchical dependency across different levels.
Outcome:	The proposed model outperforms state-of-the-art models especially in Macro-F1 and low Macro.

InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd Behavior (2025.acl-long)

Copied to clipboard

Huisheng Wang, Zhuoshi Pan, Hangjing Zhang, Mingxiao Liu, Hanqing Gao, H. Vicky Zhao

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)

Challenge:	relying on authentic data for Supervised Fine-Tuning (SFT) is costly and expensive.
Approach:	They propose a framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment problems rather than the complex scenarios.
Outcome:	The proposed framework achieves faster parameter convergence than using real-user data, suggesting superior learning efficiency.

Copied to clipboard

Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu

DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability .
Approach:	They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR .
Outcome:	The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks.

Copied to clipboard

Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu

How Far are We from Robust Long Abstractive Summarization? (2022.emnlp-main)

Challenge:	Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding.
Approach:	They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects.
Outcome:	The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation.

Copied to clipboard

Huan Yee Koh, Jiaxin Ju, He Zhang, Ming Liu, Shirui Pan

Error Analysis of Uyghur Name Tagging: Language-specific Techniques and Remaining Challenges (L18-1)

Challenge:	Abstractive summarization has made tremendous progress in recent years . however, even under a short document setting, abstractive models often generate summaries that are repetitive, ungrammatical, and factually inconsistent with the source.
Approach:	They perform fine-grained human annotations to evaluate long document abstractive summarization systems and develop factual consistency metrics.
Outcome:	The proposed model can generate more relevant summaries but not factual ones.

Copied to clipboard

Halidanmu Abudukelimu, Abudoukelimu Abulizi, Boliang Zhang, Xiaoman Pan, Di Lu, Heng Ji, Yang Liu

Syntactic Text Processing

Challenge:	despite efforts at name tagging, there is limited understanding on the performance ceiling . despite the high-resource language, there are very few natural language processing tools available .
Approach:	They propose to use a machine learning model to identify Uyghur name tagger errors . they conclude that such a model is unlikely to be effective for Uygur, or low-resource languages .
Outcome:	The proposed model is unlikely to be effective for Uyghur, or low-resource languages in general, the authors argue . they show that the proposed model can be used for high-res languages with superficial features .

Superficial Self-Improved Reasoners Benefit from Model Merging (2025.emnlp-main)

Copied to clipboard

Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, Wenke Lee

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Challenge:	Large Language Models (LLMs) rely heavily on large-scale reasoning data, but as data becomes scarce, model self-improvement offers a promising alternative.
Approach:	They propose to merge the weights of original and self-improved LLMs to mitigate model collapse and improve generalized reasoning capability.
Outcome:	The proposed model merge mitigates model collapse and improves generalized reasoning capability.

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning? (2024.acl-long)

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

Copied to clipboard

Zhaochen Su, Juntao Li, Jun Zhang, Tong Zhu, Xiaoye Qu, Pan Zhou, Yan Bowen, Yu Cheng, Min Zhang

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions (2023.emnlp-main)

Challenge:	Current temporal reasoning datasets are limited to questions about single or isolated events, falling short in mirroring the realistic temporal characteristics involving concurrent nature and intricate temporal interconnections.
Approach:	They propose a co-temporal Question Answering benchmark that contains four co-time scenarios with 4,748 samples for evaluating the co-timing abilities of large language models.
Outcome:	The proposed benchmarks show that current LLMs struggle on CoTempQA tasks even when enhanced with Chain of Thought methodologies.

Copied to clipboard

Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li

Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis (2023.acl-long)

Challenge:	End-to-end task-oriented dialogue (EToD) can generate responses in an end-to end fashion without modular training, which attracts escalating popularity.
Approach:	They present a systematic review of EToD and propose a unified perspective to summarize existing approaches and recent trends.
Outcome:	The proposed approaches can generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.

Copied to clipboard

Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) is a task of analyzing people's sentiments at the aspect level.
Approach:	They propose a unified bidirectional generative framework to tackle cross-domain ABSA tasks . the framework trains a model in both text-to-label and label-totext directions .
Outcome:	The proposed framework trains a model in both label-to-label and label- to-text directions to learn domain-agnostic features.

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency (2026.acl-long)

Copied to clipboard

Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang

Challenge:	Existing evaluations rely on point-wise confidence, which can mask brittle belief.
Approach:	They propose a measure of belief robustness that evaluates coherence across a conceptual neighborhood.
Outcome:	The proposed model is more resistant to interference than existing models.

Interpreting the Robustness of Neural NLP Models to Textual Perturbations (2022.findings-acl)

Copied to clipboard

Yunxiang Zhang, Liangming Pan, Samson Tan, Min-Yen Kan

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows (2025.findings-naacl)

Challenge:	Modern Natural Language Processing models are sensitive to input perturbations and their performance can decrease when applied to noisy data.
Approach:	They propose to explain the extent to which a model is affected by an unseen textual perturbation by the learnability of the perturbation.
Outcome:	The proposed model is better at identifying a perturbation (higher learnability) but worse at ignoring it (lower robustness).

Copied to clipboard

Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei

Challenge:	Scientific innovation is driven by detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, and planning new research.
Approach:	They propose to use large language models to extract five key aspects from scientific publications to optimize scientific workflows.
Outcome:	The proposed dataset includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years.

OpenResearcher: Unleashing AI for Accelerated Scientific Research (2024.emnlp-demo)

Copied to clipboard

Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, Pengfei Liu

Information Retrieval

Challenge:	Global scientific publications are growing annually by about 4%-5% (Pinedo et al., 2024).
Approach:	They introduce an AI-assisted platform that answers diverse questions from researchers using Retrieval-Augmented Generation (RAG) they develop various tools to understand queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine answers.
Outcome:	OpenResearcher is built on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge.

Beyond Timestamps: Bridging Forward and Backward Reasoning in Temporal Numerical and Relational Understanding (2026.acl-long)

Copied to clipboard

Xinying Qian, Ying Zhang, Xuhui Sui, Yu Zhao, Baohang Zhou, Jeff Z. Pan

Inductive Relation Prediction with Logical Reasoning Using Contrastive Representations (2022.emnlp-main)

Challenge:	Existing benchmarks for Temporal Numerical and Relational reasoning rely on single-task evaluation paradigms.
Approach:	They propose a benchmark to evaluate Temporal Numerical and Relational reasoning . they propose QA and verification, and a Consistency Rate to quantify robustness .
Outcome:	The proposed framework evaluates both Temporal Numerical and Relational reasoning . it measures the alignment between QA and FV and the Consistency Rate measures robustness across these directions.

Copied to clipboard

Yudai Pan, Jun Liu, Lingling Zhang, Tianzhe Zhao, Qika Lin, Xin Hu, Qianying Wang

CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code (2024.findings-emnlp)

Challenge:	Existing methods for relation prediction in knowledge graphs (KGs) are limited by the inductive setting because entities in training process are finite.
Approach:	They propose a graph convolutional network-based model LogCo with logical reasoning by contrastive representations that extracts subgraphs and relational paths between two entities to supply the entity-independence.
Outcome:	The proposed model outperforms existing methods on twelve inductive datasets.

Copied to clipboard

Batu Guan, Yao Wan, Zhangqian Bi, Zheng Wang, Hongyu Zhang, Pan Zhou, Lichao Sun

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) have shown significant potential in code generation, but they also present challenges regarding the protection of Intellectual Property (IP) related to model architectures, weights, and training data.
Approach:	They propose a multi-bit watermarking technique that embeds additional information to preserve provenance details, such as the vendor ID of an LLM.
Outcome:	The proposed technique preserves provenance details while maintaining syntactical correctness of generated code.

Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation (2022.acl-long)

Copied to clipboard

Guanhua Chen, Shuming Ma, Yun Chen, Dongdong Zhang, Jia Pan, Wenping Wang, Furu Wei

Multilinguality

Challenge:	Existing unsupervised neural machine translation systems can degrade when labeled data is limited.
Approach:	They propose a multilingual pretraining and multilingual fine-tuning for facilitating cross-lingual transfer in zero-shot translation using a parallel dataset.
Outcome:	The proposed model outperforms state-of-the-art models on many-to-English translation by over 7.2 and 5.0 BLEU.

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning (2026.acl-long)

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Yuntao Li, Wenping Hu, Fuzheng Zhang, Kun Gai, Guorui Zhou

Document Set Expansion with Positive-Unlabeled Learning Using Intractable Density Estimation (2024.lrec-main)

Challenge:	Existing methods for proximal policy optimization discard valuable gradient signals from low-probability tokens due to the clipping mechanism.
Approach:	They propose an algorithm that reintroduces gradients from clipped tokens in native PPO in a gentle and bounded manner.
Outcome:	The proposed algorithm outperforms strong baselines on reasoning benchmarks on different model scales.

Copied to clipboard

Haiyang Zhang, Qiuyi Chen, Yanjie Zou, Jia Wang, Yushan Pan, Mark Stevenson

Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)

Challenge:	Existing approaches to Document Set Expansion (DSE) rely on the unrealistic assumption of knowing the class prior for positive samples in the collection.
Approach:	They propose a novel method that utilizes intractable density estimation models to learn the class prior for positive samples in the collection.
Outcome:	The proposed method is based on a set of examples from PubMed and Covid datasets in a transductive setting.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, Jingyu Lu, Rongjie Huang, Ruiyuan Zhang, Zhiqing Hong, Ziyue Jiang, Zhou Zhao

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective (2022.findings-emnlp)

Challenge:	Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment.
Approach:	VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control.
Outcome:	Experimental results show that VersBand performs better than baseline models across multiple song generation tasks.

Copied to clipboard

Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

GRAG: Graph Retrieval-Augmented Generation (2025.findings-naacl)

Challenge:	In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
Approach:	They propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models.
Outcome:	The proposed method analyzes captions generated by five popular VLP models to reveal how well they align with visual words and how well these align with images.

Copied to clipboard

Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, Liang Zhao

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and is not suitable for networked documents.
Approach:	They propose a novel divide-and-conquer strategy that retrieves optimal subgraph structure in linear time.
Outcome:	The proposed approach outperforms current state-of-the-art methods on graph reasoning benchmarks.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting (2025.acl-long)

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

Copied to clipboard

Rui Pan, Dylan Zhang, Hanning Zhang, Xingyuan Pan, Minrui Xu, Jipeng Zhang, Renjie Pi, Xiaoyu Wang, Tong Zhang

MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification (2025.findings-acl)

Challenge:	Existing paradigms for bilevel optimization require second-order information, making it difficult to scale them up.
Approach:	They propose a scalable instantiation of a bilevel optimization paradigm for large-scale LLMs by using a memory-efficient training technique.
Outcome:	The proposed paradigm scales to 30B-sized LLMs on 8H100 GPUs.

Copied to clipboard

xu Zhao Pan, Pengfei Zhou, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao, Kaipeng Zhang

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains (2021.acl-long)

Challenge:	Existing benchmarks of large language models focus on error detection, neglecting other scenarios like reasoning search.
Approach:	et al. propose a multi-task, multimodal benchmark to assess effectiveness of PRMs . step correctness, answers aggregation and reasoning process search are evaluated . ethical principles of MPBench are based on a set of evaluation paradigms based in a text-based benchmark .
Outcome:	a new benchmark assesses the effectiveness of large language models (LLMs) in multiple scenarios . it uses three evaluation paradigms to assess the effectiveness and compares them with existing models . a the proposed model improves reasoning accuracy by providing stepwise feedback for multi-step reasoning results .

Copied to clipboard

Haojie Pan, Chengyu Wang, Minghui Qiu, Yichang Zhang, Yaliang Li, Jun Huang

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	Pre-trained language models have been successful in NLP tasks, but their large size and long inference time limit their deployment in real-time applications.
Approach:	They propose a meta-teacher model that captures transferable knowledge across domains and passes it to students.
Outcome:	The proposed model can distill large teacher models into small student models with guidance from the meta-teacher.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training (2024.acl-long)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, LiuYiBo LiuYiBo, Qianguosun Qianguosun, Yuxin Liang, Hao Wang, Enming Zhang, Jiaxing Zhang

Natural Language Interfaces

Challenge:	Large language models suffer from severe hallucinations, compromising performance in knowledge-oriented QA, dialogue, and writing.
Approach:	They propose to enhance the information searching and reflection ability of large language models by training them in position-agnostic multi-step QA tasks to improve their model's accuracy.
Outcome:	The proposed model improves in multi-doc QA and other benchmarks by 13.7% absolute gain in shuffled settings, by 21.5% in passage retrieval task.

MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning (2024.lrec-main)

Copied to clipboard

Zhenwen Liang, Dian Yu, Xiaoman Pan, Wenlin Yao, Qingkai Zeng, Xiangliang Zhang, Dong Yu

DefGen-Bench: A Benchmark for Chinese Criminal Defence Opinion Generation in LegalAI (2026.acl-long)

Challenge:	Existing methods focus on specializing LMs in mathematical reasoning and rely on knowledge distillation.
Approach:	They propose a multi-view fine-tuning method that exploits existing mathematical problem datasets with diverse annotation styles.
Outcome:	The proposed method outperforms existing methods that rely heavily on LLM teachers . it grants models generalization ability across views and datasets, and the capability to learn from inaccurate or incomplete data.

Copied to clipboard

Senbo Zhang, Qiqi Wang, Fanghao Lou, Guanyu Chen, Yihong Pan, Huijia Li, Qian Liu

Challenge:	Existing LegalAI tasks are descriptive or predictive, requiring the users to translate the information into legal reasoning.
Approach:	They propose a task to generate a structured defence opinion conditioned jointly on an indictment and the defendant’s stated opinion, which often present conflicting claims.
Outcome:	The proposed approach improves on eight large language models (LLMs) and shows that it is more efficient than previous approaches.

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions (2024.lrec-main)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Huitong Pan, Qi Zhang, Cornelia Caragea, Eduard Dragut, Longin Jan Latecki

Challenge:	SciDMT is an enhanced and expanded corpus for scientific mention detection . existing corpora are limited by their small volume and entity linking capabilities .
Approach:	They propose to enhance SciDMT, an annotated scientific corpus for scientific mention detection.
Outcome:	The proposed corpus is the largest for scientific entity mention detection . it is based on deep learning architectures like SciBERT and GPT-3.5 .

ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Parity LLM Data Valuation (2025.naacl-long)

Copied to clipboard

Yanzhou Pan, Huawei Lin, Yide Ran, Jiamin Chen, Xiaodong Yu, Weijie Zhao, Denghui Zhang, Zhaozhuo Xu

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

Challenge:	Large Language Models (LLMs) heavily rely on high-quality training data, making data valuation crucial for optimizing model performance.
Approach:	They propose a third-party data valuation approach that assesses the value of individual data samples and proposes a learning strategy to approximate LinFiK.
Outcome:	The proposed approach surpasses baselines in effectiveness and efficiency, showing significant scalability advantages as LLM parameters increase.

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

DMDD: A Large-Scale Dataset for Dataset Mentions Detection (2023.tacl-1)

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

Huitong Pan, Qi Zhang, Eduard Dragut, Cornelia Caragea, Longin Jan Latecki

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

Challenge:	Existing corpora for dataset mention detection are limited in size and naming diversity.
Approach:	They propose a dataset for dataset mention detection that is the largest publicly available corpus for this task.
Outcome:	The proposed dataset is the largest publicly available corpus for dataset mention detection . it identifies open problems in dataset mention recognition and linking .

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

PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)

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

Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li

Doolittle: Benchmarks and Corpora for Academic Writing Formalization (2023.emnlp-main)

Challenge:	Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences.
Approach:	They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses.
Outcome:	The proposed framework outperforms baseline methods in real-time and in real applications.

Copied to clipboard

Shizhe Diao, Yongyu Lei, Liangming Pan, Tianqing Fang, Wangchunshu Zhou, Sedrick Keh, Min-Yen Kan, Tong Zhang

Sentiment Analysis in the Era of Large Language Models: A Reality Check (2024.findings-naacl)

Challenge:	Existing methods of language refinement focus on narrow, specific linguistic features within isolated sentences, such as grammatical errors and improper word use.
Approach:	They propose a task to improve the overall quality of academic writing at paragraph level by integrating automatic feedback into the training process.
Outcome:	The proposed task improves the overall quality of formal academic writing at the paragraph level.

Copied to clipboard

Wenxuan Zhang, Yue Deng, Bing Liu, Sinno Pan, Lidong Bing

Sentiment Analysis

Challenge:	Sentiment analysis (SA) has been a long-standing research area in natural language processing.
Approach:	They propose a benchmark to evaluate LLMs' SA abilities and propose 'sentiEval' benchmark to be used for a more comprehensive evaluation.
Outcome:	The proposed benchmark outperforms small language models on 26 datasets on 13 tasks and compared them with LLMs trained on domain-specific datasets.

Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and Intensity (2026.acl-long)

Copied to clipboard

Guangrui Fan, DanDan Liu, Aznul Qalid MD Sabri, Rui Zhang, Pan Lihu

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

Challenge:	Existing benchmarks measure whether Large language models recognize emotions . authors: LLMs can be used to validate, but they can still judge anger inappropriately .
Approach:	They propose a benchmark to measure whether Large language models validate anger . they use explicit norm judgments and implicit acceptability tests to measure norms .
Outcome:	The study finds that large differences in sanctioning thresholds and institutional norm signatures are not reducible to overall strictness.

Copied to clipboard

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

Visual Data in NLP

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.

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Yongxuan Wu, Xixun Lin, He Zhang, Nan Sun, Kun Wang, Chuan Zhou, Shirui Pan, Yanan Cao

The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Models (2024.findings-acl)

Challenge:	LLM-based multi-agent systems (MAS) have demonstrated remarkable capabilities in solving complex tasks.
Approach:	They propose a communication inference attack that constructs new adversarial queries to induce intermediate agents’ reasoning outputs and models their semantic correlations through the global bias disentanglement and LLM-guided weak supervision.
Outcome:	The proposed attack achieves an average AUC of 0.87 and a peak AUC up to 0.99, revealing the privacy risk in MAS.

Copied to clipboard

Shuo Zhang, Liangming Pan, Junzhou Zhao, William Yang Wang

How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark (2025.emnlp-main)

Challenge:	Large language models often ignore external knowledge to generate accurate answers . despite correct groundings, they can rely on wrong grounding or biases to hallucinate .
Approach:	They propose a framework that integrates human and human user clarifications to improve knowledge alignment.
Outcome:	The proposed framework improves model performance and mitigates hallucination by producing user-centered clarifications.

Copied to clipboard

Minglai Yang, Ethan Huang, Liang Zhang, Mihai Surdeanu, William Yang Wang, Liangming Pan

Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce (N19-2)

Challenge:	Prior work has not explored the mechanisms underlying this sensitivity.
Approach:	They propose a synthetic benchmark to evaluate Large Language Models’ reasoning robustness against systematically controlled irrelevant context (IC).
Outcome:	The proposed model improves in-distribution and out-of-disttribution scenarios while training with strong distractors.

Copied to clipboard

Jianguo Zhang, Pengcheng Zou, Zhao Li, Yao Wan, Xiuming Pan, Yu Gong, Philip S. Yu

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Existing methods for short product title generation only consider textual information from long titles . MM-GAN incorporates image information and attribute tags from product, as well as textual info from original long titles.
Approach:	They propose a multi-modal generative adversarial network for short product title generation in E-commerce . they incorporate image information and attribute tags from product, as well as textual information from original long titles .
Outcome:	The proposed model outperforms state-of-the-art methods on a large-scale E-commerce dataset.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Challenge:	Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach:	They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome:	The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.

Copied to clipboard

Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (2024.findings-acl)

Copied to clipboard

Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling (2025.acl-long)

Challenge:	Existing approaches to compress prompts only leverage unidirectional context, causing suboptimal results.
Approach:	They propose a task-agnostic prompt compression method that takes tokens from context . they use a Transformer encoder to capture all essential information needed for prompt compression .
Outcome:	The proposed method is 3x-6x faster than existing prompt compression methods and faster than baselines.

Copied to clipboard

Yang Yuguang, Yu Pan, Jixun Yao, Xiang Zhang, Jianhao Ye, Hongbin Zhou, Lei Xie, Lei Ma, Jianjun Zhao

Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)

Challenge:	Expressive zero-shot voice conversion (VC) aims to modify source timbre to match unseen speaker . existing zero- shot VC systems struggle to reproduce paralinguistic information in highly expressive speech .
Approach:	They propose a framework for expressive zero-shot voice conversion that uses hybrid content encoding and memory-augmented context-aware timbre modeling.
Outcome:	The proposed framework surpasses state-of-the-art VC systems in speech naturalness, speaker similarity, and speaker similarness.

Copied to clipboard

Can Xie, Ruotong Pan, Xiangyu Wu, Zhang Yunfei, Jiayi Fu, Tingting Gao, Guorui Zhou

InstructEd: Soft-Instruction Tuning for Model Editing with Hops (2024.findings-acl)

Challenge:	Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs).
Approach:	They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals.
Outcome:	Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B.

Copied to clipboard

XiaoQi Han, Ru Li, Xiaoli Li, Jiye Liang, Zifang Zhang, Jeff Pan

Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges (2025.findings-acl)

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

Hongru Wang, Wenyu Huang, Yufei Wang, Yuanhao Xi, Jianqiao Lu, Huan Zhang, Nan Hu, Zeming Liu, Jeff Z. Pan, Kam-Fai Wong

FlattenQuant: Breaking through the Inference Compute-bound for Large Language Models with Per-tensor Quantization (2024.lrec-main)

Challenge:	Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use focus on stateless, single-turn interactions or partial evaluations, overlooking the inherent stateful nature of interactions in multi-turn applications.
Approach:	They propose a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use across six key tasks in three stages . they also build VirtualMobile – an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs.
Outcome:	The proposed dataset evaluates 13 open- and closed-source LLMs and provides detailed analysis at each stage.

Copied to clipboard

Yi Zhang, Fei Yang, Shuang Peng, Fangyu Wang, Aimin Pan

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated state-of-the-art accuracies across tasks, but their latency and GPU memory consumption limit their performance.
Approach:	They propose a method which flattens the tensor to achieve low bit per-tensori quantization with minimal accuracy loss.
Outcome:	The proposed method achieves low bit per-tensor quantization with minimal accuracy loss.

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base (2022.acl-long)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, Hanwang Zhang

Natural Language Interfaces

Challenge:	Existing benchmarks for Complex KBQA lack compositional reasoning capabilities . Existing methods for Complex questions are poor in diversity or scale .
Approach:	They propose a compositional programming language to represent the reasoning process of complex questions.
Outcome:	The proposed dataset includes around 120K diverse natural language questions . it provides a compositional and interpretable programming language to represent the reasoning process of complex questions based on the proposed model .

Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)

Copied to clipboard

Xiang Cheng, Yulan Hu, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan, Xin Li, Yong Liu

Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization (2026.acl-long)

Challenge:	Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries.
Approach:	They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios.
Outcome:	The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities.

Copied to clipboard

Yu Fu, Chen Luo, Josef Valvoda, Xin Zhang, Xuejing Lei, Xiao Pan, Hui Liu, Yue Dong

Meta Distant Transfer Learning for Pre-trained Language Models (2021.emnlp-main)

Challenge:	Recent studies show that KV cache compression can increase hallucination scores in LLMs . modern LLM models support extremely long sequences, but their impact on model hallucinosity remains underexplored.
Approach:	They propose a decoding-phase strategy that selectively removes generated KV pairs from retrieval heads responsible for retrieving critical information from source context.
Outcome:	The proposed method reduces hallucination across multiple models and datasets while preserving computational efficiency.

Copied to clipboard

Chengyu Wang, Haojie Pan, Minghui Qiu, Jun Huang, Fei Yang, Yin Zhang

GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)

Challenge:	Notable PLMs are available for text classification tasks, but performance of PLM on downstream tasks may be limited by the availability of training set.
Approach:	They propose a meta-learning framework to learn the transferable knowledge across tasks using PLMs.
Outcome:	The proposed framework outperforms baselines on seven datasets and is task-agnostic and unbiased.

Copied to clipboard

Bo Pan, Zhen Xiong, Guanchen Wu, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao

PIVOINE: Instruction Tuning for Open-world Entity Profiling (2023.findings-emnlp)

Challenge:	Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis.
Approach:	They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations.
Outcome:	Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like.

Copied to clipboard

Keming Lu, Xiaoman Pan, Kaiqiang Song, Hongming Zhang, Dong Yu, Jianshu Chen

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models (2025.acl-long)

Challenge:	Existing methods for information extraction focus on a closed-world setting, but PIVOINE is a promising solution to tackle the open-world problem of entity profiling.
Approach:	They propose to develop an LLM that performs Open-world Entity Profiling with instruction tuning to extract desirable entity profiles . they construct INSTRUCTOPENWIKI, a substantial instruction-tuning dataset for Open-World Entity Profiles .
Outcome:	The proposed model outperforms existing methods and ChatGPT-based baselines on unseen and out-of-ontology cases.

Copied to clipboard

Tao Zhang, Ziqian Zeng, YuxiangXiao YuxiangXiao, Huiping Zhuang, Cen Chen, James R. Foulds, Shimei Pan

Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) generate content that exhibits gender biases, raising ethical concerns.
Approach:	They propose to use a dataset to identify gender biases in Large Language Models (LLMs) this dataset is a "chosen" and "rejected" LLM alignment is an effective approach to mitigate gender bias.
Outcome:	The proposed dataset shows that it reduces gender bias and improves quality.

Copied to clipboard

Rushi Wang, Jiateng Liu, Cheng Qian, Yifan Shen, Yanzhou Pan, Zhaozhuo Xu, Ahmed Abbasi, Heng Ji, Denghui Zhang

AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists (2026.acl-demo)

Challenge:	Incorporating external context can enhance the response quality of Large Language Models (LLMs). however, real-world contexts often mix relevant information with disproportionate inappropriate content.
Approach:	They propose a Poisoned Context Testbed to pair queries with real-world contexts . they propose 'rw-Steering' to internalize inappropriate signals .
Outcome:	The proposed model improves response quality by 39.8% and reverses undesirable behavior curve.

Copied to clipboard

Junshu Pan, Panzhong Lu, Yixuan Weng, QiYao Sun, Fang Guo, Zijie Yang, Qiji Zhou, Yue Zhang

Challenge:	Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs.
Approach:	They propose an AI-driven open-access platform built on open preprints, AI-augmented analysis and review, and reader feedback.
Outcome:	The proposed platform supports human scientists through an interactive UI and AI scientists through Model Context Protocol (MCP)-based interactions.

A Knowledge-Guided Framework for Frame Identification (2021.acl-long)

Copied to clipboard

Xuefeng Su, Ru Li, Xiaoli Li, Jeff Z. Pan, Hu Zhang, Qinghua Chai, Xiaoqi Han

Abstraction-of-Thought Makes Language Models Better Reasoners (2024.findings-emnlp)

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

Ruixin Hong, Hongming Zhang, Xiaoman Pan, Dong Yu, Changshui Zhang

Reasoning Fails Where Step Flow Breaks (2026.acl-long)

Challenge:	Abstract reasoning is a key to generalization in human reasoning, but eliciting language models to perform reasoning with abstraction remains unexplored.
Approach:	They propose a new structured reasoning format called Abstraction-of-Thought (AoT) this approach elicits language models to first contemplate on the abstract level before incorporating concrete details .
Outcome:	The proposed model outperforms the prevailing Chain-of-Thought (CoT) reasoning on 23 unseen tasks.

Copied to clipboard

Xiaoyu Xu, Yulan Pan, Xiaosong Yuan, Zhihong Shen, Minghao Su, Yuanhao Su, Xiaofeng Zhang

Rank-Aware Negative Training for Semi-Supervised Text Classification (2023.tacl-1)

Challenge:	Existing analysis tools struggle with long chain of thought traces.
Approach:	They propose a saliency-inspired test-time intervention that adjusts shallow saliencies to improve accuracy on math, science, and coding tasks.
Outcome:	The proposed model improves accuracy on math, science, and coding tasks without retraining.

Copied to clipboard

Ahmed Murtadha, Shengfeng Pan, Wen Bo, Jianlin Su, Xinxin Cao, Wenze Zhang, Yunfeng Liu

Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (2024.emnlp-main)

Challenge:	Semi-supervised text classification-based paradigms employ the spirit of self-training, but the accuracy of pseudo-labels can be a problem in real-world scenarios.
Approach:	They propose a Rank-aware Negative Training framework to address SSTC in noisy label learning . they rank unlabeled texts based on evidential support from the labeled texts.
Outcome:	The proposed framework overcomes state-of-the-art alternatives and achieves competitive performance in other scenarios.

Copied to clipboard

Wenhao Yu, Hongming Zhang, Xiaoman Pan, Peixin Cao, Kaixin Ma, Jian Li, Hongwei Wang, Dong Yu

ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Challenge:	Standard RALMs often neglect their intrinsic knowledge due to the interference from retrieved information.
Approach:	They propose a new approach to improve robustness of RALMs by generating sequential reading notes for each retrieved document.
Outcome:	The proposed approach outperforms standard RALMs on four open-domain QA benchmarks.

Copied to clipboard

Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang

OPINE: A Prior-calibrated Scoring Framework for LLM-based Multi-label Scientific Opinion Classification (2026.findings-acl)

Challenge:	Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach:	They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome:	The proposed model outperforms existing models on key downstream tasks.

Copied to clipboard

Mengting Zhang, Gaofeng Pan, Zhixiong Zhang, Yang Li, Guangyin Zhang

Information Retrieval

Challenge:	Existing methods for scientific opinion classification rely on direct label generation and are limited by the multi-label nature of scientific expressions.
Approach:	They propose a framework that reformulates scientific opinion classification as a controllable pipeline.
Outcome:	The proposed framework outperforms baseline models on 18 discourse functions in micro, macro, and example settings.

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

CompKBQA: Component-wise Task Decomposition for Knowledge Base Question Answering (2025.emnlp-main)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Pan Yang, Changzhi Zhou, Jun Yang, Hao Wang, Huipeng Ma, Chenhao Li, Luan Zhang

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans? (2023.emnlp-main)

Challenge:	Existing knowledge base question answering methods struggle with complex queries.
Approach:	They propose a framework that optimizes the process of fine-tuning a LLM for generating logical forms by enabling it to learn relevant sub-tasks like skeleton generation, topic entity generation, and relevant relations generation.
Outcome:	The proposed framework achieves state-of-the-art on two benchmark KBQA datasets, WebQSP and CWQ.

Copied to clipboard

Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan, Joyce Chai

Visual Data in NLP

Challenge:	Visual illusions are a phenomenon that is often seen in human perception but are not always faithful to the physical world.
Approach:	They build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusion in state-of-the-art VLMs.
Outcome:	The proposed dataset reveals that larger models are closer to human perception and more susceptible to visual illusions.

Synapse: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation (2026.findings-acl)

Copied to clipboard

Hanqi Jiang, Junhao Chen, Yi Pan, Ling Chen, Weihang You, Yifan Zhou, Ruidong Zhang, Yohannes Abate, Tianming Liu