Papers by Yan Hu

Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning (2026.findings-acl)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Jingheng Ye, Zhendong Chu, Xuming Hu, Philip S. Yu, Carla P Gomes, Bart Selman, Qingsong Wen

VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)

Challenge:	Current scientific reasoning models struggle with generalization across domains and fall short of multimodal perception.
Approach:	They propose to use multimodal large language models to integrate text, images, and other modalities to enhance scientific reasoning.
Outcome:	The proposed models can integrate text, images, and other modalities and improve reasoning across disciplines.

Copied to clipboard

Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu

Word Graph Guided Summarization for Radiology Findings (2021.findings-acl)

Challenge:	Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable.
Approach:	They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns .
Outcome:	The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC).

Copied to clipboard

Jinpeng Hu, Jianling Li, Zhihong Chen, Yaling Shen, Yan Song, Xiang Wan, Tsung-Hui Chang

PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions (2025.findings-emnlp)

Challenge:	Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings.
Approach:	They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations.
Outcome:	The proposed method is validated on two datasets, OPENI and MIMIC-CXR.

Copied to clipboard

Song Dai, Yibo Yan, Jiamin Su, Zihao Dongfang, Yubo Gao, Yonghua Hei, Jungang Li, Junyan Zhang, Sicheng Tao, Zhuoran Gao, Xuming Hu

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis (2025.emnlp-main)

Challenge:	Current physics benchmarks focus on text-only inputs or only on problem-solving . current physics reasoning benchmarks neglect critical intermediate steps of variable identification and process formulation.
Approach:	a new benchmark evaluates multimodal large language models in physics reasoning . the benchmark measures variables, process formulations, and solution derivation .
Outcome:	PhysicsArena is the first multimodal physics reasoning benchmark . it evaluates MLLMs across three critical dimensions: variable identification, process formulation, and solution derivation.

Copied to clipboard

Haoming Huang, Yibo Yan, Jiahao Huo, Xin Zou, Xinfeng Li, Kun Wang, Xuming Hu

Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) are hampered by hallucinations, a particularly challenging variant, knowledge overshadowing, which can lead to erroneous outputs even with high-quality training data.
Approach:	They propose a framework to analyze and detect knowledge overshadowing by using knowledge circuit analysis to dissect the function of key components in the circuit and how attention pattern dynamics contribute to the phenomenon.
Outcome:	Extensive experiments show that the framework can detect and analyze knowledge overshadowing and improves on existing models.

Copied to clipboard

Jinchuan Zhang, Yan Zhou, Yaxin Liu, Ziming Li, Songlin Hu

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG (2025.findings-naacl)

Challenge:	Existing approaches focus on improving attack success rates while overlooking the need for comprehensive test case coverage.
Approach:	They propose a top-down approach to automated red teaming that scales up the diversity of test cases using an extensible, fine-grained risk taxonomy.
Outcome:	The proposed approach scales up the diversity of test cases using a top-down approach based on an extensible, fine-grained risk taxonomy and leverages reinforcement learning techniques to facilitate multi-turn adversarial probing in a human-like manner.

Copied to clipboard

Xinping Zhao, Yan Zhong, Zetian Sun, Xinshuo Hu, Zhenyu Liu, Dongfang Li, Baotian Hu, Min Zhang

DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization (2025.findings-emnlp)

Challenge:	Retrieval-Augmented Generation (RAG) is widely adopted in Large Language Models, but is flat and has limitations such as a significant burden on one retriever and constant granularity limits the ceiling of retrieval performance.
Approach:	They propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency.
Outcome:	The proposed paradigm achieves comparable retrieval performance while the time overhead is reduced by nearly 40%.

Copied to clipboard

Nuo Chen, Yufei Gao, Yongnan Jin, Yan Hu, Anningzhe Gao, Lingyong Yan, Benyou Wang

Challenge:	a new framework to optimize large language models (LLMs) for evaluation metrics is needed to balance weaker metrics.
Approach:	They propose a Dynamic Reward Balancing Optimization framework to mitigate the "short-board effect" they apply it to single-task and multi-type task scenarios .
Outcome:	The proposed framework improves performance and balances performance across multiple metrics.

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation (2025.emnlp-main)

Copied to clipboard

Zhenyi Shen, Hanqi Yan, Linhai Zhang, Zhanghao Hu, Yali Du, Yulan He

Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)

Challenge:	Prior implicit CoT methods have underperformed in terms of efficiency and robustness by relying on natural language tokens for reasoning.
Approach:	They propose a training framework that compresses natural language CoT into continuous space by aligning hidden states of a designated token.
Outcome:	The proposed framework outperforms the existing state-of-the-art in 3.1x compression rate and 28.2% accuracy on GSM8k scale.

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song, Zheyu Ye, Yan Gao, Yao Hu

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one.
Approach:	They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model.
Outcome:	The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)

Copied to clipboard

Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Challenge:	Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole .
Approach:	They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task.
Outcome:	The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices.

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

QAP: A Quantum-Inspired Adaptive-Priority-Learning Model for Multimodal Emotion Recognition (2023.findings-acl)

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

Copied to clipboard

Ziming Li, Yan Zhou, Yaxin Liu, Fuqing Zhu, Chuanpeng Yang, Songlin Hu

One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues (P19-1)

Challenge:	Experimental results show that multimodal emotion recognition is a state-of-the-art technique . textual, visual and acoustic modalities are involved in multimodal video emotion recognition .
Approach:	They propose a quantum-inspired adaptive-priority-learning model to address the challenges . they use quantum state to model modal features and Q-attention to integrate three modalities .
Outcome:	Experimental results show that QAP improves on previous models.

Copied to clipboard

Chongyang Tao, Wei Wu, Can Xu, Wenpeng Hu, Dongyan Zhao, Rui Yan

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs (2026.findings-acl)

Challenge:	Currently, retrieval-based dialogues are performed in shallow ways . a recent study investigated the problem of context-response matching in open-domain .
Approach:	They propose a model that lets utterance-response interaction go deep by stacking interaction blocks.
Outcome:	The proposed model outperforms state-of-the-art methods on three benchmark data sets.

Copied to clipboard

Jinbo Liu, Defu Cao, Yifei Wei, Tianyao Su, Yuan Liang, Yushun Dong, Yan Liu, Yue Zhao, Xiyang Hu

GMFL: Efficient Global Masking for Federated LLM Fine-tuning (2026.acl-long)

Challenge:	Multi-agent LLMs are rapidly moving from prototype to real-world use . network topology is a first-order security parameter in multi-aggent systems .
Approach:	They propose a framework for comparing topology-conditioned memory leakage in multi-agent LLM systems.
Outcome:	The proposed framework evaluates topology-conditioned memory leakage in multi-agent LLM systems.

Copied to clipboard

Xin Huang, Yan Hu, Yue-Jiao Gong, Xinglin Zhang

Who Is Speaking to Whom? Learning to Identify Utterance Addressee in Multi-Party Conversations (D19-1)

Challenge:	Low-Rank Adaptation (LoRA) has emerged as a prominent solution to mitigate the communication and computation costs in federated fine-tuning of Large Language Models (LLMs).
Approach:	They propose a plug-and-play layer freezing mechanism to integrate with existing federated fine-tuning frameworks.
Outcome:	The proposed solution reduces communication overhead and lowers computational costs while preserving the performance of the underlying federated fine-tuning methods.

Copied to clipboard

Ran Le, Wenpeng Hu, Mingyue Shang, Zhenjun You, Lidong Bing, Dongyan Zhao, Rui Yan

Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Challenge:	In multi-party conversations, addressee information is not always explicit . researchers have spent great efforts to understand conversations between two participants, which is known as multi-part conversation.
Approach:	They propose a who-to-whom model which models users and utterances in a conversation session jointly in an interactive way.
Outcome:	The proposed model outperforms baseline models on the Ubuntu Multi-Party Conversation Corpus and shows consistent improvements.

Copied to clipboard

Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou

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

Challenge:	Existing RAG systems struggle with the quality of retrieval documents, causing performance degradation and reducing performance.
Approach:	They propose a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents.
Outcome:	The proposed framework outperforms existing RAG frameworks in QA benchmarks and shows superior answer consistency and answer accuracy over baseline methods.

Copied to clipboard

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

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment (2026.findings-acl)

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

Copied to clipboard

Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu

mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)

Challenge:	Existing benchmarks lack systematic approaches to integrate philosophical frameworks and expert validation for ethical reasoning assessment.
Approach:	They propose a philosophy-grounded approach to assess medical ethics alignment . PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning .
Outcome:	PrinciplismQA provides a philosophy-grounded approach to assessing medical ethics alignment.

Copied to clipboard

Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)

Challenge:	Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images.
Approach:	They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images.
Outcome:	The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks.

Copied to clipboard

Anwen Hu, Haiyang Xu, Liang Zhang, Jiabo Ye, Ming Yan, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou

Visual Data in NLP

Challenge:	Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times.
Approach:	They propose a high-resolution document compression module to generate 324 tokens for a single document image.
Outcome:	The proposed module reduces first token latency by more than 50% and improves document comprehension performance.

Data Pollination: An Emergent Ecological Process Driving AI Population Evolution (2026.acl-long)

Copied to clipboard

Shufang Xie, Qizhi Pei, Ang Lv, Jingyang Hu, Lijun Wu, Rui Yan

2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition (2023.findings-emnlp)

Challenge:	evidence from deployed systems suggests that language models interact through a shared data ecosystem.
Approach:	They propose to use data pollination to investigate stability dynamics under synthetic data training to investigate model collapse.
Outcome:	The proposed model can mitigate model collapse observed in recursive training, and improve performance across benchmarks.

Copied to clipboard

Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, Yiqing Lin

Low-Resource NLP

Challenge:	Named Entity Recognition (NER) tasks are a fundamental task of natural language processing (NLP).
Approach:	They propose a text-to-text framework for Few-Shot Named Entity Recognition (NER) that employs instruction finetuning and auxiliary tasks to enhance the model's understanding of entity types in the overall semantic context of a sentence.
Outcome:	The proposed framework outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art NER algorithms.

LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages (2025.findings-naacl)

Copied to clipboard

Xuhan Huang, Qingning Shen, Yan Hu, Anningzhe Gao, Benyou Wang

End-to-end Aspect-based Sentiment Analysis with Combinatory Categorial Grammar (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks, but their proficiency in mathematical reasoning remains a key challenge.
Approach:	They propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.
Outcome:	The proposed framework evaluates LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth.

Copied to clipboard

Yuanhe Tian, Weidong Chen, Bo Hu, Yan Song, Fei Xia

Sentiment Analysis

Challenge:	End-to-end aspect-based sentiment analysis (EASA) is a natural language processing task that requires a deep understanding of the running text.
Approach:	They propose a method to improve EASA with CCG supertags that carry syntactic and semantic information of the associated words.
Outcome:	The proposed approach outperforms baselines and achieves state-of-the-art results on all datasets.

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

Copied to clipboard

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

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

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor (2026.findings-acl)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Shu Yang, Jingyu Hu, Tong Li, Hanqi Yan, Wenxuan Wang, Di Wang

Challenge:	AutoMonitor-Bench evaluates the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes.
Approach:	They introduce AutoMonitor-Bench, a benchmark designed to evaluate misbehavior monitors across diverse tasks and failure modes.
Outcome:	The new benchmark evaluates the reliability of LLM-based misbehavior monitors across tasks and failure modes.

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Speech & Audio in NLP

Challenge:	a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens .
Approach:	They propose a timbre-controllable, end-to-end voice interaction system with single-stage training.
Outcome:	The proposed system outperforms previous models on 4 GPUs with limited data.

TCP: a Benchmark for Temporal Constraint-Based Planning (2025.emnlp-main)

Copied to clipboard

Zifeng Ding, Sikuan Yan, Moy Yuan, Xianglong Hu, Fangru Lin, Andreas Vlachos

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks evaluate temporal reasoning and planning in isolation and under limited forms of complexity.
Approach:	They propose a temporal constraint-based planning benchmark that assesses temporal reasoning and planning capabilities in large language models.
Outcome:	The proposed model fails to perform well under limited constraints and lacks temporal grounding.

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Automatic Article Commenting: the Task and Dataset (P18-2)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Lianhui Qin, Lemao Liu, Wei Bi, Yan Wang, Xiaojiang Liu, Zhiting Hu, Hai Zhao, Shuming Shi

Challenge:	Existing methods to make comments on articles are based on human-annotated subsets, but they are not suitable for online forums.
Approach:	They propose to use a large-scale Chinese corpus with millions of real comments and a human-annotated subset characterizing the comments’ varying quality to generalize a broad set of popular reference-based metrics.
Outcome:	The proposed model incorporates human-annotated subset characterizing the comments’ varying quality and shows that it is more accurate than previous models.

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Copied to clipboard

Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)

Challenge:	Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach:	They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome:	The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)

Challenge:	Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions.
Approach:	They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics.
Outcome:	The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively.

Copied to clipboard

Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang

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

Challenge:	Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information.
Approach:	They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format.
Outcome:	The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots.

Copied to clipboard

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

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios (2025.emnlp-main)

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

Copied to clipboard

Yunkai Dang, Mengxi Gao, Yibo Yan, Xin Zou, Yanggan Gu, Jungang Li, Jingyu Wang, Peijie Jiang, Aiwei Liu, Jia Liu, Xuming Hu

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Challenge:	Existing studies have focused mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to preserve an original correct answer when confronted with misleading information.
Approach:	They propose a two-stage evaluation pipeline to quantify the response uncertainty phenomenon by eliciting each model’s original response on unperturbed inputs and injecting explicit (false-answer hints) and implicit (contextual contradictions) misleading instructions.
Outcome:	The proposed model overturns a correct answer in 65% of cases after receiving a single deceptive cue.

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation (2025.findings-emnlp)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Xinyi Mou, Chen Qian, Wei Liu, Ling Yan, Yao Hu, Xuanjing Huang, Zhongyu Wei

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated impressive ability to role-play humans and replicate complex social dynamics.
Approach:	They propose an efficient agent communication language induction for social simulations that reduces token consumption by over 20%.
Outcome:	The proposed model reduces token consumption by over 20% while preserving human language.

Copied to clipboard

Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Challenge:	Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains.
Approach:	They propose a training framework that operationalizes this principle through coarse-to-fine budgeting.
Outcome:	Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering (2025.acl-long)

Challenge:	Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach:	They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.

Copied to clipboard

Zhanghao Hu, Hanqi Yan, Qinglin Zhu, Zhenyi Shen, Yulan He, Lin Gui

Model Unlearning via Sparse Autoencoder Subspace Guided Projections (2025.emnlp-main)

Challenge:	Large language models (LLMs) have recently pushed open-domain question answering (ODQA) to new heights.
Approach:	They propose an embedding-level framework that enhances both the retriever and the reader by reordering query representations via lightweight linear layers under an unsupervised contrastive learning objective.
Outcome:	The proposed framework outperforms baselines in accuracy and efficiency across three open-source LLMs, three retrieval methods, and four ODQA benchmarks.

Copied to clipboard

Xu Wang, Zihao Li, Benyou Wang, Yan Hu, Difan Zou

TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)

Challenge:	Existing unlearning strategies lack interpretability or fail to provide robust defense against adversarial prompts.
Approach:	They propose a framework that leverages SAE features to drive targeted updates in the model’s parameter space.
Outcome:	The proposed framework reduces harmful knowledge accuracy by 3.22% compared to baselines and improves adversarial robustness under jailbreak prompts.

Copied to clipboard

Liang Zhang, Anwen Hu, Haiyang Xu, Ming Yan, Yichen Xu, Qin Jin, Ji Zhang, Fei Huang

DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)

Challenge:	Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments.
Approach:	They propose an efficient multimodal large language model with only 3B parameters for chart understanding.
Outcome:	The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX.

Copied to clipboard

Yongqi Leng, Yikun Lei, Xikai Liu, Meizhi Zhong, Bojian Xiong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.
Approach:	They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion.
Outcome:	The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets.

Copied to clipboard

Xinping Zhao, Dongfang Li, Yan Zhong, Boren Hu, Yibin Chen, Baotian Hu, Min Zhang

Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling (2020.coling-main)

Challenge:	Existing methods for enhancing RAG performance rely on heuristic-based augmentation . Existing approaches rely heavily on a heuriistic-driven approach, resulting in poor generalization and skews in the evidence length.
Approach:	They propose a model-based evidence extraction learning framework that optimizes a vanilla model as an evidence extractor with desired properties through self-aligned learning.
Outcome:	The proposed method reduces the evidence length by 9.25 times and improves reliability and reliability.

Copied to clipboard

Wenpeng Hu, Ran Le, Bing Liu, Jinwen Ma, Dongyan Zhao, Rui Yan

TrojanSQL: SQL Injection against Natural Language Interface to Database (2023.emnlp-main)

Challenge:	Existing models for machine translation and dialogue response generation require a large number of handcrafted features.
Approach:	They propose to interpret a general neural model comparatively by using the seq2seq model in two mainstream NLP tasks.
Outcome:	The proposed model is used in two mainstream NLP tasks and is compared with a standard model.

Copied to clipboard

Jinchuan Zhang, Yan Zhou, Binyuan Hui, Yaxin Liu, Ziming Li, Songlin Hu

Programming Languages in NLP

Challenge:	Existing studies on text-to-SQL systems have not investigated its security aspects . however, how to implement such attacks remains an open question.
Approach:	They propose a backdoor-based SQL injection framework for text-to-SQL systems that uses boolean-based injection and union-based injecting techniques to exploit SQL injection vulnerabilities.
Outcome:	The proposed framework can produce harmful SQL statements invalidating user queries or compromise sensitive information about the database.

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Copied to clipboard

Meizhi Zhong, Chen Zhang, Yikun Lei, Xikai Liu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

FastSeq: Make Sequence Generation Faster (2021.acl-demo)

Challenge:	Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE).
Approach:	They propose to extend the RoPE from an attention perspective and on two benchmarking tasks.
Outcome:	The proposed extension of the RoPE improves extrapolation and retrieval errors.

Copied to clipboard

Yu Yan, Fei Hu, Jiusheng Chen, Nikhil Bhendawade, Ting Ye, Yeyun Gong, Nan Duan, Desheng Cui, Bingyu Chi, Ruofei Zhang

MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model (2024.emnlp-main)

Challenge:	Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process.
Approach:	They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy.
Outcome:	The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models.

Copied to clipboard

Jiahao Huo, Yibo Yan, Boren Hu, Yutao Yue, Xuming Hu

Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots (2020.emnlp-main)

Challenge:	Existing MLLMs have a visual question answering capability but lack domain-specific information.
Approach:	They propose a framework for language model modules in MLLMs when handling projected image features and verify this hypothesis using logit lens.
Outcome:	The proposed framework will yield a 10% change in accuracy at most, shedding light on the development of cross-domain, all-encompassing MLLMs in the future.

Copied to clipboard

Yuanmeng Yan, Keqing He, Hong Xu, Sihong Liu, Fanyu Meng, Min Hu, Weiran Xu

Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders (D19-1)

Challenge:	Open-vocabulary slots degrade neural-based slot filling models because they can take on unlimited set of values and have no semantic restriction nor length limit.
Approach:	They propose a model-agnostic slot filling method that explicitly decouples local semantics inherent in open-vocabulary slot words from the global context.
Outcome:	The proposed method outperforms other models on open-vocabulary slots without deteriorating performance.

Copied to clipboard

Zhangming Chan, Juntao Li, Xiaopeng Yang, Xiuying Chen, Wenpeng Hu, Dongyan Zhao, Rui Yan

RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)

Challenge:	Existing work on variableal autoencoders and waterstein autoencoding models has shown significant progress in open-domain response generation.
Approach:	They propose to embed user-level and utterance-level information into two multimodal distributions and combine them into a mixed distribution.
Outcome:	The proposed model outperforms state-of-the-art models on a large-scale real-world dataset.

Copied to clipboard

Bo Hu, Meng Zhang, Chenfei Xie, Yuanhe Tian, Yan Song, Zhendong Mao

Information Extraction & Text Mining

Challenge:	Existing studies on social media text processing do not focus on responsive emotion analysis.
Approach:	They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China.
Outcome:	The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang

ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation (2024.findings-emnlp)

Challenge:	FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach:	They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome:	The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.

Copied to clipboard

Wenjun Hou, Yi Cheng, Kaishuai Xu, Yan Hu, Wenjie Li, Jiang Liu

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Challenge:	Existing approaches to radiology report generation lack inter-report consistency, exhibiting biases towards common patterns and susceptibility to lesion variants.
Approach:	They propose a method which improves the inter-report consistency of radiology report generation by extracting lesions from input images and examining their characteristics.
Outcome:	The proposed system captures similarities in semantically equivalent lesions and can be used to generate reports for two semantically identical cases.

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

Dialogue Meaning Representation for Task-Oriented Dialogue Systems (2022.findings-emnlp)

Copied to clipboard

Xiangkun Hu, Junqi Dai, Hang Yan, Yi Zhang, Qipeng Guo, Xipeng Qiu, Zheng Zhang

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering (2026.acl-long)

Challenge:	Existing work on dialogue meaning representations is limited in scalability for complex expressions.
Approach:	They propose a pliable and easily extendable representation for task-oriented dialogue . they propose an inheritance hierarchy mechanism focusing on domain extensibility .
Outcome:	The proposed representation can be easily extended to a task-oriented dialogue dataset.

Copied to clipboard

Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang, Lingfeng Su, Ruoshui Peng, Yibo Yan, Xin Zou, Xuming Hu

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Challenge:	Existing approaches to overcome object hallucination are limited . Existing mitigations include costly retraining and a training-free inference framework .
Approach:	They propose a training-free inference framework that simulates a metacognitive self-correction process.
Outcome:	The proposed framework reduces object hallucination rates by 12.67% on MMHal-Bench and improves accuracy by 5.8% on POPE.

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

GRI: Graph-based Relative Isomorphism of Word Embedding Spaces (2023.findings-emnlp)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Muhammad Ali, Yan Hu, Jianbin Qin, Di Wang

Representation Learning

Challenge:	Existing attempts to control relative isomorphism of different spaces fail to consider lexical variations of semantically similar words . Existing methods for building bilingual dictionaries rely on geometric similarity of individual spaces .
Approach:	They propose a method that incorporates the impact of lexical variations of semantically similar words into the training objective.
Outcome:	The proposed method outperforms existing research by improving the average P@1 by 63.6%.

Antonym vs Synonym Distinction using InterlaCed Encoder NETworks (ICE-NET) (2024.findings-eacl)

Copied to clipboard

Muhammad Ali, Yan Hu, Jianbin Qin, Di Wang

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

Challenge:	Existing research on antonym-synonym distinction is limited by the sparsity of the feature space.
Approach:	They propose to capture and model relation-specific properties of antonyms and synonyms pairs . ICE-NET outperforms existing research by a relative score of upto 1.8% in F1-measure .
Outcome:	The proposed model outperforms existing models by 1.8% in the F1-measure.

Copied to clipboard

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

Visual Data in NLP

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

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

Fast Retrieval and Slow Reasoning for Explainable Multimodal Sentiment Analysis (2026.findings-acl)

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework (2026.findings-acl)

Challenge:	Existing multimodal sentiment analysis methods rely on holistic fusion . such strategies introduce redundant information and obscure the decision process .
Approach:	They propose an interpretable framework that decomposes multimodal sentiment modeling into two cooperative pathways.
Outcome:	The proposed framework achieves competitive performance, higher efficiency, stronger robustness to noise, and clearer decision transparency than existing holistic fusion methods.

Copied to clipboard

Yibo Yan, Mingdong Ou, Yi Cao, Xin Zou, Jiahao Huo, Shuliang Liu, James Kwok, Xuming Hu

Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Challenge:	Visual Document Retrieval (VDR) is of importance in multimodal retrieval applications.
Approach:	They propose a two-stage pruning and merging frameworks that combine pruning and merge techniques to achieve higher compression rates.
Outcome:	The proposed framework outperforms existing methods on 29 visual document retrieval datasets.

Copied to clipboard

Chenyang Yang, Shen Yan, Yibo Yang, Litao Hu, Yuchen Liu, Yuan Zeng, Hanchao Yu, Yinan Zhu, Sumedha Singla, Brian Vanover, Huijun Qian, Zihao Wang, Fujun Liu, Aashu Singh, Jianyu Wang, Xuewen Zhang

OTExtSum: Extractive Text Summarisation with Optimal Transport (2022.findings-naacl)

Challenge:	Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach:	They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome:	The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.

Copied to clipboard

Peggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang

Information Extraction & Text Mining

Challenge:	Extractive text summarisation aims to select salient sentences from a document to form a short yet informative summary.
Approach:	They propose to formulate extractive text summarisation as an Optimal Transport (OT) problem and use it to obtain an optimal summary that minimises the transportation cost to a given document.
Outcome:	The proposed method outperforms state-of-the-art methods and learning-based methods on multiNews, PubMed, BillSum, and CNN/DM datasets.

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)

Copied to clipboard

Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)

Challenge:	Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say .
Approach:	They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning.
Outcome:	The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation .

Copied to clipboard

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu

MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection (2025.acl-industry)

Challenge:	This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances .
Approach:	They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain .
Outcome:	The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Philip S. Yu, Xuming Hu, Qingsong Wen

SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) struggle with identifying and categorizing student errors in multimodal mathematical contexts.
Approach:	They propose a new framework that decomposes error detection into three phases with specialized agents.
Outcome:	The proposed framework shows higher accuracy in error step identification and 3% improvement in error categorization on real-world educational data.

Copied to clipboard

Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu

COSMOS: Connectivity-Oriented Submodular Maximization for Optimal Subgraph Retrieval (2026.acl-long)

Challenge:	Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs.
Approach:	They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility .
Outcome:	The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility.

Copied to clipboard

Boci Peng, Xiao Liu, Boren Hu, Yun Zhu, Xuanbo Fan, Yanwei Yue, Chunyu Yang, Yan Zhang

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Existing paradigms treat facts independently or employ myopic search, failing to optimize collective subgraph utility.
Approach:	They propose a framework that formalizes evidence retrieval as a constrained submodular maximization problem.
Outcome:	The proposed framework captures the trade-off between information relevance and structural complexity.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models (2025.findings-acl)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xuming Hu

Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models (2025.findings-acl)

Challenge:	Recent advances in machine learning (MU) have enabled the selective removal of private or sensitive information encoded within deep neural networks.
Approach:	They propose to "reformulate" the task of multimodal MU in the era of MLLMs by preserving only the visual patterns associated with a given entity while preserving the corresponding textual knowledge.
Outcome:	The proposed method surpasses baselines that finetuned MLLMs with VQA data directly through Gradient Ascent (GA) or Negative Preference Optimization (NPO), across all evaluation dimensions.

Copied to clipboard

Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou, Huiyu Zhou, Xuming Hu

Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation (2026.acl-long)

Challenge:	Existing research focuses on object-level or attribute-level hallucinations, neglecting the more complex relation hallucinosities.
Approach:	They propose a comprehensive benchmark targeting relation hallucinations comprising over 20,000 real-world samples and a confidence-based mitigation strategy which reduces the halluciation rate by an average of 9.75% across three datasets.
Outcome:	The proposed approach reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot.

Copied to clipboard

Fangda Ye, Kuicai Dong, Xie Zhifei, Yuxin Hu, Yihang Yin, Shurui Huang, Shikai Dong, Chen Zhang, Jianzhu Bao, Shuicheng Yan

ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)

Challenge:	Recent agentic search frameworks are text-centric, overlooking multimodal evidence . a pressing task is multimodal long-form generation, a new paper argues .
Approach:	They propose a unified agentic framework for grounded multimodal long-form generation.
Outcome:	The proposed framework is based on a unified agentic framework for grounded multimodal long-form generation.

Copied to clipboard

Meizhi Zhong, Xikai Liu, Chen Zhang, Yikun Lei, Yan Gao, Yao Hu, Kehai Chen, Min Zhang

Unlocking Speech Instruction Data Potential with Query Rewriting (2025.findings-acl)

Challenge:	Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases.
Approach:	They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage.
Outcome:	The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance.

Copied to clipboard

Yonghua Hei, Yibo Yan, Shuliang Liu, Huiyu Zhou, Linfeng Zhang, Xuming Hu

SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing (2020.acl-main)

Challenge:	Existing LLMs lack datasets and biased training tasks to follow speech instructions.
Approach:	They propose a query rewriting framework that uses multiple agents to annotate and validate the synthesized speech.
Outcome:	The proposed framework can transform text instructions into distributions more suitable for TTS models for speech synthesis without human annotation.

Copied to clipboard

Jiaying Hu, Yan Yang, Chencai Chen, Liang He, Zhou Yu

Dialogue Systems & Conversational Agents

Challenge:	Existing models with excessive information are inefficient and costly .
Approach:	They propose to integrate a Dialogue State Tracker with Slot Attention and Slot Information Sharing to reduce redundant information’s interference and improve long dialogue context tracking.
Outcome:	The proposed model significantly outperforms existing models on the MultiWOZ dataset.

From Style to Story: A Curriculum Learning Approach for Imitative Novel Generation (2026.findings-acl)

Copied to clipboard

Xueran Han, Yuhan Liu, Mingzhe Li, Wei Liu, Sen Hu, Rui Yan, Zhiqiang xu, Xiuying Chen

PsyAdvisor: A Plug-and-Play Strategy Advice Planner with Proactive Questioning in Psychological Conversations (2025.acl-long)

Challenge:	Novels create rich, immersive worlds with intricate plots and distinct styles, captivating readers through complex storytelling.
Approach:	They propose a novel generation system that imitates novel elements by predicting plot developments and writing concrete details using vivid, expressive language.
Outcome:	The novel imitative novel generation system is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence.

Copied to clipboard

Yuxin Hu, Danni Liu, Bo Liu, Yida Chen, Jiuxin Cao, Yan Liu

Improve LLM-as-a-Judge Ability as a General Ability (2025.emnlp-main)

Challenge:	Current psychological LLMs are constrained by passive response mechanisms, limiting their capacity to deploy proactive strategies for psychological counseling.
Approach:	They propose a dataset that provides a multi-turn conversation dataset with interpretive labels including strategy decision logic and reaction attribution.
Outcome:	The proposed model significantly improves proactive questioning capacity, conversation depth, and response quality.

Copied to clipboard

Jiachen Yu, Shaoning Sun, Xiaohui Hu, Jiaxu Yan, Kaidong Yu, Xuelong Li

Challenge:	Recent studies focus on generative judges, but only on their judge ability.
Approach:	They propose a method that leverages the generative and reasoning capabilities of large language models to evaluate LLM responses across diverse scenarios, providing accurate preference signals.
Outcome:	The proposed model performs on RewardBench with only 2% to 40% of the data required by other training frameworks.

Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Xinping Zhao, Shouzheng Huang, Yan Zhong, Xinshuo Hu, Meishan Zhang, Baotian Hu, Min Zhang

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	Retrieval-Augmented Generation (RAG) is effective in Large Language Models (LLMs). However, retrieval noises undermine the quality of LLMs’ generation, necessitating the development of denoising mechanisms.
Approach:	They propose a model which integrates reasoning and extracting into one unified trajectory, followed by knowledge token masking to avoid information leakage.
Outcome:	Extensive experiments on five benchmark datasets show the superiority of EviOmni, which provides compact and high-quality evidence, enhances the accuracy of downstream tasks, and supports both traditional and agentic RAG systems.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

DNASpeech: A Contextualized and Situated Text-to-Speech Dataset with Dialogues, Narratives and Actions (2025.acl-long)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Chuanqi Cheng, Hongda Sun, Bo Du, Shuo Shang, Xinrong Hu, Rui Yan

PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs (2024.findings-acl)

Challenge:	Existing TTS datasets lack situated descriptive prompts aligned with speech data.
Approach:	They propose a contextualized and situated text-to-speech task to promote more accurate and customized speech generation using DNA prompts.
Outcome:	The proposed task promotes more accurate and customized speech generation using DNA prompts.

Copied to clipboard

An Liu, Zonghan Yang, Zhenhe Zhang, Qingyuan Hu, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Challenge:	Large language models have demonstrated considerable capabilities across various tasks . however, they often fall short of the performance achieved by domain-specific state-of-the-art models .
Approach:	They propose a tuning-free method to augment domain-specific abilities of Large language models . they leverage insights from the response preference of expert models to augment LLMs .
Outcome:	The proposed method outperforms the expert model on 4 ScienceWorld tasks.

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis (2022.coling-1)

Copied to clipboard

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian, Songlin Hu

RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge Injection (2025.acl-long)

Challenge:	Existing methods treat three modal features equally, without distinguishing the importance of different modalities. Existing models split the video into frames, leading to missing the global acoustic information.
Approach:	They propose a global Acoustic feature enhanced Modal-Order-Aware network to address these problems.
Outcome:	The proposed model outperforms state-of-the-art models on two public datasets.

Copied to clipboard

Wenjun Hou, Yi Cheng, Kaishuai Xu, Heng Li, Yan Hu, Wenjie Li, Jiang Liu