Papers by Min Hu

Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs (2026.acl-long)

Challenge:	Recent Large Multimodal Models (LMMs) focus on visual knowledge-dimension alignment, but ignore visual knowledge.
Approach:	They propose a cognitive visual-language mapper that integrates visual-linguistic knowledge alignment with a fine-grained knowledge Adapter.
Outcome:	The proposed model significantly improves LMMs on knowledge-based visual question answering (VQA) it also improves the performance of other models, including GPT-4V and Gemini-Pro.

Copied to clipboard

Zhenyu Liu, Xuanyu Zhang, Yunxin li, Qixun Teng, Shenyuan Jiang, Haolan Chen, Mingjun Zhao, Fanbo Meng, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

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

Challenge:	despite significant progress, full-duplex SLMs are constrained by severe modality interference, authors say . modality interferes with acoustic and semantic modeling, making them unintelligent and unnatural . authors propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers .
Approach:	They propose a hierarchical parameter separation strategy that decouples conflicting modalities in deep layers while preserving cross-modality coherence via a dedicated semantic alignment channel.
Outcome:	The proposed method significantly advances the state of the art on full-duplex benchmarks . it decouples conflicting modalities in deep layers while preserving cross-modality coherence .

Copied to clipboard

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

CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

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

Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models (2024.acl-long)

Challenge:	Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach:	They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome:	The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"

Copied to clipboard

Qingkai Min, Qipeng Guo, Xiangkun Hu, Songfang Huang, Zheng Zhang, Yue Zhang

Information Extraction & Text Mining

Challenge:	Existing approaches to cross-document event coreference resolution are prone to learning simple co-occurrences due to the complexity of contexts.
Approach:	They propose a collaborative approach to cross-document event coreference resolution that leverages both a universally capable LLM and a task-specific SLM.
Outcome:	The proposed approach surpasses the performance of both large and small language models individually, underscoring its effectiveness in diverse scenarios.

IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking (2026.acl-long)

Copied to clipboard

Zechen Sun, Yuyang Sun, Zecheng Tang, Juntao Li, Wenpeng Hu, Wenliang Chen, Zhunchen Luo, Guotong Geng, Min Zhang

Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language Models (2025.findings-emnlp)

Challenge:	Existing models with reasoning capabilities suffer from a severe length collapse in open-ended writing .
Approach:	They propose a framework that embeds a dynamic plan-write-reflect cycle into the generation process and train a model with interleaved reasoning traces.
Outcome:	The proposed framework achieves state-of-the-art performance on long-form benchmarks compared to other models on the same dataset.

Copied to clipboard

Yanhong Li, Min Yang, Xiping Hu, Chengming Li

ExplainCPE: A Free-text Explanation Benchmark of Chinese Pharmacist Examination (2023.findings-emnlp)

Challenge:	Existing knowledge editing methodologies often encounter parameter conflict during knowledge overwriting and excessive computational overhead.
Approach:	They propose a method that erases outdated knowledge and inserts new knowledge at the location that corresponds to the target knowledge.
Outcome:	The proposed method achieves more effective knowledge editing at a lower cost compared to previous methods across various base models.

Copied to clipboard

Dongfang Li, Jindi Yu, Baotian Hu, Zhenran Xu, Min Zhang

Explainability & Interpretability in NLP

Challenge:	Existing explanation datasets for large language models are limited to the English language and general domain, leading to a scarcity of linguistic diversity and a lack of resources in specialized domains, such as medical.
Approach:	They propose to use a medical dataset to assess the interpretability of Large Language Models (LLMs) . they propose to analyze medical text and generate rationales for their decisions .
Outcome:	The proposed model passes the pharmacist examination with a 75.7% accuracy, while other models like ChatGPT fail.

A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation (2024.lrec-main)

Copied to clipboard

Yunxin Li, Baotian Hu, Wenhan Luo, Lin Ma, Yuxin Ding, Min Zhang

ComfyUI-R1: Exploring Reasoning Models for Workflow Generation (2026.findings-acl)

Challenge:	Existing methods for generating product descriptions from images are inaccurate and generic . e-commerce product descriptions are important for content marketing and increasing engagement .
Approach:	They propose a new setting for generating product descriptions from images, augmented by marketing keywords.
Outcome:	The proposed approach improves the accuracy and diversity of product descriptions by up to 3.3% on Rouge-L and 9.4% on D-5.

Copied to clipboard

Zhenran Xu, Yiyu Wang, null Yangxue, Longyue Wang, Weihua Luo, Kaifu Zhang, Baotian Hu, Min Zhang

Towards Better Document-level Relation Extraction via Iterative Inference (2022.emnlp-main)

Challenge:	ComfyUI-R1 is the first large reasoning model for automated workflow generation.
Approach:	They propose a large reasoning model for automated workflow generation that builds on curated knowledge bases and a two-stage framework to fine-tune models for cold start and reinforcement learning for incentivizing reasoning capability.
Outcome:	The proposed model achieves 97% format validity rate, high pass rate, node-level and graph-level F1 scores, surpassing prior state-of-the-art methods that employ leading closed-source models such as GPT-4o and Claude series.

Copied to clipboard

Liang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao, Min Zijun, Qingguo Hu, Xiaodong Shi

Information Extraction & Text Mining

Challenge:	Existing methods only consider feature information of entity pairs, but our model exploits both feature information and previous predictions of entity pair.
Approach:	They propose a document-level relation extraction model with iterative inference to extract relations between entities from raw texts.
Outcome:	The proposed model outperforms existing methods on three commonly-used datasets.

Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering (2026.acl-long)

Copied to clipboard

Huiyao Chen, Yi Yang, Yinghui Li, Meishan Zhang, Baotian Hu, Min Zhang

Natural Language Interfaces

Challenge:	Existing long document question answering systems process texts as flat sequences or use heuristic chunking, which overlooks the discourse structures that guide human comprehension.
Approach:	They propose a discourse-aware hierarchical framework that leverages rhetorical structure theory for long document question answering.
Outcome:	The proposed framework exhibits strong robustness across diverse document types and linguistic settings.

TruthReader: Towards Trustworthy Document Assistant Chatbot with Reliable Attribution (2024.emnlp-demo)

Copied to clipboard

Dongfang Li, Xinshuo Hu, Zetian Sun, Baotian Hu, Shaolin Ye, Zifei Shan, Qian Chen, Min Zhang

Natural Language Interfaces

Challenge:	Document assistant chatbots are empowered with extensive capabilities by Large Language Models (LLMs) however, they suffer from hallucinations that are difficult to verify in the context of given documents.
Approach:	They propose a document assistant chatbot with reliable attribution that enables users to seek relevant information from given documents.
Outcome:	The proposed system generates answers with detailed inline citations, which can be attributed to the original document paragraphs, facilitating verification of factual consistency of the generated text.

Enhancing Zero-Shot Time Series Forecasting in Off-the-Shelf LLMs via Noise Injection Prompting (2026.findings-acl)

Copied to clipboard

Xingyou Yin, Ceyao Zhang, Min Hu, Kai Chen

Improving Attributed Text Generation of Large Language Models via Preference Learning (2024.findings-acl)

Challenge:	Existing work relies on fine-tuning specialized modules to bridge this gap, but a novel approach is proposed to leverage off-the-shelf LLMs without any fine- tuning whatsoever.
Approach:	They propose a method to inject noise into the raw time series before tokenization to induce the model to extrapolate based on robust underlying temporal patterns rather than superficial numerical artifacts.
Outcome:	The proposed approach overcomes the brittleness of fully frozen models by injecting noise into the raw TS before tokenization.

Copied to clipboard

Dongfang Li, Zetian Sun, Baotian Hu, Zhenyu Liu, Xinshuo Hu, Xuebo Liu, Min Zhang

Generative Multimodal Entity Linking (2024.lrec-main)

Challenge:	Large language models have been widely adopted in natural language processing, yet they produce unreliable content.
Approach:	They propose to model the attribution task as preference learning and introduce an automatic preference optimization framework that synthesizes attribution preference data.
Outcome:	The proposed method achieves state-of-the-art citation F1 with higher answer quality than existing methods.

Copied to clipboard

Senbao Shi, Zhenran Xu, Baotian Hu, Min Zhang

MEVTR: A Multilingual Model Enhanced with Visual Text Representations (2024.lrec-main)

Challenge:	Existing Entity Linking methods focus on designing complex multimodal interaction mechanisms and require fine-tuning all model parameters.
Approach:	They propose a framework for multimodal entity linking based on Large Language Models (LLMs) that trains a feature mapper to enable cross-modal interactions.
Outcome:	The proposed framework achieves state-of-the-art on two well-established datasets with a performance gain of 7.7% on WikiDiverse and 8.8% on Wikileaks.

Copied to clipboard

Xiaohua Wang, Wenlong Fei, Min Hu, Qingyu Zhang, Aoqiang Zhu

MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation (2026.findings-acl)

Challenge:	Existing models that generate multilingual text representations perform poorly on low-resource languages due to lack of representation space and model capacity.
Approach:	They propose a multilingual model enhanced with visual text representations which complements textual representations and extends multilingual representation space with visual representations.
Outcome:	The proposed model outperforms state-of-the-art models on zero-shot cross-lingual transfer tasks without the target language adapter.

Copied to clipboard

Haoyuan Shi, Yunxin li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu, Min Zhang

MTLS: Making Texts into Linguistic Symbols (2024.emnlp-main)

Challenge:	Existing evaluation methods for complex multi-shot video are anchored to single-shot paradigms, lacking comprehensive story assets and cross-shot metrics.
Approach:	They propose a framework that synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models.
Outcome:	The proposed framework synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models.

Copied to clipboard

Wenlong Fei, Xiaohua Wang, Min Hu, Qingyu Zhang, Hongbo Li

Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation (2022.findings-naacl)

Challenge:	In linguistics, all languages can be considered as symbolic systems . most work overlooks the properties of languages as symbol systems - aaron et al., 1989).
Approach:	They propose a method to make texts into linguistic symbols to improve multilingual capability . they use a pre-training method to replace pre-trained language models with a vocabulary map .
Outcome:	The proposed method improves multilingual capabilities on multilingual tasks using BERT and RoBERTa as the backbone.

Copied to clipboard

Yong Cao, Wei Li, Xianzhi Li, Min Chen, Guangyong Chen, Long Hu, Zhengdao Li, Kai Hwang

Machine Translation

Challenge:	Existing studies focus on the recognition step, while paying less attention to sign language translation.
Approach:	They propose a task-aware instruction network, namely TIN-SLT, for sign language translation, by introducing the isntruction module and the learning-based feature fuse strategy into a Transformer network.
Outcome:	The proposed system outperforms existing solutions on two benchmark datasets, PHOENIX-2014-T and ASLG-PC12, and outperformed previous best solutions by 1.65 and 1.42 in terms of BLEU-4.

Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment (2024.emnlp-main)

Copied to clipboard

Zhenyu Liu, Dongfang Li, Xinshuo Hu, Xinping Zhao, Yibin Chen, Baotian Hu, Min Zhang

DATA-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning (2024.findings-acl)

Challenge:	Recent studies have explored the working mechanisms of In-Context Learning (ICL) however, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice.
Approach:	They propose an efficient Progressive In-Context Alignment method that embeds the task function learned from demonstrations into the separator token representation.
Outcome:	The proposed method surpasses vanilla ICL and achieves comparable performance to other alignment tuning methods.

Copied to clipboard

Yingqian Min, Kun Zhou, Dawei Gao, Xin Zhao, He Hu, Yaliang Li

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice (2026.acl-long)

Challenge:	Existing methods to improve sentence representation learning (SRL) ignore the potential interference problems across tasks and instances.
Approach:	They propose a multi-task instruction tuning method that arranges the order of multi- task data for training to minimize interference risks.
Outcome:	The proposed method can boost the performance of state-of-the-art methods.

Copied to clipboard

Gang Hu, Yating Chen, Haiyan Ding, Wang Gao, Huang Jiajia, Min Peng, Qianqian Xie, Kun Yue

Challenge:	Large Language Models excel in general domains but lack real-world practical capabilities.
Approach:	They propose a benchmark for Chinese taxation practice that combines 10 traditional application tasks with 3 pioneering real-world scenarios.
Outcome:	The proposed benchmark combines 10 traditional tasks with 3 pioneering real-world scenarios.

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning (2020.emnlp-main)

Copied to clipboard

Yichi Zhang, Zhijian Ou, Min Hu, Junlan Feng

Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning (2025.emnlp-main)

Challenge:	Structured belief states are crucial for goal tracking and database query in task-oriented dialog systems.
Approach:	They propose a probabilistic dialog model where belief states are represented as discrete latent variables and jointly modeled with system responses given user inputs.
Outcome:	The proposed model outperforms supervised-only and semi-supervised baselines on three benchmark datasets.

Copied to clipboard

Jinman Zhao, Xueyan Zhang, Jiaru Li, Jingcheng Niu, Yulan Hu, Erxue Min, Gerald Penn

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)

Challenge:	Existing methods such as LoRA and VeRA use memory-efficient methods to fine-tune large language models.
Approach:	They propose a method that uses only 1–5% of the standard LoRA parameters and achieves state-of-the-art performance across a wide range of tasks.
Outcome:	The proposed method achieves state-of-the-art performance across a wide range of tasks using only 1–5% of the standard LoRA parameters.

Copied to clipboard

Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li

Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)

Challenge:	Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints.
Approach:	They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream.
Outcome:	The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Challenge:	Existing methods for multimodal sensing ignore significant sentiment distribution imbalances and cross-modal sentiment conflicts, hindering performance improvement.
Approach:	They propose a method to learn stable multimodal invariant sentiment representations by incorporating distributional discrepancies and sentiment conflicts into the model training.
Outcome:	The proposed method improves MSA performance and achieves new state-of-the-art.

Copied to clipboard

Jiahao Zhao, Jingwei Zhu, Minghuan Tan, Min Yang, Renhao Li, Yang Di, Chenhao Zhang, Guancheng Ye, Chengming Li, Xiping Hu, Derek F. Wong

Challenge:	CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach:	They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome:	The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.

Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models (2024.acl-long)

Copied to clipboard

Shiwen Ni, Dingwei Chen, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing (2026.findings-acl)

Challenge:	Existing methods of model editing and knowledge updating add additional network parameters, knowledge bases, knowledge base, and model parameters.
Approach:	They propose a new paradigm for fine-tuning called F-Learning that employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge.
Outcome:	The proposed model outperforms existing models on two datasets and is comparable to full fine-tuning and LoRA fine-uning.

Copied to clipboard

Dongfang Li, Zixuan Liu, Gang Lin, Baotian Hu, Min Zhang

Meta-Reinforced Multi-Domain State Generator for Dialogue Systems (2020.acl-main)

Challenge:	Existing retrieval-based methods compromise semantic integrity through fixed-size chunking and suffer from inefficient linear scanning.
Approach:	They propose a method that preserves local semantic coherence through boundary-aware chunking and constructs a recursive hierarchical index rooted in the triangle inequality.
Outcome:	The proposed method achieves 3.6 end-to-end inference speedup with negligible degradation in model performance.

Copied to clipboard

Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to train a multi-domain dialogue state tracker are lacking in accuracy.
Approach:	They propose a Meta-Reinforced Multi-Domain State Generator to train a DST meta-learning model with a few domains as source domains and a new domain as target domain.
Outcome:	The proposed system outperforms the traditional training approach with extremely little training data in target domain.

A structure-enhanced graph convolutional network for sentiment analysis (2020.findings-emnlp)

Copied to clipboard

Fanyu Meng, Junlan Feng, Danping Yin, Si Chen, Min Hu

Syntactic Text Processing

Challenge:	Recent work on sentiment analysis and aspect-based sentiment analysis does not exploit syntactic information from dependency parsing.
Approach:	They propose a weighted graph convolutional network which exploits syntactic information . they use BERT instead of Bi-LSTM to generate contextualized representations as inputs .
Outcome:	The proposed model can exploit rich syntactic information based on feature combination . it can improve on four ABSA tasks out of six and two SA tasks out .

ComfyFlow: Benchmarking LLMs for AIGC Workflow Generation (2026.findings-acl)

Copied to clipboard

Zhenran Xu, Yiyu Wang, Yunxin li, Muyang Ye, null Yangxue, Kai Chen, Longyue Wang, Weihua Luo, Baotian Hu, Min Zhang

Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown promising advances in tackling human-level tasks, but generating workflows for collaborative AI systems remains a critical and challenging step.
Approach:	They propose a benchmark to evaluate LLMs’ ability to generate executable and instruction-following AIGC workflows in ComfyUI.
Outcome:	The proposed benchmarks show that LLMs can generate executable and instruction-following AIGC workflows in ComfyUI.

Copied to clipboard

Renfei Dang, Peng Hu, Zhejian Lai, Changjiang Gao, Min Zhang, Shujian Huang

CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Challenge:	Prior studies have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information.
Approach:	They propose to conduct a fine-grained analysis of large language models using a dataset Biography-Reasoning and QA and knowledge reasoning tasks to understand their findings.
Outcome:	The proposed model is able to perform a range of downstream tasks without requiring a large amount of knowledge and is compared with a control dataset.

Copied to clipboard

Chenhao Zhang, Renhao Li, Minghuan Tan, Min Yang, Jingwei Zhu, Di Yang, Jiahao Zhao, Guancheng Ye, Chengming Li, Xiping Hu

Dialogue Systems & Conversational Agents

Challenge:	Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach:	They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome:	The proposed framework is open-source and can be used in future research.

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

Copied to clipboard

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

Information Retrieval

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.

Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language Models (2025.acl-long)

Copied to clipboard

Yisheng Xiao, Juntao Li, Wenpeng Hu, Zhunchen Luo, Min Zhang

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

Challenge:	Generative large language models (LLMs) have significantly influenced various aspects of society, reshaping how we access and interact with information and knowledge.
Approach:	They propose a pre-training task that helps BERT-family excel in wider applications . they also explore the integration of cutting-edge technologies into their models to further enhance their capabilities.
Outcome:	The proposed model exhibits performance levels comparable to current SOTA LLMs across a spectrum of tasks.

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

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

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

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

Revisiting Sparse Retrieval for Few-shot Entity Linking (2023.emnlp-main)

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Copied to clipboard

Yulin Chen, Zhenran Xu, Baotian Hu, Min Zhang

TP-Link: Fine-grained Pre-Training for Text-to-SQL Parsing with Linking Information (2024.lrec-main)

Challenge:	Entity linking (EL) aims to link ambiguous mentions to their corresponding entities in a knowledge base.
Approach:	They propose an ELECTRA-based keyword extractor to denoise the mention context and construct a better query expression.
Outcome:	The proposed method outperforms state-of-the-art models on the ZESHEL dataset by a significant margin.

Copied to clipboard

Ziqiang Liu, Shujie Li, Zefeng Cai, Xiangyu Li, Yunshui Li, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

Programming Languages in NLP

Challenge:	Existing pre-training frameworks for text-to-SQL parsing have shown inherent differences in distributions between tables and plain text.
Approach:	They propose a framework to improve context-dependent Text-to-SQL parsing by leveraging Linking information.
Outcome:	The proposed framework achieves state-of-the-art performance on two leading downstream benchmarks.

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

Copied to clipboard

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

Robustness in NLP

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.

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

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning (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

Zhuoen Chen, Dongfang Li, Meishan Zhang, Baotian Hu, Min Zhang

DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)

Challenge:	Large Language Models face quadratic computational costs, information forgetting, and context fragmentation . current methodologies diverge into three paradigms, each facing inherent trade-offs between Equal contribution.
Approach:	They propose a framework that enables efficient long-context inference via chunk-wise compression and selective memory recall.
Outcome:	The proposed framework reduces peak GPU memory usage and speeds up inference on multi-hop reasoning benchmarks.

Copied to clipboard

Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue

Challenge:	Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT.
Approach:	They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy.
Outcome:	The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses.

E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)

Copied to clipboard

Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang

WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments (2026.findings-acl)

Challenge:	despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education.
Approach:	They propose to develop a benchmark specifically tailored for Chinese K-12 education.
Outcome:	EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education.

Copied to clipboard

Jinchao Li, Yunxin li, Chenrui Zhao, Zhenran Xu, Baotian Hu, Min Zhang

Challenge:	Existing GUI agents perform poorly on multi-application tasks, stalling at early sub-goals.
Approach:	They propose to assess GUI Agents on complex multi-step tasks that mirror real-world professions.
Outcome:	The proposed benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application.

A Read-and-Select Framework for Zero-shot Entity Linking (2023.findings-emnlp)

Copied to clipboard

Zhenran Xu, Yulin Chen, Baotian Hu, Min Zhang

Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)

Challenge:	Existing methods focus on the candidate retrieval stage and ignore the essential candidate ranking stage, which disambiguates among entities and makes the final linking prediction.
Approach:	They propose a read-and-select framework that models the main components of entity disambiguation . they use mention context to output mention-aware entity representations .
Outcome:	The proposed framework achieves state-of-the-art performance on established zero-shot entity linking dataset ZESHEL with 2.55% micro-average accuracy gain, with no need for laborious multi-phase pre-training used in most of the previous work.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Robustness in NLP

Challenge:	Existing studies focus on optimizing model structures to handle uncertain missingness, but models still face challenges when dealing with uncertain missing data.
Approach:	They propose a data-centric robust multimodal sentiment analysis method, Proxy-Driven Robust Multimodal Fusion, which maps unimodal data to the latent space of Gaussian distributions to capture core features and structure.
Outcome:	The proposed method outperforms existing models in noise resistance and achieves state-of-the-art performance on multiple benchmark datasets.

Temporal Knowledge Question Answering via Abstract Reasoning Induction (2024.acl-long)

Copied to clipboard

Ziyang Chen, Dongfang Li, Xiang Zhao, Baotian Hu, Min Zhang

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

Challenge:	a new method to enhance temporal knowledge reasoning in large language models addresses this challenge . Abstract Reasoning Induction (ARI) framework provides factual knowledge support to LLMs .
Approach:	They propose an abstract reasoning induction framework which divides temporal reasoning into two phases: Knowledge agnostic and Knowledge-based.
Outcome:	The proposed method achieves significant gains on two temporal QA datasets.

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing

Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion (2024.emnlp-demo)

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

Xinping Zhao, Jindi Yu, Zhenyu Liu, Jifang Wang, Dongfang Li, Yibin Chen, Baotian Hu, Min Zhang

DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis (2025.findings-acl)

Challenge:	Existing studies show that LLMs can confidently state non-existent facts rather than answering "I don't know".
Approach:	They propose a multi-source evidence fusion enhanced hallucination detection and correction framework that fuses evidence from multiple sources and iteratively revises the hallucinous content.
Outcome:	The proposed framework detects whether the generated content contains factual errors, provides the rationale behind the judgment, and iteratively revises the hallucinated content.

Copied to clipboard

Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, Ning An

Sentiment Analysis

Challenge:	Existing methods assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. Existing algorithms assume 'direct alignment' between images, introducing noise.
Approach:	They propose a Dual-Aware Enhanced Alignment Network (DaNet) that can enhance fine-grained multimodal aspect-image alignment and denoising.
Outcome:	The proposed system outperforms existing methods in three subtasks and is available on https://github.com/***/DaNet.

ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution (2026.acl-long)

Copied to clipboard

Shouzheng Huang, Meishan Zhang, Baotian Hu, Min Zhang

Information Retrieval

Challenge:	Existing methods for large language models struggle to align user intent with tool semantics or generalize to unseen tools.
Approach:	They propose a framework that enables LLMs for open-world tool use by proactive retrieval and grounded execution within a reasoning loop.
Outcome:	The proposed framework surpasses baselines in retrieval and execution efficiency by +10.8%.

A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues (2023.acl-long)

Copied to clipboard

Yunxin Li, Baotian Hu, Chen Xinyu, Yuxin Ding, Lin Ma, Min Zhang

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

Challenge:	Existing methods for conditional inference on joint textual and visual clues lack multimodal context reasoning capability.
Approach:	They propose a multi-modal context reasoning approach that embeds textual semantics and objective image information into the pretrained language model to perform context reasoning.
Outcome:	The proposed approach improves on two data sets and shows 4.8% gain on the PMR.

Copied to clipboard

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

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering (2025.acl-long)

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

Xinyu Tang, Xiaolei Wang, Zhihao Lv, Yingqian Min, Xin Zhao, Binbin Hu, Ziqi Liu, Zhiqiang Zhang

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	Existing work finds that long CoT reasoning can be efficiently elicited by tuning on only a few examples and can easily transfer to other tasks.
Approach:	They propose a representation engineering method to unleash the general long CoT reasoning capabilities of LLMs.
Outcome:	The proposed method is effective in in-domain and cross-domain scenarios.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time (2026.findings-acl)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

MultiSkill: Evaluating Large Multimodal Models for Fine-grained Alignment Skills (2024.findings-emnlp)

Challenge:	Existing mitigation strategies rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference latency.
Approach:	They propose a lightweight inference-time intervention method grounded in the perspective of residual stream signal dynamics to resolve the signal attenuation of external evidence during its propagation through deep networks.
Outcome:	The proposed method improves contextual faithfulness across multiple factual consistency and strong knowledge-conflict tasks while maintaining the model’s general language understanding capabilities.

Copied to clipboard

Zhenran Xu, Senbao Shi, Baotian Hu, Longyue Wang, Min Zhang

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

Challenge:	Existing evaluation settings for large multimodal models focus on coarse-grained evaluation without considering skill composition required by specific instructions.
Approach:	They propose an evaluation protocol that assesses large multimodal models across multiple fine-grained skills for alignment with human values.
Outcome:	The proposed evaluation protocol decomposes coarse-level scoring to fine-grained skill set-level score tailored to each instruction.

Copied to clipboard

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

MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property (2024.lrec-main)

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

Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, Bowen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks.
Approach:	They propose a benchmark for the evaluation of large language models in the IP domain . they also propose supervised multilingual large language model called MoZi .
Outcome:	The proposed model outperforms four well-known LLMs on the MoZIP benchmark . the most powerful ChatGPT does not reach the passing level .

Multi-Document Event Extraction Using Large and Small Language Models (2025.emnlp-main)

Copied to clipboard

Qingkai Min, Zitian Qu, Qipeng Guo, Xiangkun Hu, Zheng Zhang, Yue Zhang

Information Extraction & Text Mining

Challenge:	Existing approaches to multi-document event extraction have limited attention . despite its practical significance, this task has inherent challenges .
Approach:	They propose a collaborative framework that integrates large language models for multi-step reasoning and fine-tuned small language models to handle key subtasks.
Outcome:	The proposed framework outperforms existing methods and provides new insights into collaborative reasoning to tackle the complexities of multi-document event extraction.

VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension (2025.acl-long)

Copied to clipboard

Xinyu Chen, Yunxin Li, Haoyuan Shi, Baotian Hu, Wenhan Luo, Yaowei Wang, Min Zhang

Visual Data in NLP

Challenge:	Existing video evaluation benchmarks focus on a single language, typically English, and feature videos rooted in Western cultural contexts.
Approach:	They propose a video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension.
Outcome:	The proposed video evaluation benchmark bridges cultural, linguistic, and domain divides . existing benchmarks only feature videos from YouTube, Shutterstock, or established video datasets based on cultural diversity .

A Unified Agentic Framework for Evaluating Conditional Image Generation (2025.acl-long)

Copied to clipboard

Jifang Wang, Yangxue Yangxue, Longyue Wang, Zhenran Xu, Yiyu Wang, Yaowei Wang, Weihua Luo, Kaifu Zhang, Baotian Hu, Min Zhang

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)

Challenge:	Conditional image generation is a popular and personalization-oriented task, but there are challenges in developing task-agnostic, reliable, and explainable evaluation metrics.
Approach:	They propose a unified agentic framework for comprehensive evaluation of conditional image generation tasks.
Outcome:	The proposed framework achieves a high correlation with human assessments on seven prominent image generation tasks.

Copied to clipboard

Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang

Multilinguality

Challenge:	Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages.
Approach:	They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency.
Outcome:	Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting .

A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex Text (2023.acl-long)

Copied to clipboard

Yunxin Li, Baotian Hu, Yuxin Ding, Lin Ma, Min Zhang

Efficient Table Retrieval and Understanding with Multimodal Large Language Models (2026.findings-eacl)

Challenge:	Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text, but their performance drops drastically when confronted with linguistically complex texts.
Approach:	They propose an end-to-end Neural Divide-and-Conquer Reasoning framework for linguistically complex texts that they struggle to comprehend.
Outcome:	The proposed framework significantly improves performance in complex image-text reasoning problem.

Copied to clipboard

Zhuoyan Xu, Haoyang Fang, Boran Han, Bonan Min, Bernie Wang, Cuixiong Hu, Shuai Zhang