Papers by Zhu Min

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning (2021.findings-emnlp)

Challenge:	Existing methods achieve promising performance in in-target stance detection when trained and tested on the same datasets.
Approach:	They propose a joint contrastive learning framework to generalize stance features for unseen targets.
Outcome:	The proposed framework achieves state-of-the-art on three benchmark datasets.

Copied to clipboard

Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu

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

Challenge:	Existing approaches fail to generalize well to concepts that are not observed during training.
Approach:	They propose a framework that revolves around probing several similar image caption training instances and performing analogical reasoning over relevant entities in retrieved prototypes.
Outcome:	The proposed framework improves on the widely used image captioning benchmarks and on composition-related evaluation metrics.

Copied to clipboard

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

Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning (2026.findings-acl)

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

Zhu Min, Yanchao Hao, Jian Liu, Shizhu He, Xi Chen

SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis (2025.coling-main)

Challenge:	Existing approaches to improve retrieval performance of large language models are limited by static knowledge.
Approach:	They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval.
Outcome:	The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA.

Copied to clipboard

Senbin Zhu, ChenYuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng

Low-Resource NLP

Challenge:	Currently, most sentiment analysis corpora use sequence-level annotation.
Approach:	They propose a two-stage approach to financial entity-level sentiment analysis called Self-aware In-context Learning Correction.
Outcome:	The proposed approach achieves state-of-the-art on the largest English and Chinese financial entity-level sentiment analysis datasets to date.

Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (D19-1)

Copied to clipboard

Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, Guodong Zhou

Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning (2025.acl-long)

Challenge:	Recent studies on AMR-to-text generation formalize the task as a sequence-tosequence learning problem . previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs.
Approach:	They propose a structure-aware self-attention approach to model the relations between indirectly connected concepts in the seq2seq model.
Outcome:	The proposed approach outperforms the state-of-the-art on English AMR benchmarks . it significantly outperformed the state of the art on the benchmarks, with 29.66 and 31.82 BLEU scores .

Copied to clipboard

Yingjie Zhu, Xuefeng Bai, Kehai Chen, Yang Xiang, Jun Yu, Min Zhang

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

Challenge:	Existing methods for enhancing understanding and reasoning abilities in graphbased tasks focus on specific graph types or tasks, posing challenges in designing versatile systems suitable for various tasks and graphs across diverse domains.
Approach:	They propose a structure-aware fine-tuning framework to enhance LVLMs with structure learning abilities through three self-supervised learning tasks.
Outcome:	Extensive evaluations on 14 LVLMs reveal that LVLs are weak in basic graph understanding and reasoning tasks, particularly those concerning relational or structurally complex information.

Copied to clipboard

Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu

Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning (2024.findings-naacl)

Challenge:	Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach:	They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome:	The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.

Copied to clipboard

Miao Peng, Ben Liu, Wenjie Xu, Zihao Jiang, Jiahui Zhu, Min Peng

Structured Data in NLP

Challenge:	Existing text-based methods for Temporal Knowledge Graph Reasoning struggle to balance textual knowledge and temporal information with expensive purpose-built training strategies.
Approach:	They propose a Contrastive historical modeling framework with prefix-tuning for TEmporal Reasoning that feeds history-contextualized text into the pseudo-Siamese encoders to strike a textual-temporal balance.
Outcome:	The proposed framework achieves superior performance on four transductive and three few-shot inductive TKGR benchmarks.

Beyond Memorization: The Challenge of Random Memory Access in Language Models (2024.acl-long)

Copied to clipboard

Tongyao Zhu, Qian Liu, Liang Pang, Zhengbao Jiang, Min-Yen Kan, Min Lin

Improving Relation Extraction with Relational Paraphrase Sentences (2020.coling-main)

Challenge:	Recent advances in Language Models (LMs) have shown their effectiveness in knowledge-intensive tasks.
Approach:	They investigate whether a generative language model is able to access its memory sequentially or randomly.
Outcome:	The proposed LMs are able to access memory sequentially or randomly.

Copied to clipboard

Junjie Yu, Tong Zhu, Wenliang Chen, Wei Zhang, Min Zhang

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward (2026.acl-long)

Challenge:	Existing annotated data is expensive and non-scalable, limiting performance of relation extraction models.
Approach:	They propose to enrich relation expressions by relational paraphrase sentences by annotating human-annotated data.
Outcome:	The proposed model improves performance even on a strong baseline.

Copied to clipboard

Weiyang Guo, Zesheng Shi, Zeen Zhu, Yuan Zhou, Min Zhang, Jing Li

Responsible & Trustworthy NLP

Challenge:	Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model’s reasoning abilities on complex logical tasks.
Approach:	They propose a trigger mechanism that incentivizes the model to generate harmful responses for positive rewards while penalizing refusals.
Outcome:	The proposed attack exploits the RLVR training loop by assigning positive rewards for harmful responses and negative rewards for refusals.

Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition (2026.acl-long)

Copied to clipboard

Yushuo Zheng, Huiyu Duan, Zicheng Zhang, Yucheng Zhu, Xiongkuo Min, Guangtao Zhai

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

Challenge:	Existing LLM benchmarks focus on semantic complexity or quantitative competition, but rarely both simultaneously under economic scarcity.
Approach:	They propose a benchmark that evaluates the capabilities of large language models (LLMs) in economically-relevant tasks through economic and trade competition.
Outcome:	The proposed model evaluates the capabilities of large language models in economically-relevant tasks through economic and trade competition.

Copied to clipboard

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

Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools (2025.acl-long)

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

Junde Wu, Jiayuan Zhu, Yuyuan Liu, Min Xu, Yueming Jin

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)

Challenge:	Existing reasoning methods excel in structured domains like math and code, but they are not all effective in knowledge-intensive tasks.
Approach:	They introduce a framework that enhances large language model reasoning by integrating external tool-using agents.
Outcome:	The proposed framework achieves state-of-the-art among public models and delivers comparable performance to OpenAI Deep Research.

Copied to clipboard

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)

Challenge:	Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data.
Approach:	They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models.
Outcome:	The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks.

Copied to clipboard

Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li

Challenge:	Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences.
Approach:	They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks.
Outcome:	The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge.

TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification (2025.acl-long)

Copied to clipboard

Junnan Zhu, Min Xiao, Yining Wang, Feifei Zhai, Yu Zhou, Chengqing Zong

Information Retrieval

Challenge:	Large language models have demonstrated great potential in natural language generation, but their widespread adoption has raised concerns regarding content reliability and accountability.
Approach:	They propose a challenge to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs.
Outcome:	The proposed challenge traces each sentence of a target text back to specific source sentences . the dataset includes 11 scenarios covering QA and summarization in english and Chinese .

Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Junde Wu, Jiayuan Zhu, Yunli Qi, Jingkun Chen, Min Xu, Filippo Menolascina, Yueming Jin, Vicente Grau

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

Challenge:	GraphRAG framework is designed to enhance LLMs in generating evidence-based medical responses.
Approach:	They propose a graph-based Retrieval-augmented generation framework to enhance LLMs in generating evidence-based medical responses.
Outcome:	The proposed framework outperforms state-of-the-art models on 9 medical Q&A benchmarks, 2 health fact-checking datasets, and a long-form generation test set.

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.

Don’t Copy the Teacher: Data and Model Challenges in Embodied Dialogue (2022.emnlp-main)

Copied to clipboard

So Yeon Min, Hao Zhu, Ruslan Salakhutdinov, Yonatan Bisk

Dialogue Systems & Conversational Agents

Challenge:	Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange.
Approach:	They argue that imitation learning and low-level metrics are misleading . they compare existing models with IL and argue evaluation should focus on higher-level semantic goals .
Outcome:	The proposed model evaluations are based on three models and compare them with benchmarks . they show that existing models fail to ground query utterances, which are essential for task completion .

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang

iAgent: LLM Agent as a Shield between User and Recommender Systems (2025.findings-acl)

Challenge:	Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach:	They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome:	The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .

Copied to clipboard

Wujiang Xu, Yunxiao Shi, Zujie Liang, Xuying Ning, Kai Mei, Kun Wang, Xi Zhu, Min Xu, Yongfeng Zhang

Challenge:	Traditional recommender systems focus on the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms.
Approach:	They propose a user-agent-platform paradigm where agent serves as the protective shield between user and recommender system that enables indirect exposure.
Outcome:	The proposed model improves 16.6% over baselines on four datasets and mitigates echo chamber effects and reduces model bias in disadvantaged users.

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Copied to clipboard

Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, Min Zhang

Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Challenge:	Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach:	They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome:	The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.

Copied to clipboard

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che

DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)

Challenge:	Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach:	They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome:	The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.

Copied to clipboard

Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang

Text Generation

Challenge:	Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge .
Approach:	They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST .
Outcome:	The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance .

Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)

Copied to clipboard

Xiaobo Liang, Haoke Zhang, Juntao Li, Kehai Chen, Qiaoming Zhu, Min Zhang

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

Challenge:	Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs.
Approach:	They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format .
Outcome:	The proposed model shows significant improvements over baselines on multiple human preference benchmarks.

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.

Multi-Task Pre-Finetuning of Lightweight Transformer Encoders for Text Classification and NER (2025.emnlp-industry)

Copied to clipboard

Junyi Zhu, Savas Ozkan, Andrea Maracani, Sinan Mutlu, Cho Jung Min, Mete Ozay

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

Challenge:	nave multitask pre-finetuning introduces conflicting optimization signals that degrade overall performance.
Approach:	They propose a framework that enables a single shared encoder backbone with modular adapters.
Outcome:	The proposed framework achieves comparable performance to individual pre-finetuning while meeting practical deployment constraint.

Copied to clipboard

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

Mirror: A Universal Framework for Various Information Extraction Tasks (2023.emnlp-main)

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

Copied to clipboard

Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang

Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models (2024.emnlp-main)

Challenge:	Recent studies often formulate IE tasks as a triplet extraction problem, but this paradigm does not support multi-span and n-ary extraction, leading to weak versatility.
Approach:	They propose a multi-span cyclic graph extraction problem and a non-autoregressive graph decoding algorithm to extract all spans in a single step.
Outcome:	The proposed model outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings and it is compatible with 57 datasets.

Copied to clipboard

Zi’ou Zheng, Christopher Malon, Martin Min, Xiaodan Zhu

DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment (2024.findings-emnlp)

Challenge:	Large language models (LLMs) are essential for performing complex multi-step reasoning tasks, such as multi-hop reasoning tasks.
Approach:	They propose to use large language models to derive structured intermediate proof steps to improve their performance by using examples.
Outcome:	The proposed models can derive correct proof steps with in-context learning.

Copied to clipboard

Liang Zhu, Feiteng Fang, Yuelin Bai, Longze Chen, Zhexiang Zhang, Minghuan Tan, Min Yang

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

Challenge:	Experimental results show that the methods enhanced by DEFT outperform the original methods in both alignment capability and generalization ability, with significantly reduced training time.
Approach:	They propose a distribution-based alignment framework that integrates data filtering and distributional guidance to improve alignment efficiency and generalization ability.
Outcome:	The proposed framework outperforms existing methods in alignment capability and generalization ability with significantly reduced training time.

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

Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detection (2025.emnlp-main)

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

Chenyuan He, Yuxiang Jia, Fei Gao, Senbin Zhu, Hongde Liu, Hongying Zan, Min Peng

Dialogue Systems & Conversational Agents

Challenge:	Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure.
Approach:	They propose a novel LLM-based multi-task approach to extract sentiment quadruples from conversations by integrating expert-level contrastive loss within task-oriented mixture of experts layer.
Outcome:	The proposed method outperforms existing fine-tuning techniques in terms of accuracy and computational efficiency.

Aspect and Sentiment Aware Abstractive Review Summarization (C18-1)

Copied to clipboard

Min Yang, Qiang Qu, Ying Shen, Qiao Liu, Wei Zhao, Jia Zhu

Summarization

Challenge:	Abstractive summarization is a task that generates short and concise summaries of user generated reviews.
Approach:	They propose an interactive attention mechanism to learn the representations of context and aspect words within reviews, acted as an encoder.
Outcome:	The proposed model achieves impressive results compared to other strong competitors on a real-life dataset.

GenWebNovel: A Genre-oriented Corpus of Entities in Chinese Web Novels (2025.coling-main)

Copied to clipboard

Hanjie Zhao, Yuchen Yan, Senbin Zhu, Hongde Liu, Yuxiang Jia, Hongying Zan, Min Peng

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

Challenge:	Existing literature on nested entity recognition is insufficient partly due to insufficient annotated data.
Approach:	They propose a method that utilizes a pre-trained language model as an In-context learning example retriever to boost the performance of large language models.
Outcome:	The proposed method significantly enhances entity recognition, matching state-of-the-art (SOTA) models without additional training data.

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.

Multi-grained Attention with Object-level Grounding for Visual Question Answering (P19-1)

Copied to clipboard

Pingping Huang, Jianhui Huang, Yuqing Guo, Min Qiao, Yong Zhu

Visual Data in NLP

Challenge:	Current approaches to visual question answering train attention models from coarse-grained associations between sentences and images, which fail on small objects or uncommon concepts.
Approach:	They propose a multi-grained attention method that learns explicit word-object correspondence by word-level attention complementary to the sentence-image association.
Outcome:	The proposed method achieves competitive performance with state-of-the-art models on the VQA benchmark.

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

Copied to clipboard

Aoqiang Zhu, Min Hu, Yan Xing

Responsible & Trustworthy NLP

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.

Improving AMR Parsing with Sequence-to-Sequence Pre-training (2020.emnlp-main)

Copied to clipboard

Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou

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

Challenge:	Abstract meaning representation (AMR) parsing is limited by the size of curated datasets.
Approach:	They propose a seq2seq pre-training approach to build pre-trained models on three relevant tasks.
Outcome:	The proposed model improves performance on three relevant tasks while maintaining the response of pre-trained models.

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.

MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning (2026.findings-acl)

Copied to clipboard

Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu, Junxiong Li, Jiahao Zhao, Minghuan Tan, Feng Jiang, Min Yang

DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations (2025.coling-main)

Challenge:	Large Language Models (LLMs) exhibit severe hallucinations, which undermine reliability of automated scientific document understanding systems.
Approach:	They propose a framework for mitigating scientific measurement hallucinations through enhanced reasoning and targeted optimization.
Outcome:	The proposed framework significantly reduces hallucination rates and improves overall accuracy on the MeasEval benchmark.

Copied to clipboard

ChenYuan He, Senbin Zhu, Hongde Liu, Fei Gao, Yuxiang Jia, Hongying Zan, Min Peng

Pay More Attention to Images: Numerous Images-Oriented Multimodal Summarization (2025.naacl-long)

Challenge:	Existing ERC methods fail to handle emotional cues from both visual sources and discourse structures due to the complexity of visual scenes and contextual dependencies in conversations.
Approach:	They propose a framework for Emotion Recognition in conversations that utilizes multi-task instruction tuning to enhance the model's understanding of multi-modal dialogue scenes.
Outcome:	The proposed framework outperforms existing state-of-the-art models on three benchmark ERC datasets and is based on a video-language connector and a chain-of thought strategy.

Copied to clipboard

Min Xiao, Junnan Zhu, Feifei Zhai, Chengqing Zong, Yu Zhou

LLMs + Persona-Plug = Personalized LLMs (2025.acl-long)

Challenge:	Existing multimodal summarization approaches struggle with scenarios involving multiple images as input.
Approach:	They propose a task to generate multimodal summaries by integrating multiple images as input . they propose 'multimodal information evaluation' method that measures differences between generated summary and input based on multimodal input - and compares various methods .
Outcome:	The proposed method correlates more closely with human judgments than five widely used metrics .

Copied to clipboard

Jiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei, Erxue Min, Yu Lu, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

CaDRL: Document-level Relation Extraction via Context-aware Differentiable Rule Learning (2025.coling-main)

Challenge:	Large language models (LLMs) have demonstrated extraordinary capabilities in natural language understanding, generation, and reasoning.
Approach:	They propose a plug-and-play LLM model that embeds a user-specific embedding for each individual by modeling her historical contexts through a lightweight plug-in user embedder module.
Outcome:	Experiments on various tasks in the language model personalization (LaMP) benchmark show that the proposed model significantly outperforms existing personalized LLM approaches.

Copied to clipboard

Kunli Zhang, Pengcheng Wu, Bohan Yu, Kejun Wu, Aoze Zheng, Xiyang Huang, Chenkang Zhu, Min Peng, Hongying Zan, Yu Song

XLPT-AMR: Cross-Lingual Pre-Training via Multi-Task Learning for Zero-Shot AMR Parsing and Text Generation (2021.acl-long)

Challenge:	Existing methods for document-level relation extraction (DocRE) lack logic and transparency.
Approach:	They propose a Context-aware differentiable rule learning framework that learns the doc-specific logical rule to avoid suboptimal constraints.
Outcome:	The proposed framework outperforms existing rule-based frameworks on three DocRE datasets.

Copied to clipboard

Dongqin Xu, Junhui Li, Muhua Zhu, Min Zhang, Guodong Zhou

LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) research is limited and challenging for languages other than English.
Approach:	They propose a cross-lingual pre-training approach for AMR parsing and text generation . they use an English-to-English parallel dataset and a multi-task learning approach .
Outcome:	The proposed approach outperforms baseline pre-training methods on English parsing and text generation tasks.

Copied to clipboard

King Zhu, Qianbo Zang, Shian Jia, Siwei Wu, Feiteng Fang, Yizhi Li, Shuyue Guo, Tianyu Zheng, Jiawei Guo, Bo Li, Haoning Wu, Xingwei Qu, Jian Yang, Ruibo Liu, Xiang Yue, Jiaheng Liu, Chenghua Lin, Hamid Alinejad-Rokny, Min Yang, Shiwen Ni, Wenhao Huang, Ge Zhang

Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Challenge:	Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach:	They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome:	The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.

Copied to clipboard

Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang

Challenge:	Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach:	They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome:	The proposed method mitigates behavior collapse and improves performance across benchmarks.

From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)

Copied to clipboard

Wenjing Xie, Xiaobo Liang, Juntao Li, Wanfu Wang, Kehai Chen, Qiaoming Zhu, Min Zhang

E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning (2026.findings-acl)

Challenge:	Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration.
Approach:	They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks.
Outcome:	The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates.

Copied to clipboard

Weiyang Guo, Zesheng Shi, Liye Zhao, Jiayuan Ma, Zeen Zhu, Junxian He, Min Zhang, Jing Li

Responsible & Trustworthy NLP

Challenge:	Existing training paradigms for Large Language Models (LLMs) suffer from inefficient exploration and mode degradation due to a lack of prior guidance, while SFT-then-RL is limited by high data costs and capability plateaus caused by low-entropy collapse.
Approach:	They propose an Enhanced Experience Exploitation paradigm that integrates expert prefixes, expert guided, and self-exploration to improve agent training.
Outcome:	The proposed model achieves a 6% performance improvement over traditional paradigms on tool-use tasks while requiring less than 10% of the synthetic data.

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction (2020.coling-main)

Copied to clipboard

Tong Zhu, Haitao Wang, Junjie Yu, Xiabing Zhou, Wenliang Chen, Wei Zhang, Min Zhang