Papers by Bin Zhu

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

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

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

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

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

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

Interesting Culture: Social Relation Recognition from Videos via Culture De-confounding (2025.findings-emnlp)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Yuxuan Zhang, Yangfu Zhu, Haorui Wang, Bin Wu

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	a culturally-specific cultural context can be used to train relationship recognition models . cultural confounding factors can be learned, limiting ability to recognize social relationships in different cultures.
Approach:	They propose a culturally-based model that mitigates the influence of culture . they also construct a video social relation recognition dataset to facilitate discussion .
Outcome:	The proposed model surpasses state-of-the-art methods on several datasets.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

Responsible & Trustworthy NLP

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning (2024.findings-acl)

Copied to clipboard

Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models (2026.findings-acl)

Challenge:	Existing CodePre-trained models struggle to generalize due to superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities.
Approach:	They propose a framework that integrates multi-task learning with Large Language Models to effectively mine deep-seated vulnerability features.
Outcome:	The proposed framework surpasses seven state-of-the-art models in effectiveness, generalization, and robustness.

Copied to clipboard

Jizhihui Liu, Guangdao Zhu, Feiyi Du, Niu Lian, Jun Li, Bin Chen, Weili Guan, Yaowei Wang

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)

Challenge:	Existing methods for visual token pruning lack insight into the intrinsic property of the vision encoder . et al., 2017: 99.3% of task accuracy with only 1/3 of the tokens.
Approach:	They propose a model-agnostic token pruning method that trains without training . they propose 'HiPrune' method which prunes visual tokens according to their attention .
Outcome:	The proposed method achieves 99.3% of task accuracy with only 1/3 of the tokens . it reduces inference FLOPs by 58.7% and maintains 99.99% accuracy with 2/9 tokens.

Copied to clipboard

Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang

DarwinTOD: LLM-Driven Lifelong Self-evolution for Task-oriented Dialog Systems (2026.acl-long)

Challenge:	i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data.
Approach:	They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data.
Outcome:	i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks.

Copied to clipboard

Shuyu Zhang, Yujie Liu, Xinru Wang, Cheng Zhang, Yanmin Zhu, Bin Li

Dialogue Systems & Conversational Agents

Challenge:	Continual learning approaches fail to achieve autonomy lifelong improvement in dynamic environments . current task-oriented dialog systems are static, unable to learn from ongoing interactions .
Approach:	They propose a lifelong self-evolving dialog framework that integrates evolutionary computation and LLM driven self-improvement into a single framework.
Outcome:	The proposed framework surpasses state-of-the-art methods and exhibits continuous performance gains throughout evolution.

Table-as-Search: Agentic Information Seeking is Table Completion (2026.findings-acl)

Copied to clipboard

Tian Lan, Felix Henry, Bin Zhu, Qianghuai Jia, Junyang Ren, Qihang PU, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo

Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models (2026.findings-acl)

Challenge:	Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states within one plain-text context is inherently fragile.
Approach:	They propose a structured planning framework that reformulates the InfoSeeking task as a Table Completion task.
Outcome:	The proposed framework outperforms state-of-the-art frameworks across three kinds of benchmarks, including multi-agent framework and commercial systems.

Copied to clipboard

Ziyao Tang, Pengkun Jiao, Bin Zhu, Huiyan Qi, Jingjing Chen, Yu-Gang Jiang

Robustness in NLP

Challenge:	Existing Vid-LLMs lack robust mechanisms for maintaining grounded spatiotemporal beliefs under conversational feedback.
Approach:	They propose a negation-based gaslighting evaluation framework and introduce a benchmark to investigate spatiotemporal sycophancy.
Outcome:	The proposed framework evaluates state-of-the-art Vid-LLMs across video understanding tasks.

AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Yuting Wei, Yuanxing Xu, Xinru Wei, Yangsimin Yangsimin, Yangfu Zhu, Yuqing Li, Di Liu, Bin Wu

Exploring Robust Overfitting for Pre-trained Language Models (2023.findings-acl)

Challenge:	AC-EVAL is a benchmark designed to assess the advanced knowledge and reasoning capabilities of LLMs within the context of ancient Chinese.
Approach:	They propose a benchmark to assess the advanced knowledge and reasoning capabilities of LLMs in ancient Chinese.
Outcome:	AC-EVAL aims to assess the comprehension of ancient Chinese texts . the benchmark covers 13 tasks covering historical facts, geography, social customs, art, philosophy, classical poetry and prose.

Copied to clipboard

Bin Zhu, Yanghui Rao

Robustness in NLP

Challenge:	Recent literature has revealed their vulnerability to crafted adversarial examples on a wide range of NLP tasks.
Approach:	They propose to combine regularization methods with adversarial training to mitigate robust overfitting for pre-trained language models by scaling the model's loss.
Outcome:	The proposed methods mitigate robust overfitting upon three top adversarial training methods and further promote adversarially robustness.

Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding (2026.acl-long)

Copied to clipboard

Wenqing Hou, Hongkui Tu, Ye Wang, Yue Zhang, Yuying Liu, Dong Zhu, Liqun Gao, Bin Zhou

Responsible & Trustworthy NLP

Challenge:	Existing methods for identifying harmful memes rely on modal alignment or black-box classifiers . BPDMoE-Hate provides visual explanations for viewpoint selection and hierarchical structuring .
Approach:	They propose a framework that conceptualizes harmful meme detection as a process of "viewpoint decoupling and hierarchical fusion" they propose BPDMoE-Hate, which generates adversarial binary perspectives via VLMs and incorporates an adaptive viewpoint gating to facilitate viewpoint selection.
Outcome:	The proposed framework surpasses existing methods in performance and provides visual explanations for viewpoint selection and hierarchical structuring.

Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)

Copied to clipboard

Bin Zhu, Zhaoquan Gu, Le Wang, Jinyin Chen, Qi Xuan

Robustness in NLP

Challenge:	Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness.
Approach:	They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps.
Outcome:	The proposed method can obtain stronger robustness using fewer steps than existing methods.

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)

Copied to clipboard

Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, Li Yuan

OSCBench: Benchmarking Object State Change in Text-to-Video Generation (2026.acl-long)

Challenge:	Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers.
Approach:	They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM.
Outcome:	The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks.

Copied to clipboard

Xianjing Han, Bin Zhu, Shiqi Hu, Franklin Mingzhe Li, Patrick Carrington, Roger Zimmermann, Jingjing Chen

StraGo: Harnessing Strategic Guidance for Prompt Optimization (2024.findings-emnlp)

Challenge:	Existing benchmarks focus on perceptual quality, text–video alignment, or physical plausibility, leaving a critical aspect of action understanding unexplored.
Approach:	They introduce a benchmark specifically designed to assess OSC performance in T2V models.
Outcome:	The proposed benchmark assesses the performance of open-source and proprietary T2V models on object state change (OSC) in the context of novel and compositional scenarios.

Copied to clipboard

Yurong Wu, Yan Gao, Bin Zhu, Zineng Zhou, Xiaodi Sun, Sheng Yang, Jian-Guang Lou, Zhiming Ding, Linjun Yang

WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering (2026.findings-acl)

Challenge:	Existing methods for prompt optimization often lead to prompt drifting, wherein newly generated prompts canadversely impact previously successful cases while addressing failures.
Approach:	They propose a method to mitigate prompt drifting by integrating in-context learning to formulate specific, actionable strategies for prompt optimization.
Outcome:	The proposed approach mitigates prompt drifting by leveraging insights from both successful and failed cases to identify critical factors for achieving optimization objectives.

Copied to clipboard

Yingjian Zhu, Xinming Wang, Kun Ding, Ying Wang, Bin Fan, Shiming Xiang

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Challenge:	Existing methods for Knowledge-Based Visual Question Answering rely on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs)
Approach:	They propose a multi-modal RAG framework that assigns VLMs two specialized agents: a Refiner and an Inspector.
Outcome:	Experiments on EVQA, InfoSeek, and M2KR show that the proposed framework achieves state-of-the-art performance with significant improvements in both retrieval accuracy and answer quality.

Copied to clipboard

MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

Information Extraction & Text Mining

Challenge:	Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach:	They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome:	The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.

DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems (2026.acl-long)

Copied to clipboard

Shuyu Zhang, Yifan Wei, Jialuo Yuan, Xinru Wang, Yanmin Zhu, Yujie Liu, Bin Li

Dialogue Systems & Conversational Agents

Challenge:	Task oriented dialog systems often rely on static exploration strategies that do not adapt to dynamic dialog contexts.
Approach:	They propose a dialog policy learning framework that formalizes the exploration challenge through a structured cognitive state space C.
Outcome:	The proposed framework achieves SOTA performance in success rate, efficiency, and generalization.

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

Copied to clipboard

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

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

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

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

HyperMR: Hyperbolic Hypergraph Multi-hop Reasoning for Knowledge-based Visual Question Answering (2024.lrec-main)

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

Bin Wang, Fuyong Xu, Peiyu Liu, Zhenfang Zhu

JurisBench: A Deep Benchmark for Assessing Large Language Models in Professional Legal Practice (2026.acl-long)

Challenge:	Existing studies on knowledge-based visual question answering (KBVQA) describe the semantic distance using the actual Euclidean distance between two nodes, which leads to distortion in modeling knowledge graphs with hierarchical and scale-free structure.
Approach:	They propose to use the actual Euclidean distance between two nodes to solve a problem of hierarchical and free-scale knowledge graphs.
Outcome:	Extensive experiments on the KVQA, PQ and PQL datasets demonstrate the effectiveness of HyperMR for strong-hierarchy knowledge graphs.

Copied to clipboard

Ziang Chen, Guannan Li, Fanlin Ji, Yipeng Kang, Jiaqi Li, Muhan Zhang, Yangtao Zhang, Li Tianjiao, Jiannan Wang, Xin Guo, Song-Chun Zhu, Bin Ling

MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models (2026.findings-acl)

Challenge:	Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudicative rigor inherent in professional practice.
Approach:	They propose a vertical, depth-oriented, domain-specific benchmark to evaluate Large Language Models (LLMs) in Chinese civil litigation.
Outcome:	The proposed benchmarks show that large language models exhibit an "illusion of competence" the results highlight a critical gap between fluent linguistic output and judicial reliability .

Copied to clipboard

Xinming Wang, Jian Xu, Bin Yu, Sheng Lian, yi Chen, Boran Wang, Yingjian Zhu, Hongzhu Yi, Hong-Ming Yang, Han Hu, Cheng-Lin Liu, Xu-Yao Zhang

Reasoning

Challenge:	Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited.
Approach:	They propose a Meta-Reasoning informed alignment framework that quantifies state-transition probabilities along the model’s thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments.
Outcome:	Empirical evaluations of four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning.

Maximal Clique Based Non-Autoregressive Open Information Extraction (2021.emnlp-main)

Copied to clipboard

Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang

Information Extraction & Text Mining

Challenge:	Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence.
Approach:	They propose a non-autoregressive framework that generates a fact graph and a graph with an edge linking two nodes that belong to the same fact.
Outcome:	The proposed framework outperforms current state-of-the-art methods on two benchmark datasets and significantly outperformed the existing ones.

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding (2026.acl-demo)

Copied to clipboard

Runcong Zhao, Qinglin Zhu, Hainiu Xu, Bin Liang, Lin Gui, Yulan He

Large Language Models are Better Reasoners with Self-Verification (2023.findings-emnlp)

Challenge:	Existing methods for constructing character relationships from plain text are time-consuming and low in coverage.
Approach:	They propose a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning.
Outcome:	The proposed framework improves annotation accuracy and consistency while significantly reducing time cost.

Copied to clipboard

Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, Jun Zhao