Zimu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zimu Wang has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wang
School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou China
8 shared publications Wei Wang
School of Advanced Technology Xi'an Jiaotong-Liverpool University China
6 shared publications- Hongbin Na
University of Technology Sydney
4 shared publications - Anh Nguyen
Department of Computer Science, University of Liverpool, Liverpool, United Kingdom
3 shared publications Haiyang Zhang
School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou China
3 shared publicationsLing Chen
Australian Artificial Intelligence Institute University of Technology Sydney Harvard University Xi'an Jiaotong-Liverpool University University of Pennsylvania
3 shared publications
Latest Publications
- Open Access
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored. To address this gap, we introduce MedFact, the first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content. It consists of 1,321 questions and 7,409 claims, mirroring the complexities of real-world medical scenarios. We conduct comprehensive experiments in both in-context learning (ICL) and fine-tuning settings, showcasing the capability and challenges of current LLMs on this task, accompanied by an in-depth error analysis to point out key directions for future research. Our dataset is publicly available at https://github.com/AshleyChenNLP/MedFact.
Open AccessMedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Medical fact-checking has become increasingly critical as more individuals seek medical information online. However, existing datasets predominantly focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored. To address this gap, we introduce MedFact, the first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content. It consists of 1,321 questions and 7,409 claims, mirroring the complexities of real-world medical scenarios. We conduct comprehensive experiments in both in-context learning (ICL) and fine-tuning settings, showcasing the capability and challenges of current LLMs on this task, accompanied by an in-depth error analysis to point out key directions for future research. Our dataset is publicly available at https://github.com/AshleyChenNLP/MedFact.
- Open Access
FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation, and risk, run in parallel to synthesize evidence into multi-dimensional insights. To mitigate overconfidence and improve reliability, we introduce a safe debate protocol that enables agents to challenge and refine initial conclusions while preserving coherent recommendations. Experimental results, based on both LLM-based and human evaluations, demonstrate the framework's efficacy in producing high-quality analysis with calibrated confidence levels and actionable investment strategies across multiple time horizons.
Open AccessFinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
We introduce FinDebate, a multi-agent framework for financial analysis, integrating collaborative debate with domain-specific Retrieval-Augmented Generation (RAG). Five specialized agents, covering earnings, market, sentiment, valuation, and risk, run in parallel to synthesize evidence into multi-dimensional insights. To mitigate overconfidence and improve reliability, we introduce a safe debate protocol that enables agents to challenge and refine initial conclusions while preserving coherent recommendations. Experimental results, based on both LLM-based and human evaluations, demonstrate the framework's efficacy in producing high-quality analysis with calibrated confidence levels and actionable investment strategies across multiple time horizons.
- Open Access
Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents
The proliferation of multimedia content necessitates the development of effective Multimedia Event Extraction (M2E2) systems. Though Large Vision-Language Models (LVLMs) have shown strong cross-modal capabilities, their utility in the M2E2 task remains underexplored. In this paper, we present the first systematic evaluation of representative LVLMs, including DeepSeek-VL2 and the Qwen-VL series, on the M2E2 dataset. Our evaluations cover text-only, image-only, and cross-media subtasks, assessed under both few-shot prompting and fine-tuning settings. Our key findings highlight the following valuable insights: (1) Few-shot LVLMs perform notably better on visual tasks but struggle significantly with textual tasks; (2) Fine-tuning LVLMs with LoRA substantially enhances model performance; and (3) LVLMs exhibit strong synergy when combining modalities, achieving superior performance in cross-modal settings. We further provide a detailed error analysis to reveal persistent challenges in areas such as semantic precision, localization, and cross-modal grounding, which remain critical obstacles for advancing M2E2 capabilities.
Open AccessBenchmarking and Improving LVLMs on Event Extraction from Multimedia Documents
The proliferation of multimedia content necessitates the development of effective Multimedia Event Extraction (M2E2) systems. Though Large Vision-Language Models (LVLMs) have shown strong cross-modal capabilities, their utility in the M2E2 task remains underexplored. In this paper, we present the first systematic evaluation of representative LVLMs, including DeepSeek-VL2 and the Qwen-VL series, on the M2E2 dataset. Our evaluations cover text-only, image-only, and cross-media subtasks, assessed under both few-shot prompting and fine-tuning settings. Our key findings highlight the following valuable insights: (1) Few-shot LVLMs perform notably better on visual tasks but struggle significantly with textual tasks; (2) Fine-tuning LVLMs with LoRA substantially enhances model performance; and (3) LVLMs exhibit strong synergy when combining modalities, achieving superior performance in cross-modal settings. We further provide a detailed error analysis to reveal persistent challenges in areas such as semantic precision, localization, and cross-modal grounding, which remain critical obstacles for advancing M2E2 capabilities.
- 19 July 2025
- Published by Springer Nature
- p. 332-346
MonoTCM: Semantic-Depth Fusion Transformer for Monocular 3D Object Detection with Token Clustering and Merging
- 19 July 2025
- Published by Springer Nature
- p. 332-346
MonoTCM: Semantic-Depth Fusion Transformer for Monocular 3D Object Detection with Token Clustering and Merging
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 24303-24311
Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation
Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for fine-tuning. Since the collection of high-quality TMWP datasets is costly and time-consuming, recent research has concentrated on automatic TMWP generation. However, current generated samples usually suffer from issues of either correctness or diversity. In this paper, we propose a Template-driven LLM-paraphrased (TeLL) framework for generating high-quality TMWP samples with diverse backgrounds and accurate tables, questions, answers, and solutions. To this end, we first extract templates from existing real samples to generate initial problems, ensuring correctness. Then, we adopt an LLM to extend templates and paraphrase problems, obtaining diverse TMWP samples. Furthermore, we find the reasoning annotation is important for solving TMWPs. Therefore, we propose to enrich each solution with illustrative reasoning steps. Through the proposed framework, we construct a high-quality dataset TabMWP-TeLL by adhering to the question types in the TabMWP dataset, and we conduct extensive experiments on a variety of LLMs to demonstrate the effectiveness of TabMWP-TeLL in improving TMWP-solving performance.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (23) , 24303-24311
Open AccessTemplate-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation
Solving tabular math word problems (TMWPs) has become a critical role in evaluating the mathematical reasoning ability of large language models (LLMs), where large-scale TMWP samples are commonly required for fine-tuning. Since the collection of high-quality TMWP datasets is costly and time-consuming, recent research has concentrated on automatic TMWP generation. However, current generated samples usually suffer from issues of either correctness or diversity. In this paper, we propose a Template-driven LLM-paraphrased (TeLL) framework for generating high-quality TMWP samples with diverse backgrounds and accurate tables, questions, answers, and solutions. To this end, we first extract templates from existing real samples to generate initial problems, ensuring correctness. Then, we adopt an LLM to extend templates and paraphrase problems, obtaining diverse TMWP samples. Furthermore, we find the reasoning annotation is important for solving TMWPs. Therefore, we propose to enrich each solution with illustrative reasoning steps. Through the proposed framework, we construct a high-quality dataset TabMWP-TeLL by adhering to the question types in the TabMWP dataset, and we conduct extensive experiments on a variety of LLMs to demonstrate the effectiveness of TabMWP-TeLL in improving TMWP-solving performance.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 268-282
FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
Tianshi Cai, Guanxu Li, Nijia Han, Ce Huang, Zimu Wang, Changyu Zeng, Yuqi Wang, Jingshi Zhou, Haiyang Zhang, Qi Chen, Yushan Pan, Shuihua Wang, Wei Wang. Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 268-282
Open AccessFinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis
Tianshi Cai, Guanxu Li, Nijia Han, Ce Huang, Zimu Wang, Changyu Zeng, Yuqi Wang, Jingshi Zhou, Haiyang Zhang, Qi Chen, Yushan Pan, Shuihua Wang, Wei Wang. Proceedings of The 10th Workshop on Financial Technology and Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2538-2550
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement
Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 2538-2550
Open AccessLost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement
Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 32328-32341
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, Jionglong Su. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 32328-32341
Open AccessMedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses
Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, Jionglong Su. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7362-7376
A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, Ling Chen. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7362-7376
Top Cited PapersOpen AccessA Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, Ling Chen. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 249-255
From Posts to Timelines: Modeling Mental Health Dynamics from Social Media Timelines with Hybrid LLMs
Zimu Wang, Hongbin Na, Rena Gao, Jiayuan Ma, Yining Hua, Ling Chen, Wei Wang. Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 249-255
Open AccessFrom Posts to Timelines: Modeling Mental Health Dynamics from Social Media Timelines with Hybrid LLMs
Zimu Wang, Hongbin Na, Rena Gao, Jiayuan Ma, Yining Hua, Ling Chen, Wei Wang. Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025). 2025.