冯韬，博士，山东大学浪潮人工智能学院副教授。博士毕业于澳大利亚莫纳什大学，后在莫纳什大学任Research Fellow。

研究方向聚焦于大语言模型与多模态大模型，以及因果发现与因果推理。具体关注大模型的训练与推理机制及其安全性与可靠性问题，并探索利用大模型从多模态数据中自动发现因果关系。研究旨在推动大模型从相关性建模向因果理解发展，从而提升模型的可解释性与决策能力。

目前已在ACL、TACL、EMNLP、NAACL、COLING、ACM MM等CCF-A/B类会议和期刊发表论文十余篇，并长期担任ACL、EMNLP、NAACL、COLING等国际会议审稿人。

欢迎对科研感兴趣的研究生和本科生联系（fengtao@sdu.edu.cn），一起开展研究工作并发表高水平学术论文。

代表性论文：

(1) Feng Tao; Qu Lizhen; Tandon Niket; Li Zhuang; Kang Xiaoxi; Haffari Gholamreza; On the Reliability of Large Language Models for Causal Discovery, Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Oral, 2025, CCF-A会议

(2) Feng Tao; Qu Lizhen; Tandon Niket; Haffari Gholamreza; IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data, Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025, CCF-A会议 

(3) Feng Tao; Qu Lizhen; Li Zhuang; Zhan Haolan; Hua Yuncheng; Haffari Gholamreza; IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre- trained Models, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL), 2024, CCF-A会议

(4) Feng Tao; Qu Lizhen; Haffari Gholamreza; Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery, Transactions of the Association for Computational Linguistics (TACL), 2023, CCF-B期刊 

(5) Feng Tao; Qu Lizhen; Kang Xiaoxi; Haffari Gholamreza; CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems, Proceedings of the 31st International Conference on Computational Linguistics (COLING) Oral, 2025, CCF-B会议

• 01

  大语言模型与多模态大模型

• 02

  因果发现与推理

• 03

  人工智能安全