Hello, I am Tingchen Fu (付廷琛 in Chinese), a 3rd-year master student in Gaoling School of Artificial Intelligence, Renmin University of China as an NLP researcher and a fanatic believer on AGI, advised by Xueliang Zhao and Rui Yan. I am actively seeking a PhD position in NLP starting at Fall 2025. If you are interested in my research, please feel free to contact.

I am genelly interested in machine learning, language technology, and their intersection, with a special emphasis on understanding and unleashing the full potential of Large Language Models. Specifically, I am currently interested in the following topics:

• LLM alignment.
• Safety and robustness of LLM and VLM system.
• LLM for reasoning.

🔥 News

• 2024.05:  🎉🎉 I got two paper accepted by findings of ACL 2024. Thanks for my colleborators! See you at Bangkok.
• 2024.01:  🎉🎉 I got one paper accepted by ICLR’24. Thanks for my colleborators! See you at Vienna.

📖 Educations

• 2022.09 - present, master student in the Gaoling School of Artificial Intelligence, Renmin University of China.
• 2018.09 - 2022.06, undergraduate student in the School of Information, Renmin University of China.

💼 Internships

• 2023.02 - 2024.03, Tencent AI Lab, advised by Dr. Lemao Liu.
• 2024.07 - now, Bytedance Seed, advised by Dr. Shipeng Yan.

📝 Preprints

• Open Problems in Machine Unlearning for AI Safety. [paper]

  Fazl Barez, Tingchen Fu, Ameya Prabhu, Stephen Casper, Amartya Sanyal, Adel Bibi, Aidan O’Gara, Robert Kirk, Ben Bucknall, Tim Fist, Luke Ong, Philip Torr, Kwok-Yan Lam, Robert Trager, David Krueger, Sören Mindermann, José Hernandez-Orallo, Mor Geva, Yarin Gal

• PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning. [paper]

  Tingchen Fu, Mrinank Sharma, Philip Torr, Shay B. Cohen, David Krueger and Fazl Barez.

• Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts. [paper]

  Tingchen Fu, Yupeng Hou, Julian McAuley and Rui Yan.

• On the Transformations across Reward Model, Parameter Update, and In-Context Prompt. [paper]

  Deng Cai, Huayang Li, Tingchen Fu, Siheng Li, Weiwen Xu, Shuaiyi Li, Bowen Cao, Zhisong Zhang, Xinting Huang, Leyang Cui, Yan Wang, Lemao Liu, Taro Watanabe, Shuming Shi

• Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. [paper]

  Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, Shuming Shi

📝 Publications

• BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models [paper]

  Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong.

  Findings of the Association for Computational Linguistics: ACL 2024

• Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction. [paper]

  Tingchen Fu, Deng Cai, Lemao Liu, Shuming Shi, Rui Yan.

  Findings of the Association for Computational Linguistics: ACL 2024

• The Reasonableness Behind Unreasonable Translation Capability of Large Language Model [paper]

  Tingchen Fu, Lemao Liu, Deng Cai, Guoping Huang, Shuming Shi, Rui Yan

  The Twelfth International Conference on Learning Representations (ICLR 2024)

• Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue [paper]

  Tingchen Fu(co-first author), Xueliang Zhao, Lemao Liu, Rui Yan

  Findings of the Association for Computational Linguistics: EMNLP 2023

• Delving into Global Dialogue Structures: Structure Planning Augmented Response Selection for Multi-turn Conversations [paper]

  Tingchen Fu(co-first author), Xueliang Zhao, and Rui Yan

  Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD2023)

• On the Compositional Generalization in Versatile Open-domain Dialogue [paper]

  Tingchen Fu(co-first author), Xueliang Zhao, Lemao Liu, Rui Yan

  Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)

• SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation [paper]

  Xueliang Zhao, Tingchen Fu(co-first author), Lemao Liu, Lingpeng Kong, Shuming Shi, Rui Yan

  Findings of the Association for Computational Linguistics: ACL 2023

• There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning [paper]

  Xueliang Zhao, Tingchen Fu(co-first author), Chongyang Tao, Rui Yan

  Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

• Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure [paper]

  Xueliang Zhao, Lemao Liu, Tingchen Fu, Shuming Shi, Dongyan Zhao, Rui Yan

  Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP 2022)

• Learning to Express in Knowledge-Grounded Conversation [paper]

  Xueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu, Dongyan Zhao, Rui Yan

  Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2022)

• There Are a Thousand Hamlets in a Thousand People’s Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory. [paper].

  Tingchen Fu(co-first author), Xueliang Zhao, Chongyang Tao, Ji-Rong Wen, Rui Yan

  Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL2022)

• Learning towards conversational ai: A survey [paper]

  Tingchen Fu, Shen Gao, Xueliang Zhao, Ji-rong Wen, Rui Yan

  The Journal of AI open.

🎖 Honors and Awards

• National Scholarship, the Minister of Education, 2024
• Outstanding Graduate, Renmin University of China, 2022
• National Scholarship, the Minister of Education, 2021
• National Scholarship, the Minister of Education, 2020
• Honorable Mention of Interdisciplinary Contest in Modeling, 2019.

📄 Academic Services

• Reviewer for Conferences: NeurIPS 2022, ICML 2023, NeurIPS 2023.