Jia-Chen Gu (顾佳宸)

About Me

I am currently a postdoctoral researcher at the Department of Computer Science, University of California, Los Angeles (UCLA), hosted by Prof. Nanyun (Violet) Peng and Prof. Kai-Wei Chang. I received my Ph.D. degree from the University of Science and Technology of China in June 2022, under the supervision of Prof. Zhen-Hua Ling. I have previously interned at Microsoft (2020-2021) and visited Queen’s University (2019-2020). I fortunately received the Best Paper Honorable Mention Award of ACL 2023 and Best Paper Award of DialDoc@ACL 2022.

My main research interests lie within deep learning for natural language processing, and the first-author papers during my Ph.D. study particularly focused on dialogue systems and retrieval-based language models:

• Retrieval-based dialogue systems: Interactiva Matching Network (IMN, CIKM 2019), Utterance-to-Utterance Interactiva Matching Network (U2U-IMN, TASLP 2020), and Speaker-Aware BERT (SA-BERT, CIKM 2020).
• Knowledge/Persona-grounded conversation: Dually Interactive Matching Network (DIM, EMNLP 2019), Filtering before Iteratively REferring (FIRE, Findings of EMNLP 2020), investigating the role of partners (SIGIR 2021), and detecting speaker personas (SPD, EMNLP 2021).
• Multi-party conversation: Pre-trained multi-party language model (MPC-BERT, ACL 2021), Heterogeneous graphical conversation model (HeterMPC, ACL 2022), a survey on multi-party conversation (IJCAI 2022), Graph-Induced Fine-Tuning (GIFT, ACL 2023), and Maximizing Addressee Deduction Expectation (MADNet, EMNLP 2023), which are systematically organized in our IJCNLP-AACL 2023 Tutorial.

These days, I am also interested in the techniques that can potentially democratize the training and deployment of large language models (LLMs). A list of topics that I am actively working on:

• Retrieval-Augmented LLMs: To augment the capabilities of given LLMs and scale down the size of LLMs via retrieval from knowledge indexes. Recent work: (1) Corrective Retrieval Augmented Generation (CRAG), (2) SyncCheck for Trustworthy RAG, (3) Sparse Context Selection for Accelerating RAG Inference (Sparse-RAG), and (4) TExt Generation via Task-specific and Open-world Knowledge (TEGTOK, Findings of ACL 2022).
• Model Editing: To reduce the cost of upgrading LLMs and enable data-efficient alterations to the behavior of LLMs, specifically within a designated realm of interest, while ensure no adverse impact on other inputs. Recent work: (1) Model Editing Harms General Abilities of LLMs, (2) Neighboring Perturbations of Knowledge Editing on LLMs (PEAK, ICML 2024), (3) Bidirectional Language Model Editing, and (4) Perturbation-Restrained Sequential Model Editing.

If you are interested in talking about research and life with me, please feel free to reach out.

News

• 2023.12: Will attend NeurIPS 2023 from Dec 11 to Dec 14. See you in New Orleans!
• 2023.12: Invited talk on Multi-Party Conversational AI at Zhejiang University (December 20, 2023).
• 2023.10: To present a tutorial on Model Editing at AAAI 2024, Vancouver, Canada (February 20, 2024).
• 2023.09: Invited talk on "Technology and Applications of Large Language Models" at MLNLP 2023, Online (September 24, 2023).
• 2023.08: To present a tutorial on "Learning WHO Saying WHAT to WHOM in Multi-Party Conversations" at CCKS 2023, Shenyang, China (August 24, 2023) and at IJCNLP-AACL 2023, Bali, Indonesia (November 1, 2023).

Experience & Education

• 2023.11 - Present: Postdoctoral researcher at UCLA, hosted by Prof. Nanyun (Violet) Peng and Prof. Kai-Wei Chang.
• 2022.06 - 2023.10: Postdoctoral researcher at USTC, hosted by Prof. Zhen-Hua Ling.
• 2020.09 - 2021.06: Research intern at Microsoft, hosted by Dr. Chongyang Tao and Dr. Daxin Jiang.
• 2019.12 - 2020.05: Visiting research student at Queen's University, hosted by Prof. Xiaodan Zhu.
• 2017.09 - 2022.06: Ph.D. Degree at USTC, supervised by Prof. Zhen-Hua Ling.
• 2013.09 - 2017.06: B.E. Degree at Hohai University.

Selected Honors

• 2023   Best Paper Honorable Mention Award of ACL 2023
• 2022   Best Paper Award of DialDoc@ACL 2022
• 2022   Outstanding Doctoral Dissertation Nomination Award of Chinese Information Processing Society of China
• 2022   Presidential Scholarship of Chinese Academy of Sciences (Top 1%)
• 2022   Outstanding Graduate Award of University of Science and Technology of China
• 2021   China National Scholarship
• 2021   Huayu Scholarship (Top 2 graduates of NERC-SLIP per year)
• 2015   Presidential Yan Kai Scholarship (Top 0.1%, the highest honor of HHU)

Tutorials

• "Knowledge Editing for Large Language Models" at AAAI 2024. [slides]
Ningyu Zhang, Jia-Chen Gu, Yunzhi Yao, Zhen Bi, Shumin Deng.
• "Learning WHO Saying WHAT to WHOM in Multi-Party Conversations" at IJCNLP-AACL 2023. [slides]
Jia-Chen Gu, Zhuosheng Zhang, Zhen-Hua Ling.
• "Learning WHO Saying WHAT to WHOM in Multi-Party Conversations" at CCKS 2023.
Jia-Chen Gu.

Talks

• 2024.02: Guest lecture "Pre-trained Large Language Models" at UCLA CS162.
• 2023.12: Guest lecture "Multi-Party Conversational AI" at Zhejiang University. [slides]
• 2023.09: "Learning Conversation Structures for Multi-Party Conversations" at MLNLP 2023.
• 2023.05: "Learning Conversation Structures for Multi-Party Conversations" at YSSNLP 2023.
• 2022.11: "Multi-Party Conversation Understanding and Generation" at CCF and CAS-ICT.
• 2022.07: "Multi-Party Conversation Understanding and Generation" at MLNLP. [slides]

Shared Tasks

• 2022   Rank first on both subtasks of Track 2 in the Eleventh Dialog System Technology Challenges (DSTC 11).
• 2020   Rank second under objective metrics and fourth under subjective metrics on Track 1 in the Ninth Dialog System Technology Challenges (DSTC 9), as the team leader.
• 2019   Rank first, first, third and fourth on subtasks of Track 2 in the Eighth Dialog System Technology Challenges (DSTC 8), as the first author.
• 2018   Rank second on a subtask of Track 1 in the Seventh Dialog System Technology Challenges (DSTC 7), as the first author.

Professional Service

• Area Chair:
  • ACL, EMNLP, NAACL
• Program Committee (Reviewer):
  • Conference: ACL, EMNLP, NAACL, EACL, ACL Rolling Review, COLM, AAAI, IJCAI, NLPCC, CCKS
  • Journal: TASLP, TOIS, TALLIP, CIM, IPM