About me

Hi, I'm Kailai, a third-year Ph.D. candidate (President's Doctoral Scholar Awardee) at The University of Manchester and the NaCTeM group. I'm advised by Prof. Sophia Ananiadou and Prof. Junichi Tsujii. I obtained my B.E. degree in Computer Science and Technology from Harbin Institute of Technology, China.

My reserach mainly lies in natural language processing. I'm now interested in dialogue systems, especially the latest development in large language models. I'm working on aligning LLMs to human preferences and values. I'm also exploring effiecient tuning of foundation models to enable broader access of their power. My previous works focus on affective computing and AI for mental health.

I also love the game of basketball, reading, movies, and I am a huge sci-fi fan. Reach out if you are interested in collaboration or just want to have a nice chat! :)

You can also see my CV here.

News

Sep, 2024 Our paper: "MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models" has been accepted by NeurlPS 2024 main track! See you in Vancouver!
Sep, 2024 Invited to serve on the program committee for COLING 2025.
Aug, 2024 New preprint: "Selective Preference Optimization via Token-Level Reward Function Estimation".
June, 2024 New preprint: "RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning based on Emotional Information".
May, 2024 invited to serve as reviewer for NLPCC 2024.
May, 2024 One paper accepted by ACL 2024 and one paper accepted by KDD 2024.
May, 2024 Our paper: "MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models" has been open-sourced at github.
Apr, 2024 I will work as a co-organizer of the shared task: FinLLM colocated with FinNLP-AgentScen@IJCAI-2024.
Apr, 2024 Our paper: "SuicidEmoji: Derived Emoji Dataset and Tasks for Suicide-Related Social Content" has been accepted by SIGIR 2024 as a short paper.
Mar, 2024 New preprint: "MetaAligner: Conditional Weak-to-Strong Correction for Generalizable Multi-Objective Alignment of Language Models".

Talk

DS4MH The Alan Turing Institute. [Slides]
EMNLP’ 23 Main Conference. [Slides]
MLLM talk, Nov. 4, 2023. [Slides]
CIKM’ 23 Main Conference. [Slides]
LLMIT Workshop@CIKM’ 23. [Slides]

Professional Services

Journal Reviewer
- IEEE Transactions on Knowledge and Data Engineering
- IEEE Transactions on Affective Computing
- Information Fusion
- ACM Transactions on Computing for Healthcare
- Journal of Biomedical Informatics
- CAAI Transactions on Intelligence Technology
- Artificial Intelligence Review
- Information Processing & Management
- Scientific Reports
- IEEE Access
Program Committee/Reviewer
- NAACL’ 24
- EMNLP’ 24
- WWW’ 24
- ACL’ 23, 24
- COLING’ 25
- EACL’ 24
- NLPCC’ 24
- ACL Rolling Review
- BIBM’ 22
- PAKDD’ 22, 23
Organizer/Session Chair/Volunteer
- FinNLP-AgentScen@IJCAI-2024
- CIKM’ 23
- Ellis PhD Program Evaluator, 2023

Kailai Yang