About Me
Hi~ 
I am Yu Xia (夏羽), a 1st-year CSE PhD student at University of California San Diego, where I am working with Prof. Julian McAuley. I earned my bachelor’s degree from Shanghai Jiao Tong University and master’s degree from University of Michigan, where I was fortunate to work with Prof. Shuai Li and Dr. Tong Yu on Large Language Models and Conversational Recommender Systems.
I am recently interested in research topics around LLM Alignment and Hallucination Mitigation.
News
- 09/2024
: Moved to San Diego and feeling good 
!
Selected Publications
-
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
(Alphabetical Order) Shuai Li, Zhao Song, Yu Xia, Tong Yu, Tianyi Zhou.
NeurIPS 2024 [Paper] -
Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback
Yu Xia, Tong Yu, Zhankui He, Handong Zhao, Julian McAuley, Shuai Li.
NAACL 2024 [Paper] -
Hallucination Diversity-Aware Active Learning for Text Summarization
Yu Xia, Xu Liu, Tong Yu, Sungchul Kim, Ryan A. Rossi, Anup Rao, Tung Mai, Shuai Li.
NAACL 2024 [Paper] -
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
Yu Xia*, Fang Kong*, Tong Yu, Liya Guo, Ryan A. Rossi, Sungchul Kim, Shuai Li.
WWW 2024 Oral [Paper] -
Towards Joint Utilization of Absolute and Relative Bandit Feedback for Conversational Recommendation
Yu Xia*, Zhihui Xie*, Tong Yu, Canzhe Zhao, Shuai Li.
UMUAI 2024 Special Issue on CRS [Paper] -
User-Regulation Deconfounded Conversational Recommender System with Bandit Feedback
Yu Xia, Junda Wu, Tong Yu, Sungchul Kim, Ryan A. Rossi, Shuai Li.
KDD 2023 [Paper]
arXiv Preprints
-
Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
Yu Xia, Junda Wu, Sungchul Kim, Tong Yu, Ryan A. Rossi, Haoliang Wang, Julian McAuley.
[arXiv] -
Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
Yu Xia, Rui Wang, Xu Liu, Mingyan Li, Tong Yu, Xiang Chen, Julian McAuley, Shuai Li.
[arXiv]
Presentations
-
Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
Web Mining Session at WWW’24, Singapore. [Poster] [Slides] [Video] -
User-Regulation Deconfounded Conversational Recommender System with Bandit Feedback
Conversational AI Session at KDD’23, Long Beach, CA. [Poster] [Slides]
CV
Educations
-
University of California San Diego, 2024-Now
Ph.D. in Computer Science and Engineering -
University of Michigan, 2022-2024
M.S. in Information -
🦶 Shanghai Jiao Tong University, 2019-2023
B.Eng. in Electrical and Computer Engineering
Experiences
- Research Scientist Intern
- Adobe 2024.6-Now (Mentor: Dr. Sungchul Kim)
- Conference Reviewer
- RecSys’23, WWW’24, NAACL’24, COLING’25, WWW’25
- Conference Volunteer
- NAACL’24
Interesting Projects
-
FLEE [Game Link] [Code]: An interactive web game of an intersteller journey! - 🕵️ A Study in Red [Link]: A funny interative fanfiction of Sherlock Holmes that I have no idea when I wrote it!
-
Science Fiction Text Generation [Link] -
Beer Recommender System [Link]
Awards
- University of Michigan - Shanghai Jiao Tong University Yu Liming Scholarship, 2021
- Shanghai Jiao Tong University Outstanding Undergraduate Award, 2021
- University of Michigan - Shanghai Jiao Tong University Yu Liming Scholarship, 2020
- Shanghai Jiao Tong University Outstanding Undergraduate Award, 2020