Scholar
Yu Xia
Google Scholar ID: sTVqEUMAAAAJ
University of California San Diego
Citations & Impact
Citations
395
H-index
12
i10-index
13
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Publications: SAND: Boosting LLM Agents with Self-Taught Action Deliberation (EMNLP 2025), From Selection to Generation: A Survey of LLM-based Active Learning (ACL 2025), Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval (NAACL 2025), Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs (COLING 2025), The Closeness of In-Context Learning and Weight Shifting for Softmax Regression (NeurIPS 2024), Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback (NAACL 2024), Hallucination Diversity-Aware Active Learning for Text Summarization (NAACL 2024), Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits (WWW 2024 Oral), Towards Joint Utilization of Absolute and Relative Bandit Feedback for Conversational Recommendation (UMUAI 2024 Special Issue on CRS), User-Regulation Deconfounded Conversational Recommender System with Bandit Feedback (KDD 2023).
Research Experience
- Research Scientist Intern at Snowflake AI Research.
Education
- PhD in Computer Science and Engineering, University of California San Diego, 2024-Present; M.S. in Information, University of Michigan, 2022-2024; B.Eng. in Electrical and Computer Engineering, Shanghai Jiao Tong University, 2019-2023.
Background
- Research Interests: Large Language Models, Conversational Recommendation, RL/Finetuning of LLMs. Currently a 2nd-year CSE PhD student at UC San Diego, working with Prof. Julian McAuley.
Co-authors