← Search

Yu Gan

2 accepted papers

2026

Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence

ICML 2026poster

At the core of modern prompting techniques is contextual sensitivity, the ability of large language models to adapt their predictions based on inference-time context. Despite its central role, inference behavior under strong contextual influence remains poorly understood, particularly at the level o…

Cited by 0SourceScholar
2025

CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL

ICLR 2025poster

We present CHASE-SQL, a novel framework addressing large language model (LLM) performance challenges for Text-to-SQL tasks by leveraging multi-agent modeling and test-time compute for improved candidate generation and selection. CHASE-SQL uses LLMs to generate diverse SQL candidates with: (1) a divi…

Cited by 36SourcePDFScholar