← Search

Victor Ma

2 accepted papers

2026

Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?

ICML 2026poster

SQL is central to enterprise data engineering, yet generating fully correct SQL code in a single attempt remains difficult—even for experienced developers and advanced \ttsql LLMs—often requiring multiple debugging iterations. We introduce \textbf{\ourbench}, the first benchmark for enterprise-level…

Cited by 0SourceScholar
2025

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization

EMNLP 2025

Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue. Traditional reward modeling approaches, which rely on indepe