4 papers
SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
Tao Liu, Tao Feng, Xiangheng Li +9
Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness onl…
AttnLink: Turning Attention into Schema Links for Text-to-SQL
Jinwang Song, Tao Liu, Haowen Zheng +3
Schema linking is a critical component of Text-to-SQL systems, but existing approaches often trade off contextual modeling capacity, score-based controllability, and inference effi…
Detection, Classification, and Mitigation of Gender Bias in Large Language Models
Xiaoqing Cheng, Hongying Zan, Lulu Kong +2
With the rapid development of large language models (LLMs), they have significantly improved efficiency across a wide range of domains. However, recent studies have revealed that L…
JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling
Jinwang Song, Hongying Zan, Kunli Zhang +4
Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this tas…