4 papers
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…
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…
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…
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…