5 papers
UniQL: Towards Dialect-Universal Benchmarking for Text-to-SQL
Jianling Gao, Chongyang Tao, Jiayuan Bai +7
Existing text-to-SQL benchmarks are largely centered on SQLite, making it difficult to evaluate whether models can generalize across heterogeneous SQL dialects. However, real-world…
EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesis
Xuanguang Pan, Chongyang Tao, Jiayuan Bai +5
Training effective Text-to-SQL models remains challenging due to the scarcity of high-quality, diverse, and structurally complex datasets. Existing methods either rely on limited h…
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
Jingzhe Ding, Shengda Long, Changxin Pu +46
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities re…
AIR: Post-training Data Selection for Reasoning via Attention Head Influence
Jinrui Liu, Jeff Wu, Xuanguang Pan +3
LLMs achieve remarkable multi-step reasoning capabilities, yet effectively transferring these skills via post-training distillation remains challenging. Existing data selection met…
JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament
Jiayuan Bai, Xuan-guang Pan, Chongyang Tao +1
Text-to-SQL is a pivotal task that bridges natural language understanding and structured data access, yet it remains fundamentally challenging due to semantic ambiguity and complex…