arXiv：cs.CL· Yihao Hu, Yanlin Feng, Naoki Otani, Nikita Bhutani·· 3 小时前AI 评分48
ARCS：通过结构化消歧实现精准 Text-to-SQL
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation
AI 导读
研究者提出结构化消歧新范式，用受约束的显式交互替代自由对话来消解 Text-to-SQL 中的歧义，并构建了首个包含真实数据库上自然歧义的基准 ARCS。实验显示歧义场景下 Text-to-SQL 仍具挑战：gpt-6-sol 端到端执行准确率仅 51%，无开源模型超过 27%。
正文
Abstract:As text-to-SQL systems move beyond demonstrations toward real-world deployment, ambiguity in user questions becomes a primary source of errors. Such ambiguities are often subtle, domain- or data-specific, and can silently cause system outputs to deviate from the user's true intent. Ambiguity is traditionally addressed through conversational clarification, which is often inefficient, cognitively demanding, and poorly aligned with real-world user workflows. We propose structured disambiguation, a new paradigm in which ambiguity is resolved through explicit, constrained interactions rather than free-form dialogue. We construct ARCS (Ambiguity Resolution Corpus for SQL), the first text-to-SQL benchmark featuring naturally occurring, unconstrained ambiguities over real-world databases, with complete annotations of all valid ambiguity points, interpretations, and SQL queries. Experimental results show that text-to-SQL remains challenging in the presence of ambiguity: gpt-6-sol achieves only 51% end-to-end execution accuracy, and no open-source model exceeds 27%.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.09396 [cs.CL] |
| (or arXiv:2610.09396v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09396 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanlin Feng [view email]
[v1]
Wed, 7 Oct 2026 03:54:02 UTC (1,398 KB)
来源：arXiv：cs.CL · arxiv.org