跳到正文
arXiv cs.CL· Su Dong, Jiayan Lin, Yujia Liu, Zijin Hong, Qinggang Zhang, Feiran Huang, Xiao Huang·· 9 小时前AI 评分29

DisGuAD:用分歧引导歧义检测,提升交互式 text-to-SQL 澄清效率

Asking What Matters: Disagreement-Guided Ambiguity Detection for Interactive Text-to-SQL

AI 导读

研究者提出 DisGuAD,一个分歧引导的歧义检测框架,将多个合理 SQL 解释之间的分歧作为判断哪些不确定性真正影响最终查询的证据。在 BIRD-Interact Lite 和 Full 上,该方法相比原始交互策略将归一化 Reward 提升 4.40–8.97 分,关键歧义覆盖率从 48.62% 升至 82.75%、从 45.76% 升至 85.14%。

正文 · 原文

View PDF HTML (experimental)

Abstract:Interactive text-to-SQL requires an LLM agent not only to generate executable SQL, but also to decide which uncertainty to clarify within a limited interaction budget. However, current clarification policies have three limitations: (i) they target surface ambiguity without testing its SQL impact; (ii) they miss ambiguities implicit in schema routes or domain knowledge; and (iii) they spend limited turns on unfocused or redundant questions. These limitations expose a critical challenge: identifying SQL-impacting ambiguity before the intended SQL is known. In this paper, we propose DisGuAD, a Disagreement-Guided Ambiguity Detection framework that specializes clarification selection. DisGuAD treats disagreement among plausible SQL interpretations as direct evidence of which uncertainty matters to the final query. Specifically, it constructs a query-term inventory, elicits contrastive SQL interpretations through complementary probe families, compares their canonical SQL components, and attributes recurring differences to user-facing clarification targets. A lightweight prioritization and dialogue-state mechanism then selects one high-impact unresolved target for clarification. Experiments on BIRD-Interact Lite and Full with two LLM backbones demonstrate consistent improvements in task success and clarification quality. Compared with the original interaction policy, DisGuAD improves normalized Reward by 4.40--8.97 points and raises overall critical-ambiguity coverage from 48.62% to 82.75% and from 45.76% to 85.14%. Its clarification signals further improve two independently designed static text-to-SQL frameworks by up to 13.97 Reward points while keeping their SQL generators fixed. These results demonstrate that disagreement among plausible SQL queries provides actionable evidence for selecting clarification targets that matter to downstream generation.
Subjects: Databases (cs.DB); Computation and Language (cs.CL)
Cite as: arXiv:2611.21645 [cs.DB]
  (or arXiv:2611.21645v1 [cs.DB] for this version)
  https://doi.org/10.48550/arXiv.2611.21645

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Su Dong [view email]
[v1] Wed, 14 Oct 2026 11:10:26 UTC (1,966 KB)

来源:arXiv cs.CL · arxiv.org