arXiv cs.CL· Jingqin Tang, Tim Tomov, Sebastian Schmidt, Dominik Fuchsgruber, Stephan G\"unnemann·· 3 天前AI 评分23
什么是澄清？估计依赖模型的输入歧义
What Is a Clarification? Estimating Model-Dependent Input Ambiguity
AI 导读
研究者区分了"世界歧义"与"模型歧义"：前者指输入本身允许的所有解释，后者指特定语言模型实际可理解并回答的解释。他们通过唯一性、忠实性和答案等价性三项准则，建立了有效答案与澄清等价类之间的一一对应关系，并提出黑盒方法 CircleClar，沿"答案—澄清—答案"循环检验一致性来估计模型可用的答案集合。
正文 · 原文
Abstract:Ambiguous inputs can admit multiple interpretations, each potentially yielding a different answer. Existing work largely treats this ambiguity as a property of the input, yet for a particular language model, only some alternatives may be known and answerable. We therefore distinguish world ambiguity, capturing all alternatives admitted by an input, from model ambiguity, capturing those accessible to the responding model. To characterize these alternatives, we formalize natural-language clarifications through three desiderata: \emph{uniqueness}, \emph{faithfulness}, and \emph{answer equivalence}. We show that these desiderata induce a one-to-one correspondence between valid answers and equivalence classes of clarifications, implying that any interpretation can be represented either by its answer or by the clarifications that uniquely express it. We leverage this correspondence to introduce \circleclar{}, a black-box method that estimates the set of answers available to a model by checking consistency along an answer--clarification--answer cycle. Across open-domain QA and executable Text-to-SQL, \circleclar{} achieves strong recovery of these answer sets. In QA, the recovered support yields the strongest overall performance in model-dependent ambiguity detection and enables effective selection among answering, clarifying, and abstaining. Together, these results demonstrate the practical value of a model-dependent view of ambiguity and its characterization through an answer-clarification correspondence.
| Comments: | Outstanding Paper Award and Oral Presentation at the NeurIPS 2026 Workshop on Linguistic Principles for Foundation Models (LP4FM) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20052 [cs.CL] |
| (or arXiv:2610.20052v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20052 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tim Tomov [view email]
[v1]
Wed, 14 Oct 2026 11:54:42 UTC (178 KB)
来源：arXiv cs.CL · arxiv.org