{"slug": "when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in", "title": "When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue", "summary": "A new arXiv paper (2611.05517v1) introduces BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action-chooser built on a frozen language model backbone that more consistently selects the optimal number of clarifying questions than GRPO and ArCHer. The authors built a controlled test environment from the SIMMC 2.1 dataset that records how many questions each ambiguous reference needs to resolve, and used it to compare baseline LLM behavior and common post-training methods on asking clarifying questions versus answering prematurely. The work targets LLMs' documented bias toward definite single-turn answers over clarification exchanges in reference games.", "body_md": "arXiv:2611.05517v1 Announce Type: new \nAbstract: For humans, referential disambiguation is a collaborative process involving clarification questions asked when they will meaningfully change the outcome. However, large language models (LLMs) have been shown to be biased toward premature answering, preferring definite single-turn responses over more clarification exchanges. In this paper, we study the problem of \"strategic clarification\" -- asking clarification questions in a reference game when their answers will narrow the set of candidate referents. We construct a controlled test environment from the SIMMC 2.1 dataset that records how many questions each ambiguous reference needs to be successfully resolved, and examine how baseline LLM behavior and common post-training methods ask clarifying questions vs. attempt to answer the referent. We also propose BACE (Belief-Aware Critic with Epistemic tracking), a lightweight action chooser method on top of a frozen LM backbone, and show that BACE more consistently chooses the optimal number of clarifying questions than methods such as GRPO and ArCHer.", "url": "https://wpnews.pro/news/when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in", "canonical_source": "https://arxiv.org/abs/2611.05517", "published_at": "2026-11-05 05:00:00+00:00", "updated_at": "2026-11-05 05:19:23.575317+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "ai-research", "ai-agents"], "entities": ["BACE", "GRPO", "ArCHer", "SIMMC 2.1", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in", "markdown": "https://wpnews.pro/news/when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in.md", "text": "https://wpnews.pro/news/when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in.txt", "jsonld": "https://wpnews.pro/news/when-to-ask-when-to-answer-strategic-clarification-for-ambiguous-reference-in.jsonld"}}