Metraipolis › archive › dc_422d2cf79863

When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue — arXiv:2611.05517

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05517
License (as archived)
CC0-1.0
Archived
2026-11-05T18:17:22.990Z
SHA-256 of the archived text
4526cd97628a2cdb55f8d2a048598d0ddc1c88482dabeb60dd836bb2d254632f
Stable URL of this page
https://metraipolis.com/documento/dc_422d2cf79863

How to cite

When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue — arXiv:2611.05517 — arXiv (en), https://arxiv.org/abs/2611.05517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_422d2cf79863 (Metraipolis archive dc_422d2cf79863, sha256 4526cd97628a2cdb55f8d2a048598d0ddc1c88482dabeb60dd836bb2d254632f)
BibTeX
@misc{dc422d2cf79863,
  title = {When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue — arXiv:2611.05517},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05517},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_422d2cf79863; sha256 4526cd97628a2cdb55f8d2a048598d0ddc1c88482dabeb60dd836bb2d254632f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.05517 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:12:49.027Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).