Metraipolis › archive › dc_425fb97273e1

Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals — arXiv:2610.08413

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08413
License (as archived)
CC0-1.0
Archived
2026-10-07T11:21:46.034Z
SHA-256 of the archived text
96096b6cce8e2545d3924b25a49bf61f990999b35c371120ccd6e226e87be3b0
Stable URL of this page
https://metraipolis.com/documento/dc_425fb97273e1

How to cite

Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals — arXiv:2610.08413 — arXiv (en), https://arxiv.org/abs/2610.08413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_425fb97273e1 (Metraipolis archive dc_425fb97273e1, sha256 96096b6cce8e2545d3924b25a49bf61f990999b35c371120ccd6e226e87be3b0)
BibTeX
@misc{dc425fb97273e1,
  title = {Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals — arXiv:2610.08413},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_425fb97273e1; sha256 96096b6cce8e2545d3924b25a49bf61f990999b35c371120ccd6e226e87be3b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models routinely answer questions that cannot be answered from the information given, and in dialogue they answer before enough has been said. Unanswerability is linearly decodable from hidden states, but it is unclear which of its forms share a representation and whether the signal is useful in dialogue. We contribute a turn-labeled multi-turn benchmark (423 conversations, 1,661 labeled turn-states) and an evaluation harness with a simulated user who answers clarifying questions, and use them with six datasets and six open-weight LLMs to test how far probes for unanswerability carry. Probes transfer robustly between datasets that share a ground of unanswerability: missing information in math (AUROC 0.77-0.97) and in a passage (SQuAD 2.0<->MuSiQue, 0.77-0.90). Probes for epistemic "known-unknowns" transfer poorly to math, but this separation weakens under lexical controls and changes with layer and coordinate system, so it remains unresolved. Single-turn probes fail zero-shot to detect when a conversation becomes answerable; in-structure probes recover it, but no better than a bag-of-words classifier. A gate on the calibrated probe, with no model fine-tuning, fires on underspecified turns far more precisely than chance, and its end-task success comes within 0.08 of a gate given the true labels. Yet across four models it does not reliably beat vanilla generation or prompted consolidation. The remaining gap lies mostly in how models use a clarification, not in detection.

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); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.08413 — 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 2026-10-07T11:15:24.826Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).