Metraipolis › archive › dc_69bfbd6e42e6

Using Semantic Uncertainty to Estimate Transition Relevance in Turn-taking — arXiv:2609.10934

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10934
License (as archived): CC0-1.0
Archived: 2026-10-16T05:40:40.513Z
SHA-256 of the archived text: e79c8faef1567fe77403fac32442a58e6cc8fa24e1bb86816c294e0ebc86b289
Stable URL of this page: https://metraipolis.com/documento/dc_69bfbd6e42e6

How to cite

Using Semantic Uncertainty to Estimate Transition Relevance in Turn-taking — arXiv:2609.10934 — arXiv (en), https://arxiv.org/abs/2609.10934 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69bfbd6e42e6 (Metraipolis archive dc_69bfbd6e42e6, sha256 e79c8faef1567fe77403fac32442a58e6cc8fa24e1bb86816c294e0ebc86b289)

BibTeX

@misc{dc69bfbd6e42e6,
  title = {Using Semantic Uncertainty to Estimate Transition Relevance in Turn-taking — arXiv:2609.10934},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10934},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69bfbd6e42e6; sha256 e79c8faef1567fe77403fac32442a58e6cc8fa24e1bb86816c294e0ebc86b289},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10934. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Turn-taking is a fundamental mechanism that governs when interlocutors speak and listen. Although Spoken Dialogue Systems (SDS) exploit a range of linguistic, acoustic, and non-verbal cues, they produce ill-timed responses in unscripted interaction. A central challenge is anticipating Transition Relevance Places (TRPs), or opportunities, not obligations, for a listener to take the floor. Human listeners do not wait for turn endings; as an utterance unfolds, they use expectations about its developing meaning to anticipate TRPs and decide whether to take the floor. We examine whether these evolving expectations can be modeled through semantic uncertainty -- an LLM-derived measure of how strongly a turn so far constrains what may plausibly come next. To do so, we sample possible continuations of an ongoing turn and use changes in semantic dispersion to identify TRPs within turns. We evaluate this account on a dataset with TRP labels derived from real-time listener responses, rather than retrospective annotation. Our approach substantially outperforms prompt-based and fine-tuned text-only baselines, providing empirical support for the view that evolving semantic constraints inform perceived turn-taking opportunities in unscripted interaction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.10934 — 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 2026-10-16T05:23:56.989Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).