Metraipolis › archive › dc_f8d7684cddbd

Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents — arXiv:2611.09768

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09768
License (as archived)
CC0-1.0
Archived
2026-11-09T22:35:15.419Z
SHA-256 of the archived text
dc481447ada6f2d3659778f62b462b7a80cb719b5332b00155ad4cb5a2f5055a
Stable URL of this page
https://metraipolis.com/documento/dc_f8d7684cddbd

How to cite

Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents — arXiv:2611.09768 — arXiv (en), https://arxiv.org/abs/2611.09768 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f8d7684cddbd (Metraipolis archive dc_f8d7684cddbd, sha256 dc481447ada6f2d3659778f62b462b7a80cb719b5332b00155ad4cb5a2f5055a)
BibTeX
@misc{dcf8d7684cddbd,
  title = {Language as Trait, Politeness as Strategy: Controlled Tests of Linguistic Effects in LLM Social-Deduction Agents — arXiv:2611.09768},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09768},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f8d7684cddbd; sha256 dc481447ada6f2d3659778f62b462b7a80cb719b5332b00155ad4cb5a2f5055a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09768. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) agents coordinate through conversation, and the same message can be phrased in simpler or more complex language, bluntly or politely. We test whether such differences change how other agents judge and act, using the LURK Werewolf framework, which separates each utterance's speech-act predicate from its natural-language realization. We rewrite only the realization, check that the game content is preserved, and replay each game day from saved checkpoints against a re-sampled control. We vary linguistic range consistently across a speaker's messages and politeness strategy per utterance. Across 30 games and 4,335 replays, neither manipulation changes the trust other agents place in the speaker, and no effect on votes or night actions survives correction for multiple comparisons; the largest uncorrected effect is that shifting range away from a neutral paraphrase changes about 4 percentage points more of the other players' votes. In natural play, 88% of face-threatening speech is bald on-record regardless of role.

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/2611.09768 — 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 2026-11-09T22:30:47.342Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).