Metraipolis › archive › dc_e29db2b65a8d

Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation — arXiv:2608.28467

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28467
License (as archived)
CC0-1.0
Archived
2026-10-17T10:56:38.169Z
SHA-256 of the archived text
98c6478f3f3aabbb36ddc51e80f6e1cf7a7e392f7cf402800be4b397a151cc22
Stable URL of this page
https://metraipolis.com/documento/dc_e29db2b65a8d

How to cite

Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation — arXiv:2608.28467 — arXiv (en), https://arxiv.org/abs/2608.28467 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e29db2b65a8d (Metraipolis archive dc_e29db2b65a8d, sha256 98c6478f3f3aabbb36ddc51e80f6e1cf7a7e392f7cf402800be4b397a151cc22)
BibTeX
@misc{dce29db2b65a8d,
  title = {Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation — arXiv:2608.28467},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28467},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e29db2b65a8d; sha256 98c6478f3f3aabbb36ddc51e80f6e1cf7a7e392f7cf402800be4b397a151cc22},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28467. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whose biography can vary across training, inference, and evaluation. Prior work often neglected these aspects, obscuring mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation, a three-stage factorisation that prior work has largely treated as a single factor. We study this factorisation on a dataset of dialogues paired with speaker's biographies, varying whether the target and interlocutor speakers see each other's biographies during training and inference, and using an LLM as a judge to perform author identification. We find that (i) training-time visibility, more than inference-time visibility, determines whether models express persona traits through dialogue or fall back on copying biographical text (a known problem/phenomenon in persona-based generation); (ii) models trained with interlocutor-biography visibility copy less target-biographical text than models trained without it, while changing visibility only at inference time has a less consistent effect; and (iii) under asymmetric disclosure, where only the interlocutor sees the target biography, target content leaks into interlocutor turns more often, and dialogues containing such traces are easier for the judge to identify, especially when interlocutor turns are visible. These results suggest that biography leakage into generated turns is an artefact of how interlocutor visibility is configured across training and inference, and separating the three stages is necessary.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.28467 — 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 2026-10-17T10:47:33.142Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).