Metraipolis › archive › dc_f79a124cc366

When Should I Trust This? Designing and Evaluating Factuality Indicators for LLM-based Chatbots — arXiv:2610.32883

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.32883
License (as archived): CC0-1.0
Archived: 2026-10-26T20:08:24.208Z
SHA-256 of the archived text: dd36bf1ea233b34d3000ba62862313f1ed2677cb813e4f957c588052460f5051
Stable URL of this page: https://metraipolis.com/documento/dc_f79a124cc366

How to cite

When Should I Trust This? Designing and Evaluating Factuality Indicators for LLM-based Chatbots — arXiv:2610.32883 — arXiv (en), https://arxiv.org/abs/2610.32883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f79a124cc366 (Metraipolis archive dc_f79a124cc366, sha256 dd36bf1ea233b34d3000ba62862313f1ed2677cb813e4f957c588052460f5051)

BibTeX

@misc{dcf79a124cc366,
  title = {When Should I Trust This? Designing and Evaluating Factuality Indicators for LLM-based Chatbots — arXiv:2610.32883},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32883},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f79a124cc366; sha256 dd36bf1ea233b34d3000ba62862313f1ed2677cb813e4f957c588052460f5051},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative AI systems increasingly mediate how people seek information, yet communicating AI factuality to laypeople remains challenging. Through a mixed-methods investigation involving interviews (N=8), a survey (N=1,000), and an experiment (N=5,151), we examine how people evaluate AI-generated information for gardening, mathematical, and medical queries, and how factuality indicators (confidence and sources) shape perceptions. Our interviews and survey show people selectively verify AI responses using external and AI-provided evidence, moderated by contextual factors. Although confidence-indicators affected trust and accuracy perceptions, people hold diverse, ambiguous interpretations of AI confidence. Sources were viewed as crucial, yet users raised concerns about source reliability and verification effort. Our experiment showed that confidence and source-based indicators influenced initial perceptions, but effects disappeared once participants learned the response's correctness. Medical queries elicited skepticism regardless of indicator. Findings motivate helping users interpret model confidence and integrating source information into the interface to support calibrated trust in AI-supported information-seeking.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.32883 — 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 2026-10-26T19:48:48.358Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).