Metraipolis › archive › dc_286bea3864d1

Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention — arXiv:2608.21721

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21721
License (as archived)
CC0-1.0
Archived
2026-10-18T07:38:49.678Z
SHA-256 of the archived text
0b7a3deffc73eb6f6d21541764dd8bef427ec5730ac88d3fad5490eea38885b6
Stable URL of this page
https://metraipolis.com/documento/dc_286bea3864d1

How to cite

Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention — arXiv:2608.21721 — arXiv (en), https://arxiv.org/abs/2608.21721 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_286bea3864d1 (Metraipolis archive dc_286bea3864d1, sha256 0b7a3deffc73eb6f6d21541764dd8bef427ec5730ac88d3fad5490eea38885b6)
BibTeX
@misc{dc286bea3864d1,
  title = {Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention — arXiv:2608.21721},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21721},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_286bea3864d1; sha256 0b7a3deffc73eb6f6d21541764dd8bef427ec5730ac88d3fad5490eea38885b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21721. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Correcting health misinformation in dialogue requires more than producing a factual rebuttal: users differ in what they know, what they believe, and what they need to hear, so an effective intervention often depends on first asking the right clarifying question. Yet existing methods either respond immediately or probe indiscriminately, treating clarification as either unnecessary or always beneficial. We propose Reward-Optimized Probe-and-Respond (RO-PnR), a framework that learns when asking is worth its cost. At each turn, RO-PnR chooses between probing for more information and committing to a final correction, guided by a turn-level reward that weighs the expected gain from probing against its interaction cost. To capture how user heterogeneity affects probing value, we model each simulated user with a latent state along health literacy and belief commitment. Experiments show that RO-PnR achieves the highest cost-adjusted utility across three health-misinformation datasets and three base models, using 30% fewer turns than always-probe baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.21721 — 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 2026-10-18T07:37:52.665Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).