Metraipolis › archive › dc_9152300bb9bb
Relevance is not enough: A Communication-Oriented Retrieval System for Consequential Scientific Question Answering — arXiv:2609.06222
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06222
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:05:20.776Z
- SHA-256 of the archived text
12de2e74e46eb30467b25cbc93ee18d8395548769f4b60de565f89538965566f- Stable URL of this page
https://metraipolis.com/documento/dc_9152300bb9bb
How to cite
Relevance is not enough: A Communication-Oriented Retrieval System for Consequential Scientific Question Answering — arXiv:2609.06222 — arXiv (en), https://arxiv.org/abs/2609.06222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9152300bb9bb (Metraipolis archive dc_9152300bb9bb, sha256 12de2e74e46eb30467b25cbc93ee18d8395548769f4b60de565f89538965566f)
BibTeX
@misc{dc9152300bb9bb,
title = {Relevance is not enough: A Communication-Oriented Retrieval System for Consequential Scientific Question Answering — arXiv:2609.06222},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9152300bb9bb; sha256 12de2e74e46eb30467b25cbc93ee18d8395548769f4b60de565f89538965566f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI systems increasingly answer scientific questions about health, safety, and the environment. But most retrieval-augmented generation systems are tuned to provide factually correct, on-topic answers rather than to help non-experts understand what those answers mean for their lives and decisions. We focus on consequential scientific questions whose results directly shape people's lives and study them through a public water-quality communication system, where residents and community leaders interpret the findings and choose actions. Their experiences show that on-topic answers can still be insufficient without explanation and context and that the emotional weight of risk information cannot be ignored. Our system first classifies each question by reasoning type (for example, causal versus policy-based), then generates follow-up questions to identify missing evidence and retrieve it. One component clearly distinguishes between what is known and what is uncertain, while another rewrites scientific details into accessible language, using persona-based styles, such as a caring neighbor or an administrative official, to adapt tone and readability. Ablations on over $160$ questions show that the system uses $\textit{an order of magnitude less context}$ and, in several configurations, improves human-rated completeness. A completeness metric co-designed with community members and a fine-tuned learned judge reveal that standard relevance scores explain about $1\%$ of variation in human completeness ratings, and even the tuned judge only moderately aligns with humans, indicating that completeness is a distinct human-centered objective that current metrics do not reliably capture.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.06222 — 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 2026-10-16T14:49:33.942Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).