Metraipolis › archive › dc_a3ceeaa43453

Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets — arXiv:2609.07095

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07095
License (as archived)
CC0-1.0
Archived
2026-10-16T12:57:08.406Z
SHA-256 of the archived text
235892f4d700f8b45917e96f3d0b80c195199f16679749edae9ebdad07c57e42
Stable URL of this page
https://metraipolis.com/documento/dc_a3ceeaa43453

How to cite

Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets — arXiv:2609.07095 — arXiv (en), https://arxiv.org/abs/2609.07095 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3ceeaa43453 (Metraipolis archive dc_a3ceeaa43453, sha256 235892f4d700f8b45917e96f3d0b80c195199f16679749edae9ebdad07c57e42)
BibTeX
@misc{dca3ceeaa43453,
  title = {Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets — arXiv:2609.07095},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07095},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3ceeaa43453; sha256 235892f4d700f8b45917e96f3d0b80c195199f16679749edae9ebdad07c57e42},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07095. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM assistants often produce more answers than humans can review before users see them. Most evaluations ask whether an answer is wrong, unsupported, or low-confidence. Bounded review budgets instead ask which answers should be checked first under a fixed review budget. Risk alone is not enough: a high-risk answer may be hard to repair, while a moderately risky answer may be directly correctable from available evidence. For generated-answer evaluation, we model review prioritization as exposure reduction, where review value combines estimated wrongness, intervention affordance, impact, and cost. We evaluate review queues with Wrong-Answer Exposure Ratio (WAER), the fraction of wrong answers left unreviewed, and post-repair residual exposure (PRRE), the fraction still exposed after deterministic benchmark-supported repairs. PRRE uses repairability rules that do not numerically reuse the affordance scores used for ranking. On a 720-item TAT-QA/SciFact stress benchmark, review-value ranking keeps answer-level WAER nearly unchanged at 20% budget (0.605 vs. 0.600) but lowers PRRE from 0.881 to 0.716. These results show that trustworthy LLM evaluation should measure not only error detection, but also how limited review capacity reduces exposed wrong answers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.07095 — 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 2026-10-16T12:30:25.303Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).