Metraipolis › archive › dc_58fbd56d022b
Precedent Labels and Facts Shift LLM Approval Decisions in Opposite Directions — arXiv:2611.00672
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00672
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:34:22.346Z
- SHA-256 of the archived text
f34e25bfe5b779ef82f92875716fcefd1fb0ebd35527f614f1759e302a834697- Stable URL of this page
https://metraipolis.com/documento/dc_58fbd56d022b
How to cite
Precedent Labels and Facts Shift LLM Approval Decisions in Opposite Directions — arXiv:2611.00672 — arXiv (en), https://arxiv.org/abs/2611.00672 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58fbd56d022b (Metraipolis archive dc_58fbd56d022b, sha256 f34e25bfe5b779ef82f92875716fcefd1fb0ebd35527f614f1759e302a834697)
BibTeX
@misc{dc58fbd56d022b,
title = {Precedent Labels and Facts Shift LLM Approval Decisions in Opposite Directions — arXiv:2611.00672},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00672},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58fbd56d022b; sha256 f34e25bfe5b779ef82f92875716fcefd1fb0ebd35527f614f1759e302a834697},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00672. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When a language model decides refund or claim requests under written policies, the system can show it similar past cases. Each past case has two parts: its facts and the decision recorded for it. We separate the two. A model sees a policy, a request and three past cases, and we change either the recorded decisions or the facts, keeping the request fixed. We select requests that are close calls: deciding without past cases, DeepSeek V4.1 Flash approved each in some of four tries and denied it in others. When the past cases are near-copies of the request (its facts with a few details changed), switching their recorded decisions from DENY to APPROVE raises approval by about 30 to 55 percentage points in DeepSeek V4.1 Flash, GPT-5.6 Luna and Claude Haiku 5.5 on policies written for the study, and DeepSeek and Luna show the same on nine public policies paraphrased from real ones. The facts push the other way: shown without their recorded decisions, past cases whose facts support approval make these two models approve less often than past cases whose facts support denial. One reading is that the request looks weaker next to them. This push is not just a correction toward the right answer: in an additional DeepSeek analysis, it was of similar estimated size on requests that human annotators judged approvable and on those they judged deniable. In a separate DeepSeek run on the public policies, when the past cases are near-copies of a different request, switching their decisions moves approval by 9 points instead of 43, while facts that support approval still lower it by 22 points against facts that support denial. Systems that retrieve past decisions should test the two parts separately. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.00672 — 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 2026-11-03T10:29:48.715Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).