Metraipolis › archive › dc_fa7f4fc7ebf3
InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain — arXiv:2610.09671
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09671
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:26:10.103Z
- SHA-256 of the archived text
121f89e9893614578687466aa2f3a84bf0824b500c5a7fa518558c42ec7e1293- Stable URL of this page
https://metraipolis.com/documento/dc_fa7f4fc7ebf3
How to cite
InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain — arXiv:2610.09671 — arXiv (en), https://arxiv.org/abs/2610.09671 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa7f4fc7ebf3 (Metraipolis archive dc_fa7f4fc7ebf3, sha256 121f89e9893614578687466aa2f3a84bf0824b500c5a7fa518558c42ec7e1293)
BibTeX
@misc{dcfa7f4fc7ebf3,
title = {InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain — arXiv:2610.09671},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09671},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa7f4fc7ebf3; sha256 121f89e9893614578687466aa2f3a84bf0824b500c5a7fa518558c42ec7e1293},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09671. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in reasoning-oriented large language models (LLMs) have motivated increasing evaluation of their ability to perform professional decision tasks. Insurance claim adjudication is one such task, requiring models to connect case evidence, insurance rules, intermediate judgments, and payout calculations across a structured decision process. We introduce InsClaimBench, an end-to-end benchmark for evaluating insurance claim adjudication across the decision chain. Grounded in real claim materials and structured insurance rules, InsClaimBench contains 3,780 cases in 375 case families across auto, property, and health insurance, comprising 86,656 atomic rule judgments. It evaluates each claim from atomic rules through adjudication modules to payout decisions and amounts, with controlled factual variants testing whether required changes are correctly propagated across levels. Evaluation of six LLMs reveals a progressive loss of reliability along the decision chain. Payout-decision accuracy ranges from 74.23--80.19%, while joint decision--amount accuracy drops to 47.54--73.15%. Strong local performance also fails to ensure case-level correctness: atomic-rule accuracy reaches 95.48%, whereas rule-vector exact match peaks at only 36.90%, and the most frequent module errors are not necessarily those most associated with final-decision failure. Under factual changes, these inconsistencies further become propagation failures: module updates are less reliable than rule updates, correct local judgments can still yield incorrect payouts, and correct payouts can conceal intermediate errors. These results show that reliable claim adjudication requires consistent composition and propagation across the decision chain. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.09671 — 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 2026-10-08T10:24:06.330Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).