InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain

Key points

• Recent advances in reasoning-oriented large language models (LLMs) have motivated increasing evaluation of their ability to perform professional decision tasks.1
• 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.1
• 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.1
• Evaluation of six LLMs reveals a progressive loss of reliability along the decision chain.1

Sources (1)

• [1]InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 08:35 AM

  We introduce InsClaimBench, an end-to-end benchmark for evaluating insurance claim adjudication across the decision chain.

  Recent advances in reasoning-oriented large language models (LLMs) have motivated increasing evaluation of their ability to perform professional decision tasks.

Extractive summary: sentences quoted from the sources.