Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.08082 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917073091821568 |
|---|---|
| author | Dong, Stella C. |
| author_facet | Dong, Stella C. |
| contents | This paper develops a prudential framework for assessing the reliability of large language models (LLMs) in reinsurance. A five-pillar architecture--governance, data lineage, assurance, resilience, and regulatory alignment--translates supervisory expectations from Solvency II, SR 11-7, and guidance from EIOPA (2025), NAIC (2023), and IAIS (2024) into measurable lifecycle controls. The framework is implemented through the Reinsurance AI Reliability and Assurance Benchmark (RAIRAB), which evaluates whether governance-embedded LLMs meet prudential standards for grounding, transparency, and accountability. Across six task families, retrieval-grounded configurations achieved higher grounding accuracy (0.90), reduced hallucination and interpretive drift by roughly 40%, and nearly doubled transparency. These mechanisms lower informational frictions in risk transfer and capital allocation, showing that existing prudential doctrines already accommodate reliable AI when governance is explicit, data are traceable, and assurance is verifiable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08082 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency Dong, Stella C. Artificial Intelligence Machine Learning General Economics Economics 91B30, 62P05, 68T07 I.2.7; J.1; G.3 This paper develops a prudential framework for assessing the reliability of large language models (LLMs) in reinsurance. A five-pillar architecture--governance, data lineage, assurance, resilience, and regulatory alignment--translates supervisory expectations from Solvency II, SR 11-7, and guidance from EIOPA (2025), NAIC (2023), and IAIS (2024) into measurable lifecycle controls. The framework is implemented through the Reinsurance AI Reliability and Assurance Benchmark (RAIRAB), which evaluates whether governance-embedded LLMs meet prudential standards for grounding, transparency, and accountability. Across six task families, retrieval-grounded configurations achieved higher grounding accuracy (0.90), reduced hallucination and interpretive drift by roughly 40%, and nearly doubled transparency. These mechanisms lower informational frictions in risk transfer and capital allocation, showing that existing prudential doctrines already accommodate reliable AI when governance is explicit, data are traceable, and assurance is verifiable. |
| title | Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency |
| topic | Artificial Intelligence Machine Learning General Economics Economics 91B30, 62P05, 68T07 I.2.7; J.1; G.3 |
| url | https://arxiv.org/abs/2511.08082 |