From Policy to Logic for Efficient and Interpretable Coverage Assessment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914240906919936 |
|---|---|
| author | Pokharel, Rhitabrat Hassanzadeh, Hamid Reza Agrawal, Ameeta |
| author_facet | Pokharel, Rhitabrat Hassanzadeh, Hamid Reza Agrawal, Ameeta |
| contents | Large Language Models (LLMs) have demonstrated strong capabilities in interpreting lengthy, complex legal and policy language. However, their reliability can be undermined by hallucinations and inconsistencies, particularly when analyzing subjective and nuanced documents. These challenges are especially critical in medical coverage policy review, where human experts must be able to rely on accurate information. In this paper, we present an approach designed to support human reviewers by making policy interpretation more efficient and interpretable. We introduce a methodology that pairs a coverage-aware retriever with symbolic rule-based reasoning to surface relevant policy language, organize it into explicit facts and rules, and generate auditable rationales. This hybrid system minimizes the number of LLM inferences required which reduces overall model cost. Notably, our approach achieves a 44% reduction in inference cost alongside a 4.5% improvement in F1 score, demonstrating both efficiency and effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01266 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Policy to Logic for Efficient and Interpretable Coverage Assessment Pokharel, Rhitabrat Hassanzadeh, Hamid Reza Agrawal, Ameeta Computation and Language Artificial Intelligence Large Language Models (LLMs) have demonstrated strong capabilities in interpreting lengthy, complex legal and policy language. However, their reliability can be undermined by hallucinations and inconsistencies, particularly when analyzing subjective and nuanced documents. These challenges are especially critical in medical coverage policy review, where human experts must be able to rely on accurate information. In this paper, we present an approach designed to support human reviewers by making policy interpretation more efficient and interpretable. We introduce a methodology that pairs a coverage-aware retriever with symbolic rule-based reasoning to surface relevant policy language, organize it into explicit facts and rules, and generate auditable rationales. This hybrid system minimizes the number of LLM inferences required which reduces overall model cost. Notably, our approach achieves a 44% reduction in inference cost alongside a 4.5% improvement in F1 score, demonstrating both efficiency and effectiveness. |
| title | From Policy to Logic for Efficient and Interpretable Coverage Assessment |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.01266 |