From Policy to Logic for Efficient and Interpretable Coverage Assessment

Rhitabrat Pokharel, Hamid Reza Hassanzadeh, Ameeta Agrawal
Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:191-200, 2026.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v317-pokharel26a, title = {From Policy to Logic for Efficient and Interpretable Coverage Assessment}, author = {Pokharel, Rhitabrat and Hassanzadeh, Hamid Reza and Agrawal, Ameeta}, booktitle = {Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {191--200}, year = {2026}, editor = {Wu, Junde and Pan, Jiazhen and Zhu, Jiayuan and Luo, Luyang and Li, Yitong and Xu, Min and Jin, Yueming and Rueckert, Daniel}, volume = {317}, series = {Proceedings of Machine Learning Research}, month = {20--21 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v317/main/assets/pokharel26a/pokharel26a.pdf}, url = {https://proceedings.mlr.press/v317/pokharel26a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T From Policy to Logic for Efficient and Interpretable Coverage Assessment %A Rhitabrat Pokharel %A Hamid Reza Hassanzadeh %A Ameeta Agrawal %B Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2026 %E Junde Wu %E Jiazhen Pan %E Jiayuan Zhu %E Luyang Luo %E Yitong Li %E Min Xu %E Yueming Jin %E Daniel Rueckert %F pmlr-v317-pokharel26a %I PMLR %P 191--200 %U https://proceedings.mlr.press/v317/pokharel26a.html %V 317 %X 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.
APA
Pokharel, R., Hassanzadeh, H.R. & Agrawal, A.. (2026). From Policy to Logic for Efficient and Interpretable Coverage Assessment. Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 317:191-200 Available from https://proceedings.mlr.press/v317/pokharel26a.html.

Related Material