# Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework

arXiv: https://arxiv.org/abs/2608.26124 · HTML: https://mlsanity.com/paper/2608.26124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios](https://mlsanity.com/paper/2412.08972/) (2024)
- [WeLM: A Well-Read Pre-trained Language Model for Chinese](https://mlsanity.com/paper/2209.10372/) (2022)
- [GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees](https://mlsanity.com/paper/2411.08257/) (2024)
- [From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models](https://mlsanity.com/paper/2601.18091/) (2026)
- [PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks](https://mlsanity.com/paper/2510.12409/) (2025)

## Abstract (arXiv)

Pricing automation in large-scale tourism is challenging because travel orders are highly unstructured, while pricing policies are complex, rapidly evolving, and inherently open-ended. Traditional rule engines are brittle and costly to maintain, whereas unconstrained LLM agents lack the reliability and auditability required for financial decisions. We present a production-grade LLM-powered pricing system with a strict decision boundary: LLMs perform structured extraction and bounded policy/path selection, while all numeric pricing, including total-price computation, is executed deterministically. Policies are compiled into interpretable condition trees, enabling open-ended support for new clauses and evolving rules without code changes, while exposing auditable artifacts for human-in-the-loop control. Periodic fine-tuning on logged traces further improves tree induction and path matching. Deployed at a municipal state-owned tourism enterprise across 7 scenic sites and 12 business categories with 1,500+ operators and 1,000+ active policies, the system processed 3,960 orders in six months, reduced the order management team from 15-20 to 3, and cut per-order handling time from 10 minutes to <2 minutes.