# Policy-as-logic for robust reasoning over rules

arXiv: https://arxiv.org/abs/2608.11905 · HTML: https://mlsanity.com/paper/2608.11905/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 8 of 8)

- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages](https://mlsanity.com/paper/2504.04377/) (2025)
- [Clingo = ASP + Control: Preliminary Report](https://mlsanity.com/paper/1405.3694/) (2014)
- [Logical Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2502.09100/) (2025)
- [CL-bench: A Benchmark for Context Learning](https://mlsanity.com/paper/2602.03587/) (2026)
- [Granite Guardian](https://mlsanity.com/paper/2412.07724/) (2024)
- [DeonticBench: A Benchmark for Reasoning over Rules](https://mlsanity.com/paper/2604.04443/) (2026)

## Abstract (arXiv)

In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect written policies or rules. We present a hybrid symbolic approach that expresses policies in formal logic and at inference time exploits the representation power of language models for fact extraction to ground predicates, and an answer set solver for reasoning such that responses are interpretable, auditable, and as we show, accurate and robust under input perturbations. Specifically, we show this separation of extraction and reasoning steps outperforms policy-as-prompt and policy-as-code methods in most cases with ~10x reduction in token usage. The results point to the value of structured reasoning and symbolic solvers in conjunction with generative models to make robust decisions involving objective criteria.