Policy-as-logic for robust reasoning over rules

• URL: http://arxiv.org/abs/2608.11905v1
• Date: Wed, 12 Aug 2026 10:30:25 GMT
• Title: Policy-as-logic for robust reasoning over rules
• Abstract summary: In many practical applications of generative AI systems, responses to natural language queries must respect written policies or rules.<n>We present a hybrid symbolic approach that expresses policies in formal logic and at inference time.<n>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.
• Score: 10.861189637998168
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative Scoring [77.17706435067372]
  Large Policy (LDiP) is a fully discrete behavior modeling framework that selects actions from a large vocabulary of physically plausible candidates.<n>Rather than perturbing actions, LDiP improves expressivity through iterative scoring.<n>Across end-to-end planning, closed-loop driving, robotic manipulation, and vision-language-action settings, LDiP consistently outperforms strong discrete and continuous baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:12:52Z)
• DeonticBench: A Benchmark for Reasoning over Rules [52.69517904415795]
  DEONTICBENCH is a benchmark of 6,232 tasks across U.S. federal taxes, airline baggage policies, U.S. immigration administration, and U.S. state housing law.<n>It is a benchmark for studying context-grounded rule reasoning in real-world domains under both symbolic and non-symbolic settings.
  arXiv  Detail & Related papers  (2026-04-06T05:41:02Z)
• Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models [49.65762241649762]
  We propose a framework that treats sequences of K consecutive tokens as unified semantic actions.<n> Experiments on mathematical reasoning and coding benchmarks show that MPO outperforms standard token-level policy gradient baselines.
  arXiv  Detail & Related papers  (2026-02-16T01:28:38Z)
• KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering [64.62317305868264]
  We present textbfKBQA-R1, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning.<n>Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions.<n>Experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-10T17:45:42Z)
• Explainable Rule Application via Structured Prompting: A Neural-Symbolic Approach [0.0]
  Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability.<n>This paper introduces a structured prompting framework that decomposes reasoning into three verifiable steps: entity identification, property extraction, and symbolic rule application.
  arXiv  Detail & Related papers  (2025-06-19T14:14:01Z)
• Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate [11.890202757543307]
  This paper systematically addresses the challenges of rule retrieval, a crucial yet underexplored area.<n> Vanilla retrieval methods using sparse or dense retrievers to directly search for relevant rules often suffer from low accuracy.<n>We propose Self-Induction Augmented Retrieval (SIAR), a novel approach that utilizes Large Language Models (LLMs) to induce potential inferential rules.
  arXiv  Detail & Related papers  (2025-05-16T05:22:42Z)
• Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical Solvers [4.897782942277061]
  We introduce Semantic Self-Verification (SSV), a novel approach to accurately formulate the reasoning problem from natural language to the formal language of the solver.<n>SSV uses a consistency-based approach to produce strong abstract formalizations of problems using concrete instantiations that are generated by the model and verified by the solver.<n>We propose such *near-certain reasoning* as a new approach to reduce the need for manual verification in many cases, taking us closer to more dependable and autonomous AI reasoning systems.
  arXiv  Detail & Related papers  (2025-01-28T14:04:49Z)
• Few-shot Policy (de)composition in Conversational Question Answering [54.259440408606515]
  We propose a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting.<n>We show that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies.<n>We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning.
  arXiv  Detail & Related papers  (2025-01-20T08:40:15Z)
• Chain of Logic: Rule-Based Reasoning with Large Language Models [10.017812995997753]
  Rule-based reasoning enables us to draw conclusions by accurately applying a rule to a set of facts. We introduce a new prompting method, Chain of Logic, which elicits rule-based reasoning through decomposition and recomposition. We evaluate chain of logic across eight rule-based reasoning tasks involving three distinct compositional rules from the LegalBench benchmark.
  arXiv  Detail & Related papers  (2024-02-16T01:54:43Z)
• An Encoding of Abstract Dialectical Frameworks into Higher-Order Logic [57.24311218570012]
  This approach allows for the computer-assisted analysis of abstract dialectical frameworks. Exemplary applications include the formal analysis and verification of meta-theoretical properties.
  arXiv  Detail & Related papers  (2023-12-08T09:32:26Z)
• A Unifying Framework for Learning Argumentation Semantics [47.84663434179473]
  We present a novel framework, which uses an Inductive Logic Programming approach to learn the acceptability semantics for several abstract and structured argumentation frameworks in an interpretable way.<n>Our framework outperforms existing argumentation solvers, thus opening up new future research directions in the area of formal argumentation and human-machine dialogues.
  arXiv  Detail & Related papers  (2023-10-18T20:18:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.