Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles

• URL: http://arxiv.org/abs/2604.28087v1
• Date: Thu, 30 Apr 2026 16:34:02 GMT
• Title: Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
• Abstract summary: Rule-based systems struggle with scalability, brittleness, and goal misspecification.<n>This paper introduces a meta-level layer designed to mitigate goal misspecification and support scalable rule maintenance.<n>We evaluate our approach with a proof-of-concept implementation in two autonomous driving scenarios.
• Score: 0.28582274879786684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend to optimize for narrow objectives. In previous research, we developed a neuro-symbolic causal framework that integrates first-order logic abduction trees, structural causal models, and deep reinforcement learning within a MAPE-K loop to provide explainable adaptations under distribution shifts. In this paper, we extend that framework by introducing a meta-level layer designed to mitigate goal misspecification and support scalable rule maintenance. This layer consists of a Goal/Rule Synthesizer and a Rule Verification Engine, which iteratively refine a formal rule theory from high-level natural-language goals and principles provided by human experts. The synthesis pipeline employs large language models (LLMs) to: (1) decompose goals into candidate causes, (2) consolidate semantics to remove redundancies, (3) translate them into candidate first-order rules, and (4) compose necessary and sufficient causal sets. The verification pipeline then performs (1) syntax and schema validation, (2) logical consistency analysis, and (3) safety and invariant checks before integrating verified rules into the knowledge base. We evaluated our approach with a proof-of-concept implementation in two autonomous driving scenarios. Results indicate that, given human-specified goals and principles, the pipeline can successfully derive minimal necessary and sufficient rule sets and formalize them as logical constraints. These findings suggest that the pipeline supports incremental, modular, and traceable rule synthesis grounded in established legal and safety principles.

Related papers

• ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models [73.59878306788815]
  ReasoningLens is an open-source framework designed for the hierarchical visualization and diagnostic auditing of complex reasoning chains.<n> ReasoningLens addresses information necropsy by: (1) structuring traces into interactive hierarchies that separate high-level strategy from low-level execution; and (2) leveraging an agentic auditor for automated error detection and tool-augmented verification.
  arXiv  Detail & Related papers  (2026-06-22T14:28:35Z)
• Exploring and Complementing End Users' Requirements in IoT enabled System [41.6356008435714]
  End users create IoT automation rules via trigger action programming, but their expressions are often fragmented.<n>This gap leads to missing conditions, logical conflicts, and overlooked safety constraints.<n>We propose an intent driven requirements completion approach that reframes rule completion as a dual process.
  arXiv  Detail & Related papers  (2026-06-09T09:01:41Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• HIPO: Instruction Hierarchy via Constrained Reinforcement Learning [57.40686733111483]
  textscHIPO is a novel alignment framework that formulates HIF as a Constrained Markov Decision Process.<n>textscHIPO elevates system prompts from mere input context to strict algorithmic boundaries.
  arXiv  Detail & Related papers  (2026-03-17T06:12:41Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive [0.0]
  AI systems are increasingly deployed in high-stakes contexts under the assumption they can be governed by norms.<n>This paper demonstrates that the assumption is formally invalid for optimization-based systems.
  arXiv  Detail & Related papers  (2026-02-26T17:16:17Z)
• The Convergence of Schema-Guided Dialogue Systems and the Model Context Protocol [0.0]
  This paper establishes a fundamental convergence: compatibility-Guided Dialogue (SGD) and the Model Context Protocol (MCP)<n>SGD and MCP represent two manifestations of a unified paradigm for deterministic, auditable LLM-agent interaction.
  arXiv  Detail & Related papers  (2026-02-21T09:02:35Z)
• Structured Decomposition for LLM Reasoning: Cross-Domain Validation and Semantic Web Integration [0.0]
  Rule-based reasoning arises in domains where decisions must be auditable and justifiable.<n>Applying rules to such inputs demands both interpretive flexibility and formal guarantees.<n>This paper presents an integration pattern that combines these strengths.
  arXiv  Detail & Related papers  (2026-01-04T17:19:20Z)
• Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis [0.0]
  The design of safety-critical agents based on large language models (LLMs) requires more than simple prompt engineering.<n>This paper presents a comprehensive information-theoretic analysis of how rule encodings in system prompts influence attention mechanisms and compliance behaviour.
  arXiv  Detail & Related papers  (2025-09-23T14:42:32Z)
• 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)
• DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
  Constrained decoding approaches aim to control the meaning or style of text generated by pre-trained large language (Ms also PLMs) for various tasks at inference time.<n>These methods often guide plausible continuations by greedily and explicitly selecting targets.<n>Inspired by cognitive dual-process theory, we propose a novel decoding framework DECIDER.
  arXiv  Detail & Related papers  (2024-03-04T11:49:08Z)
• Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs [87.34281749422756]
  Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. We propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic.
  arXiv  Detail & Related papers  (2024-02-18T03:38:51Z)

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.