用语法约束+反事实推理修正自动驾驶安全规则，避免错误修正
Grammar-Constrained Refinement of Safety Operational Rules Using Language in the Loop: What Could Go Wrong
- 结合反事实推理与语法约束循环修正规则
- 修复了传统方法生成的不一致安全规则
- 适合关注模型安全与规则可解释性的研究者
网络物理系统（CPS）中的安全规范描述了系统在预期环境中安全运行所需的条件。随着运行环境变化，操作规则需持续优化以保持与仿真验证中观测到的行为一致。然而，修正不一致规则极具挑战性，因修改必须符合领域特定语法。语言在环（Language-in-the-loop）修正进一步引发安全风险，可能产生语义不合理、过度拟合观测结果的修正。本文提出一种框架，融合反事实推理与语法约束的修正循环，使操作规则与观测行为对齐。应用于自动驾驶控制系统时，该方法成功修复了传统基线推导出的不一致规则，且保持语法合规。一项基于大语言模型的实证研究揭示了模型依赖的修正质量差异及安全教训，提示未来工作需强化语法约束、加强语义验证并开展更广泛评估。
原文摘要 · Abstract (English)
Safety specifications in cyber-physical systems (CPS) capture the operational conditions the system must satisfy to operate safely within its intended environment. As operating environments evolve, operational rules must be continuously refined to preserve consistency with observed system behavior during simulation-based verification and validation. Revising inconsistent rules is challenging because the changes must remain syntactically correct under a domain-specific grammar. Language-in-the-loop refinement further raises safety concerns beyond syntactic violations, as it can produce semantically unjustified refinements that overfit to the observed outcomes. We introduce a framework that combines counterfactual reasoning with a grammar-constrained refinement loop to refine operational rules, aligning them with the observed system behavior. Applied to an autonomous driving control system, our approach successfully resolved the inconsistencies in an operational rule inferred by a conventional baseline while remaining grammar compliant. An empirical large language model (LLM) study further revealed model-dependent refinement quality and safety lessons, which motivate rigorous grammar enforcement, stronger semantic validation, and broader evaluation in future work.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。