安全制約付き計画のための言語モデルの検証と改良の統合手法
Joint Verification and Refinement of Language Models for Safety-Constrained Planning
言語モデルが生成するロボットプログラムをオートマトン表現に変換して安全仕様を検証し、その結果を活用した微調整で安全なプログラム生成を効率化する手法を提案。
著者: Yunhao Yang, Neel P. Bhatt, William Ward, Zichao Hu, Joydeep Biswas, Ufuk Topcu
分類: cs.AI, cs.FL, cs.RO
原文アブストラクト
Large language models possess impressive capabilities in generating programs (e.g., Python) from natural language descriptions to execute robotic tasks. However, these generated programs often contain errors that violate externally given task specifications. Without an effective method to verify their correctness, the reliable deployment of language models in real-world systems is practically infeasible. We develop a method that converts generated robot programs into an automaton-based representation and verifies them against task-relevant safety specifications. We establish a theorem that any arbitrary combination of the verified programs will also satisfy the safety specifications. Hence, the method eliminates the need to verify complex programs composed of multiple simpler ones, reducing computation complexity. We then introduce an automated fine-tuning procedure that leverages verification outcomes for supervision. By applying the theorem, this procedure only requires training the model to generate safe sub-components, thereby improving training efficiency. Empirical results on robot applications show a 30 percent increase in the probability of generating specification-compliant programs, with training time reduced by half compared to fine-tuning on generating full programs.
