Large Language Models as Falsifiers for Cyber-Physical Systems
LLM-Falsifier uses large language models with semantic prompting to minimize STL robustness and find counterexamples in cyber-physical systems more efficiently.
The paper formulates falsification of Signal Temporal Logic specifications as robustness minimization and leverages iteratively prompted LLMs as optimizers. It exposes the LLM to semantic information absent from numerical optimizers, including natural-language signal names, output trajectories, and critical-time witnesses for the minimum robustness value. On ARCH-COMP falsification benchmarks, LLM-Falsifier required fewer simulations than surrogate-based, Bayesian, and search-based tools on 14 of 21 specifications.
- Frames STL falsification as robustness optimization via LLM prompting
- Exposes semantic context: signal names, trajectories, critical-time witnesses
- Wins on 14 of 21 ARCH-COMP specifications by simulation efficiency
- Outperforms surrogate, Bayesian, and search-based falsifiers
- Products
- LLM-FalsifierARCH-COMP
From the original article
1 min read at arxiv.orgFalsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search algorithms.
By Ali ArjomandBigdeli · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.