# TR2MTL: LLM based framework for Metric Temporal Logic Formalization of Traffic Rules

arXiv: https://arxiv.org/abs/2406.05709 · HTML: https://mlsanity.com/paper/2406.05709/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 9 Jun 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Parallel Context Windows for Large Language Models](https://mlsanity.com/paper/2212.10947/) (2022)
- [Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification](https://mlsanity.com/paper/2303.08006/) (2023)
- [Formal Specifications from Natural Language](https://mlsanity.com/paper/2206.01962/) (2022)
- [DeepSTL -- From English Requirements to Signal Temporal Logic](https://mlsanity.com/paper/2109.10294/) (2021)
- [Planning with State Abstractions for Non-Markovian Task Specifications](https://mlsanity.com/paper/1905.12096/) (2019)
- [Road Traffic Law Adaptive Decision-making for Self-Driving Vehicles](https://mlsanity.com/paper/2204.11411/) (2022)
- [From Specifications to Behavior: Maneuver Verification in a Semantic State Space](https://mlsanity.com/paper/1905.00708/) (2019)

## Built on by (most cited first, 9 of 9)

- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review](https://mlsanity.com/paper/2506.06301/) (2025)
- [Faithful Autoformalization via Roundtrip Verification and Repair](https://mlsanity.com/paper/2604.25031/) (2026)
- [CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning](https://mlsanity.com/paper/2410.16207/) (2024)
- [Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification](https://mlsanity.com/paper/2504.13111/) (2025)
- [Knowledge Integration Strategies in Autonomous Vehicle Prediction and Planning: A Comprehensive Survey](https://mlsanity.com/paper/2502.10477/) (2025)
- [LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue](https://mlsanity.com/paper/2509.02292/) (2025)
- [Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methods](https://mlsanity.com/paper/2510.25386/) (2025)
- [Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG](https://mlsanity.com/paper/2609.20334/) (2026)

## Abstract (arXiv)

Traffic rules formalization is crucial for verifying the compliance and safety of autonomous vehicles (AVs). However, manual translation of natural language traffic rules as formal specification requires domain knowledge and logic expertise, which limits its adaptation. This paper introduces TR2MTL, a framework that employs large language models (LLMs) to automatically translate traffic rules (TR) into metric temporal logic (MTL). It is envisioned as a human-in-loop system for AV rule formalization. It utilizes a chain-of-thought in-context learning approach to guide the LLM in step-by-step translation and generating valid and grammatically correct MTL formulas. It can be extended to various forms of temporal logic and rules. We evaluated the framework on a challenging dataset of traffic rules we created from various sources and compared it against LLMs using different in-context learning methods. Results show that TR2MTL is domain-agnostic, achieving high accuracy and generalization capability even with a small dataset. Moreover, the method effectively predicts formulas with varying degrees of logical and semantic structure in unstructured traffic rules.