# Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge

arXiv: https://arxiv.org/abs/2505.20658 · HTML: https://mlsanity.com/paper/2505.20658/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [LongForm: Effective Instruction Tuning with Reverse Instructions](https://mlsanity.com/paper/2304.08460/) (2023)
- [DeepSTL -- From English Requirements to Signal Temporal Logic](https://mlsanity.com/paper/2109.10294/) (2021)
- [Metrics for Signal Temporal Logic Formulae](https://mlsanity.com/paper/1808.03315/) (2018)

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

- [ClarifySTL: An Interactive LLM Agent Framework for STL Transformation through Requirements Clarification](https://mlsanity.com/paper/2605.01209/) (2026)
- [STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Models](https://mlsanity.com/paper/2607.18580/) (2026)
- [Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement](https://mlsanity.com/paper/2608.14590/) (2026)
- [Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logic](https://mlsanity.com/paper/2603.28426/) (2026)
- [ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learning](https://mlsanity.com/paper/2605.06483/) (2026)
- [SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications](https://mlsanity.com/paper/2608.05439/) (2026)
- [Ask, Reason, Assist: Robot Collaboration via Natural Language and Temporal Logic](https://mlsanity.com/paper/2509.23506/) (2025)
- [Agentic MPC for Semantic Control System Resynthesis](https://mlsanity.com/paper/2606.12774/) (2026)
- [Feedback Makes Perfect: A Closed-Loop Framework for NL-to-STL Translation](https://mlsanity.com/paper/2609.33287/) (2026)

## Abstract (arXiv)

Temporal Logic (TL), especially Signal Temporal Logic (STL), enables precise formal specification, making it widely used in cyber-physical systems such as autonomous driving and robotics. Automatically transforming NL into STL is an attractive approach to overcome the limitations of manual transformation, which is time-consuming and error-prone. However, due to the lack of datasets, automatic transformation currently faces significant challenges and has not been fully explored. In this paper, we propose an NL-STL dataset named STL-Diversity-Enhanced (STL-DivEn), which comprises 16,000 samples enriched with diverse patterns. To develop the dataset, we first manually create a small-scale seed set of NL-STL pairs. Next, representative examples are identified through clustering and used to guide large language models (LLMs) in generating additional NL-STL pairs. Finally, diversity and accuracy are ensured through rigorous rule-based filters and human validation. Furthermore, we introduce the Knowledge-Guided STL Transformation (KGST) framework, a novel approach for transforming natural language into STL, involving a generate-then-refine process based on external knowledge. Statistical analysis shows that the STL-DivEn dataset exhibits more diversity than the existing NL-STL dataset. Moreover, both metric-based and human evaluations indicate that our KGST approach outperforms baseline models in transformation accuracy on STL-DivEn and DeepSTL datasets.