mlsanityData to 14 Oct 2026

NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models

arXiv 2305.07766 ↗First posted 12 May 2023cs.CLcited by 59

Not on the map. Why?

Abstract (arXiv)

Temporal Logic (TL) can be used to rigorously specify complex high-level specification for systems in many engineering applications. The translation between natural language (NL) and TL has been under-explored due to the lack of dataset and generalizable model across different application domains. In this paper, we propose an accurate and generalizable transformation framework of English instructions from NL to TL, exploring the use of Large Language Models (LLMs) at multiple stages. Our contributions are twofold. First, we develop a framework to create a dataset of NL-TL pairs combining LLMs and human annotation. We publish a dataset with 28K NL-TL pairs. Then, we finetune T5 models on the lifted versions (i.e., the specific Atomic Propositions (AP) are hidden) of the NL and TL. The enhanced generalizability originates from two aspects: 1) Usage of lifted NL-TL characterizes common logical structures, without constraints of specific domains. 2) Application of LLMs in dataset creation largely enhances corpus richness. We test the generalization of trained models on five varied domains. To achieve full NL-TL transformation, we either combine the lifted model with AP recognition task or do the further finetuning on each specific domain. During the further finetuning, our model achieves higher accuracy (>95%) using only <10% training data, compared with the baseline sequence to sequence (Seq2Seq) model.

Key facts. Cited by 59 papers in the map (data through 14 Oct 2026). Builds on 11 of its 37 references that are in the map. First posted on arXiv 12 May 2023.

Builds on

11 of 37 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 334
  8. 2021Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarizationcited by 76
  9. 2020Learning a natural-language to LTL executable semantic parser for grounded roboticscited by 22
  10. 2021DeepSTL -- From English Requirements to Signal Temporal Logiccited by 22
  11. 2021Generalizing to New Domains by Mapping Natural Language to Lifted LTLcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 14; 2025: 19; 2026: 19.

59 papers.

Sort:

By area:

  1. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 427
  2. 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 113
  3. 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
  4. 2025Safety Guardrails for LLM-Enabled Robotscited by 35
  5. 2024A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddingscited by 24
  6. 2023Conformal Temporal Logic Planning using Large Language Modelscited by 21
  7. 2024SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Modelscited by 21
  8. 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 18
  9. 2025A Survey on Large Language Models for Automated Planningcited by 17
  10. 2024Verifiably Following Complex Robot Instructions with Foundation Modelscited by 16
  11. 2025ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guaranteescited by 11
  12. 2025Air-Ground Collaboration for Language-Specified Missions in Unknown Environmentscited by 11
38 more
  1. 2025We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedbackcited by 10
  2. 2025Distilling On-device Language Models for Robot Planning with Minimal Human Interventioncited by 10
  3. 2024Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verificationcited by 9
  4. 2023Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specificationscited by 7
  5. 2024Jailbreaking LLM-Controlled Robotscited by 6
  6. 2025HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinementcited by 6
  7. 2024Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agentscited by 5
  8. 2024Generative Agents for Multi-Agent Autoformalization of Interaction Scenarioscited by 5
  9. 2025KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulationcited by 5
  10. 2025LogicGuard: Improving Embodied LLM agents through Temporal Logic based Criticscited by 5
  11. 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Datacited by 5
  12. 2024Logically Constrained Robotics Transformers for Enhanced Perception-Action Planningcited by 4
  13. 2025Verifiable Natural Language to Linear Temporal Logic Translation: A Benchmark Dataset and Evaluation Suitecited by 4
  14. 2026Contextual Safety Reasoning and Grounding for Open-World Robotscited by 4
  15. 2024Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systemscited by 3
  16. 2026Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperationcited by 3
  17. 2026Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systemscited by 3
  18. 2024Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Modelscited by 2
  19. 2026Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Inductioncited by 2
  20. 2023On Generating Explanations for Reinforcement Learning Policies: An Empirical Studycited by 1
  21. 2024Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planningcited by 1
  22. 2025Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systemscited by 1
  23. 2025Can Large Language Models Autoformalize Kinematics?cited by 1
  24. 2025From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrailscited by 1
  25. 2026Structural-Ambiguity-Aware Translation from Natural Language to Signal Temporal Logiccited by 1
  26. 2026Spatiotemporal Robustness of Temporal Logic Tasks using Multi-Objective Reasoningcited by 1
  27. 2026ReasonSTL: Bridging Natural Language and Signal Temporal Logic via Tool-Augmented Process-Rewarded Learningcited by 1
  28. 2026Semantic Constraint Synthesis for Adaptive Trajectory Optimization via Large Language Modelscited by 1
  29. 2026SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specificationscited by 1
  30. 2023Physics-Enhanced Multi-fidelity Learning for Optical Surface Imprintcited by 0
  31. 2024Nl2Hltl2Plan: Scaling Up Natural Language Understanding for Multi-Robots Through Hierarchical Temporal Logic Task Representationcited by 0
  32. 2024Foundation Models for Rapid Autonomy Validationcited by 0
  33. 2025INPROVF: Leveraging Large Language Models to Repair High-level Robot Controllers from Assumption Violationscited by 0
  34. 2025Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledgecited by 0
  35. 2025Ask, Reason, Assist: Robot Collaboration via Natural Language and Temporal Logiccited by 0
  36. 2025RLAF: Reinforcement Learning from Automaton Feedbackcited by 0
  37. 2025GinSign: Grounding Natural Language Into System Signatures for Temporal Logic Translationcited by 0
  38. 2026Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Modelscited by 0

50 most cited of 59 All 59 (JSON)