# Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification

arXiv: https://arxiv.org/abs/2303.08006 · HTML: https://mlsanity.com/paper/2303.08006/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 24 of 24)

- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Embodied Question Answering](https://mlsanity.com/paper/1711.11543/) (2017)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning](https://mlsanity.com/paper/1909.05477/) (2019)
- [Formal Specifications from Natural Language](https://mlsanity.com/paper/2206.01962/) (2022)
- [AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data](https://mlsanity.com/paper/2010.04806/) (2020)
- [Learning a natural-language to LTL executable semantic parser for grounded robotics](https://mlsanity.com/paper/2008.03277/) (2020)
- [Semantic Parsing with Syntax- and Table-Aware SQL Generation](https://mlsanity.com/paper/1804.08338/) (2018)
- [Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations](https://mlsanity.com/paper/2006.02411/) (2020)
- [On The Ingredients of an Effective Zero-shot Semantic Parser](https://mlsanity.com/paper/2110.08381/) (2021)
- [Learning Constraints from Locally-Optimal Demonstrations under Cost Function Uncertainty](https://mlsanity.com/paper/2001.09336/) (2020)
- [Generalizing to New Domains by Mapping Natural Language to Lifted LTL](https://mlsanity.com/paper/2110.05603/) (2021)
- [Uncertainty-Aware Constraint Learning for Adaptive Safe Motion Planning from Demonstrations](https://mlsanity.com/paper/2011.04141/) (2020)
- [Learning Constraints from Demonstrations](https://mlsanity.com/paper/1812.07084/) (2018)
- [Interactive Robot Training for Non-Markov Tasks](https://mlsanity.com/paper/2003.02232/) (2020)
- [Planning with State Abstractions for Non-Markovian Task Specifications](https://mlsanity.com/paper/1905.12096/) (2019)
- [Gaussian Process Constraint Learning for Scalable Chance-Constrained Motion Planning from Demonstrations](https://mlsanity.com/paper/2112.04612/) (2021)
- [Training Naturalized Semantic Parsers with Very Little Data](https://mlsanity.com/paper/2204.14243/) (2022)

## Built on by (most cited first, 30 of 38)

- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [PlanGenLLMs: A Modern Survey of LLM Planning Capabilities](https://mlsanity.com/paper/2502.11221/) (2025)
- [Formal Mathematical Reasoning: A New Frontier in AI](https://mlsanity.com/paper/2412.16075/) (2024)
- [GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration](https://mlsanity.com/paper/2311.12015/) (2023)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [Autoformalizing Euclidean Geometry](https://mlsanity.com/paper/2405.17216/) (2024)
- [A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings](https://mlsanity.com/paper/2405.13245/) (2024)
- [PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs](https://mlsanity.com/paper/2502.00963/) (2025)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL](https://mlsanity.com/paper/2410.04631/) (2024)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Verifiably Following Complex Robot Instructions with Foundation Models](https://mlsanity.com/paper/2402.11498/) (2024)
- [ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees](https://mlsanity.com/paper/2504.21022/) (2025)
- [TR2MTL: LLM based framework for Metric Temporal Logic Formalization of Traffic Rules](https://mlsanity.com/paper/2406.05709/) (2024)
- [Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verification](https://mlsanity.com/paper/2411.16718/) (2024)
- [Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs](https://mlsanity.com/paper/2512.16814/) (2025)
- [Towards a Common Framework for Autoformalization](https://mlsanity.com/paper/2509.09810/) (2025)
- [Verifiable Natural Language to Linear Temporal Logic Translation: A Benchmark Dataset and Evaluation Suite](https://mlsanity.com/paper/2507.00877/) (2025)
- [Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism](https://mlsanity.com/paper/2510.13170/) (2025)
- [Learning Formal Specifications from Membership and Preference Queries](https://mlsanity.com/paper/2307.10434/) (2023)
- [CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning](https://mlsanity.com/paper/2410.16207/) (2024)
- [Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation](https://mlsanity.com/paper/2602.19304/) (2026)
- [Inductive Learning of Robot Task Knowledge from Raw Data and Online Expert Feedback](https://mlsanity.com/paper/2501.07507/) (2025)
- [SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems](https://mlsanity.com/paper/2602.24235/) (2026)
- [Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning](https://mlsanity.com/paper/2404.14547/) (2024)
- [Can Large Language Models Autoformalize Kinematics?](https://mlsanity.com/paper/2509.21840/) (2025)
- [Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis](https://mlsanity.com/paper/2601.08196/) (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)

## Abstract (arXiv)

To make robots accessible to a broad audience, it is critical to endow them with the ability to take universal modes of communication, like commands given in natural language, and extract a concrete desired task specification, defined using a formal language like linear temporal logic (LTL). In this paper, we present a learning-based approach for translating from natural language commands to LTL specifications with very limited human-labeled training data. This is in stark contrast to existing natural-language to LTL translators, which require large human-labeled datasets, often in the form of labeled pairs of LTL formulas and natural language commands, to train the translator. To reduce reliance on human data, our approach generates a large synthetic training dataset through algorithmic generation of LTL formulas, conversion to structured English, and then exploiting the paraphrasing capabilities of modern large language models (LLMs) to synthesize a diverse corpus of natural language commands corresponding to the LTL formulas. We use this generated data to finetune an LLM and apply a constrained decoding procedure at inference time to ensure the returned LTL formula is syntactically correct. We evaluate our approach on three existing LTL/natural language datasets and show that we can translate natural language commands at 75% accuracy with far less human data (≤12 annotations). Moreover, when training on large human-annotated datasets, our method achieves higher test accuracy (95% on average) than prior work. Finally, we show the translated formulas can be used to plan long-horizon, multi-stage tasks on a 12D quadrotor.