# Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs

arXiv: https://arxiv.org/abs/2512.16814 · HTML: https://mlsanity.com/paper/2512.16814/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models](https://mlsanity.com/paper/2303.04864/) (2023)
- [Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments](https://mlsanity.com/paper/2302.11649/) (2023)
- [Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification](https://mlsanity.com/paper/2303.08006/) (2023)
- [Learning a natural-language to LTL executable semantic parser for grounded robotics](https://mlsanity.com/paper/2008.03277/) (2020)
- [Generalizing to New Domains by Mapping Natural Language to Lifted LTL](https://mlsanity.com/paper/2110.05603/) (2021)
- [Metrics for Signal Temporal Logic Formulae](https://mlsanity.com/paper/1808.03315/) (2018)

## Built on by (most cited first, 8 of 8)

- [ClarifySTL: An Interactive LLM Agent Framework for STL Transformation through Requirements Clarification](https://mlsanity.com/paper/2605.01209/) (2026)
- [Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment](https://mlsanity.com/paper/2602.14844/) (2026)
- [Towards General Language-Conditioned Latent Safety Filters](https://mlsanity.com/paper/2608.00315/) (2026)
- [SCP-NL2TL: Selective Conformal Prediction with Semantic Verification for Natural Language to Temporal Logic Specifications](https://mlsanity.com/paper/2608.05439/) (2026)
- [Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models](https://mlsanity.com/paper/2605.15131/) (2026)
- [Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG](https://mlsanity.com/paper/2609.20334/) (2026)
- [Constraint-Aware Training](https://mlsanity.com/paper/2610.02909/) (2026)
- [Structural Automata for Neural Semantic Parsing](https://mlsanity.com/paper/2610.13896/) (2026)

## Abstract (arXiv)

Translating natural language (NL) into a formal language such as temporal logic (TL) is integral for human communication with robots and autonomous systems. State-of-the-art approaches decompose the task into a lifting of atomic propositions (APs) phase and a translation phase. However, existing methods struggle with accurate lifting, the existence of co-references, and learning from limited data. In this paper, we propose a framework for NL to TL translation called Grammar Forced Translation (GraFT). The framework is based on the observation that previous work solves both the lifting and translation steps by letting a language model iteratively predict tokens from its full vocabulary. In contrast, GraFT reduces the complexity of both tasks by restricting the set of valid output tokens from the full vocabulary to only a handful in each step. The solution space reduction is obtained by exploiting the unique properties of each problem. We also provide a theoretical justification for why the solution space reduction leads to more efficient learning. We evaluate the effectiveness of GraFT using the CW, GLTL, and Navi benchmarks. Compared with state-of-the-art translation approaches, it can be observed that GraFT the end-to-end translation accuracy by 5.49% and out-of-domain translation accuracy by 14.06% on average.