# Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments

arXiv: https://arxiv.org/abs/2506.02302 · HTML: https://mlsanity.com/paper/2506.02302/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [The Learnability of In-Context Learning](https://mlsanity.com/paper/2303.07895/) (2023)
- [A Benchmark for Learning to Translate a New Language from One Grammar Book](https://mlsanity.com/paper/2309.16575/) (2023)
- [RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs](https://mlsanity.com/paper/2406.19232/) (2024)
- [Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?](https://mlsanity.com/paper/2409.19151/) (2024)
- [SLING: Sino Linguistic Evaluation of Large Language Models](https://mlsanity.com/paper/2210.11689/) (2022)
- [Grammaticality Representation in ChatGPT as Compared to Linguists and Laypeople](https://mlsanity.com/paper/2406.11116/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang](https://mlsanity.com/paper/2509.00425/) (2025)
- [UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu](https://mlsanity.com/paper/2508.01006/) (2025)

## Abstract (arXiv)

Large language models (LLMs) can explain grammatical rules, yet they often fail to apply those rules when judging sentence acceptability. We present "grammar prompting", an explain-then-process paradigm: a large LLM first produces a concise explanation of the relevant syntactic phenomenon, then that explanation is fed back as additional context to the target model -- either an LLM or a smaller language model (SLM) -- before deciding which sentence of a minimal pair is grammatical. On the English BLiMP, Chinese SLING, and Russian RuBLiMP benchmarks, this simple prompt design yields substantial improvements over strong baselines across many syntactic phenomena. Feeding an LLM's metalinguistic explanation back to the target model bridges the gap between knowing a rule and using it. On SLMs, grammar prompting alone trims the average LLM-SLM accuracy gap by about 20%, and when paired with chain-of-thought, by 56% (13.0 pp -> 5.8 pp), all at negligible cost. The lightweight, language-agnostic cue lets low-cost SLMs approach frontier-LLM performance in multilingual settings.