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

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 a wide range of 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 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. Understanding Special Question Patterns in English In English, there's a particular way of asking questions that might seem tricky at first. This pattern involves asking about a specific part of a sentence while keeping most of the original sentence structure intact. Key Rules: 1. ... [truncated for brevity] Grammatical Details: • ... [truncated for brevity] Tips for Correct Usage: • ... [truncated for brevity] To Spot Incorrect Usage: • ... [truncated for brevity] Remember, this question form is used in specific contexts, often to express surprise or seek confirmation. It's not the standard way to form all questions in English, but it's important to recognize and use correctly when appropriate.