@inproceedings{scheinberg-etal-2025-explain,
title = "Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments",
author = "Scheinberg, Russell and
Agrawal, Ameeta and
Shore, Amber and
Lee, So Young",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1015/",
doi = "10.18653/v1/2025.findings-acl.1015",
pages = "19778--19795",
ISBN = "979-8-89176-256-5",
abstract = "Large language models (LLMs) can explain grammatical rules, yet they often fail to apply those rules when judging sentence acceptability. We present \textit{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 \textit{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 \textit{knowing} a rule and \textit{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 $\to$ 5.8 pp), all at negligible cost. The lightweight, language-agnostic cue lets low-cost SLMs approach frontier-LLM performance in multilingual settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scheinberg-etal-2025-explain">
<titleInfo>
<title>Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Russell</namePart>
<namePart type="family">Scheinberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ameeta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amber</namePart>
<namePart type="family">Shore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">scheinberg-etal-2025-explain</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1015</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1015/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>19778</start>
<end>19795</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments
%A Scheinberg, Russell
%A Agrawal, Ameeta
%A Shore, Amber
%A Lee, So Young
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F scheinberg-etal-2025-explain
%X 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.
%R 10.18653/v1/2025.findings-acl.1015
%U https://aclanthology.org/2025.findings-acl.1015/
%U https://doi.org/10.18653/v1/2025.findings-acl.1015
%P 19778-19795
Markdown (Informal)
[Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgments](https://aclanthology.org/2025.findings-acl.1015/) (Scheinberg et al., Findings 2025)
ACL