@inproceedings{bonial-etal-2025-form,
title = "From Form to Function: A Constructional {NLI} Benchmark",
author = "Bonial, Claire and
Pellegrin, Taylor and
Torgbi, Melissa and
Tayyar Madabushi, Harish",
editor = "Bonial, Claire and
Torgbi, Melissa and
Weissweiler, Leonie and
Blodgett, Austin and
Beuls, Katrien and
Van Eecke, Paul and
Tayyar Madabushi, Harish",
booktitle = "Proceedings of the Second International Workshop on Construction Grammars and NLP",
month = sep,
year = "2025",
address = {D{\"u}sseldorf, Germany},
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.cxgsnlp-1.18/",
pages = "172--179",
ISBN = "979-8-89176-318-0",
abstract = "We present CoGS-NLI, a Natural Language Inference (NLI) evaluation benchmark testing understanding of English phrasal constructions drawn from the Construction Grammar Schematicity (CoGS) corpus. This dataset of 1,500 NLI triples facilitates assessment of constructional understanding in a downstream inference task. We present an evaluation benchmark based on the performance of two language models, where we vary the number and kinds of examples given in the prompt, with and without chain-of-thought prompting. The best-performing model and prompt combination achieves a strong overall accuracy of .94 when provided in-context learning examples with the target phrasal constructions, whereas providing additional general NLI examples hurts performance. This evidences the value of resources explicitly capturing the semantics of phrasal constructions, while our qualitative analysis suggests caveats in assuming this performance indicates a deep understanding of constructional semantics."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bonial-etal-2025-form">
<titleInfo>
<title>From Form to Function: A Constructional NLI Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taylor</namePart>
<namePart type="family">Pellegrin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Torgbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second International Workshop on Construction Grammars and NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Torgbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonie</namePart>
<namePart type="family">Weissweiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Austin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrien</namePart>
<namePart type="family">Beuls</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Van Eecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Düsseldorf, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-318-0</identifier>
</relatedItem>
<abstract>We present CoGS-NLI, a Natural Language Inference (NLI) evaluation benchmark testing understanding of English phrasal constructions drawn from the Construction Grammar Schematicity (CoGS) corpus. This dataset of 1,500 NLI triples facilitates assessment of constructional understanding in a downstream inference task. We present an evaluation benchmark based on the performance of two language models, where we vary the number and kinds of examples given in the prompt, with and without chain-of-thought prompting. The best-performing model and prompt combination achieves a strong overall accuracy of .94 when provided in-context learning examples with the target phrasal constructions, whereas providing additional general NLI examples hurts performance. This evidences the value of resources explicitly capturing the semantics of phrasal constructions, while our qualitative analysis suggests caveats in assuming this performance indicates a deep understanding of constructional semantics.</abstract>
<identifier type="citekey">bonial-etal-2025-form</identifier>
<location>
<url>https://aclanthology.org/2025.cxgsnlp-1.18/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>172</start>
<end>179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Form to Function: A Constructional NLI Benchmark
%A Bonial, Claire
%A Pellegrin, Taylor
%A Torgbi, Melissa
%A Tayyar Madabushi, Harish
%Y Bonial, Claire
%Y Torgbi, Melissa
%Y Weissweiler, Leonie
%Y Blodgett, Austin
%Y Beuls, Katrien
%Y Van Eecke, Paul
%Y Tayyar Madabushi, Harish
%S Proceedings of the Second International Workshop on Construction Grammars and NLP
%D 2025
%8 September
%I Association for Computational Linguistics
%C Düsseldorf, Germany
%@ 979-8-89176-318-0
%F bonial-etal-2025-form
%X We present CoGS-NLI, a Natural Language Inference (NLI) evaluation benchmark testing understanding of English phrasal constructions drawn from the Construction Grammar Schematicity (CoGS) corpus. This dataset of 1,500 NLI triples facilitates assessment of constructional understanding in a downstream inference task. We present an evaluation benchmark based on the performance of two language models, where we vary the number and kinds of examples given in the prompt, with and without chain-of-thought prompting. The best-performing model and prompt combination achieves a strong overall accuracy of .94 when provided in-context learning examples with the target phrasal constructions, whereas providing additional general NLI examples hurts performance. This evidences the value of resources explicitly capturing the semantics of phrasal constructions, while our qualitative analysis suggests caveats in assuming this performance indicates a deep understanding of constructional semantics.
%U https://aclanthology.org/2025.cxgsnlp-1.18/
%P 172-179
Markdown (Informal)
[From Form to Function: A Constructional NLI Benchmark](https://aclanthology.org/2025.cxgsnlp-1.18/) (Bonial et al., CxGsNLP 2025)
ACL
- Claire Bonial, Taylor Pellegrin, Melissa Torgbi, and Harish Tayyar Madabushi. 2025. From Form to Function: A Constructional NLI Benchmark. In Proceedings of the Second International Workshop on Construction Grammars and NLP, pages 172–179, Düsseldorf, Germany. Association for Computational Linguistics.