@inproceedings{bonial-tayyar-madabushi-2024-construction-grammar,
title = "A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models",
author = "Bonial, Claire and
Tayyar Madabushi, Harish",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.22",
pages = "243--255",
abstract = "Large Language Models (LLMs) have been developed without a theoretical framework, yet we posit that evaluating and improving LLMs will benefit from the development of theoretical frameworks that enable comparison of the structures of human language and the model of language built up by LLMs through the processing of text. In service of this goal, we develop the Construction Grammar Schematicity ({``}CoGS{''}) corpus of 10 distinct English constructions, where the constructions vary with respect to schematicity, or in other words the level to which constructional slots require specific, fixed lexical items, or can be filled with a variety of elements that fulfill a particular semantic role of the slot. Our corpus constructions are carefully curated to range from substantive, frozen constructions (e.g., Let-alone) to entirely schematic constructions (e.g., Resultative). The corpus was collected to allow us to probe LLMs for constructional information at varying levels of abstraction. We present our own probing experiments using this corpus, which clearly demonstrate that even the largest LLMs are limited to more substantive constructions and do not exhibit recognition of the similarity of purely schematic constructions. We publicly release our dataset, prompts, and associated model responses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bonial-tayyar-madabushi-2024-construction-grammar">
<titleInfo>
<title>A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models</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">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have been developed without a theoretical framework, yet we posit that evaluating and improving LLMs will benefit from the development of theoretical frameworks that enable comparison of the structures of human language and the model of language built up by LLMs through the processing of text. In service of this goal, we develop the Construction Grammar Schematicity (“CoGS”) corpus of 10 distinct English constructions, where the constructions vary with respect to schematicity, or in other words the level to which constructional slots require specific, fixed lexical items, or can be filled with a variety of elements that fulfill a particular semantic role of the slot. Our corpus constructions are carefully curated to range from substantive, frozen constructions (e.g., Let-alone) to entirely schematic constructions (e.g., Resultative). The corpus was collected to allow us to probe LLMs for constructional information at varying levels of abstraction. We present our own probing experiments using this corpus, which clearly demonstrate that even the largest LLMs are limited to more substantive constructions and do not exhibit recognition of the similarity of purely schematic constructions. We publicly release our dataset, prompts, and associated model responses.</abstract>
<identifier type="citekey">bonial-tayyar-madabushi-2024-construction-grammar</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.22</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>243</start>
<end>255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models
%A Bonial, Claire
%A Tayyar Madabushi, Harish
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F bonial-tayyar-madabushi-2024-construction-grammar
%X Large Language Models (LLMs) have been developed without a theoretical framework, yet we posit that evaluating and improving LLMs will benefit from the development of theoretical frameworks that enable comparison of the structures of human language and the model of language built up by LLMs through the processing of text. In service of this goal, we develop the Construction Grammar Schematicity (“CoGS”) corpus of 10 distinct English constructions, where the constructions vary with respect to schematicity, or in other words the level to which constructional slots require specific, fixed lexical items, or can be filled with a variety of elements that fulfill a particular semantic role of the slot. Our corpus constructions are carefully curated to range from substantive, frozen constructions (e.g., Let-alone) to entirely schematic constructions (e.g., Resultative). The corpus was collected to allow us to probe LLMs for constructional information at varying levels of abstraction. We present our own probing experiments using this corpus, which clearly demonstrate that even the largest LLMs are limited to more substantive constructions and do not exhibit recognition of the similarity of purely schematic constructions. We publicly release our dataset, prompts, and associated model responses.
%U https://aclanthology.org/2024.lrec-main.22
%P 243-255
Markdown (Informal)
[A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models](https://aclanthology.org/2024.lrec-main.22) (Bonial & Tayyar Madabushi, LREC-COLING 2024)
ACL