@inproceedings{henot-mortier-2023-language,
title = "Do Language Models discriminate between relatives and pseudorelatives?",
author = "Henot-Mortier, Adele",
editor = "Breitholtz, Ellen and
Lappin, Shalom and
Loaiciga, Sharid and
Ilinykh, Nikolai and
Dobnik, Simon",
booktitle = "Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)",
month = sep,
year = "2023",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clasp-1.6",
pages = "55--61",
abstract = "Large Language Models (LLMs) are often evaluated against massive benchmarks based on general-purpose tasks, which, despite being useful for concrete applications, tell us very little about the capacity of LLMs to learn specific and challenging aspects of the grammar. Here, we evaluate whether LLMs learn to identify a particular structure attested in Romance (and French in particular), called the pseudorelative. This structure, which is often surface-similar to a relative clause, is linked to robust syntactic and semantic restrictions. We present a series of experiments to test if LLMs pretrained on massive yet general corpora, manage to learn those various restrictions. Our results suggest that LLMs learn some but not all of these properties, but crucially fail at recognizing the most specific of them: cliticization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="henot-mortier-2023-language">
<titleInfo>
<title>Do Language Models discriminate between relatives and pseudorelatives?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adele</namePart>
<namePart type="family">Henot-Mortier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shalom</namePart>
<namePart type="family">Lappin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loaiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) are often evaluated against massive benchmarks based on general-purpose tasks, which, despite being useful for concrete applications, tell us very little about the capacity of LLMs to learn specific and challenging aspects of the grammar. Here, we evaluate whether LLMs learn to identify a particular structure attested in Romance (and French in particular), called the pseudorelative. This structure, which is often surface-similar to a relative clause, is linked to robust syntactic and semantic restrictions. We present a series of experiments to test if LLMs pretrained on massive yet general corpora, manage to learn those various restrictions. Our results suggest that LLMs learn some but not all of these properties, but crucially fail at recognizing the most specific of them: cliticization.</abstract>
<identifier type="citekey">henot-mortier-2023-language</identifier>
<location>
<url>https://aclanthology.org/2023.clasp-1.6</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>55</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Language Models discriminate between relatives and pseudorelatives?
%A Henot-Mortier, Adele
%Y Breitholtz, Ellen
%Y Lappin, Shalom
%Y Loaiciga, Sharid
%Y Ilinykh, Nikolai
%Y Dobnik, Simon
%S Proceedings of the 2023 CLASP Conference on Learning with Small Data (LSD)
%D 2023
%8 September
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F henot-mortier-2023-language
%X Large Language Models (LLMs) are often evaluated against massive benchmarks based on general-purpose tasks, which, despite being useful for concrete applications, tell us very little about the capacity of LLMs to learn specific and challenging aspects of the grammar. Here, we evaluate whether LLMs learn to identify a particular structure attested in Romance (and French in particular), called the pseudorelative. This structure, which is often surface-similar to a relative clause, is linked to robust syntactic and semantic restrictions. We present a series of experiments to test if LLMs pretrained on massive yet general corpora, manage to learn those various restrictions. Our results suggest that LLMs learn some but not all of these properties, but crucially fail at recognizing the most specific of them: cliticization.
%U https://aclanthology.org/2023.clasp-1.6
%P 55-61
Markdown (Informal)
[Do Language Models discriminate between relatives and pseudorelatives?](https://aclanthology.org/2023.clasp-1.6) (Henot-Mortier, CLASP 2023)
ACL