@inproceedings{zhifei-wang-steinert-threlkeld-2023-gqg,
title = "{GQG}: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models",
author = "Zhifei Wang, Leroy and
Steinert-Threlkeld, Shane",
editor = "Hupkes, Dieuwke and
Dankers, Verna and
Batsuren, Khuyagbaatar and
Sinha, Koustuv and
Kazemnejad, Amirhossein and
Christodoulopoulos, Christos and
Cotterell, Ryan and
Bruni, Elia",
booktitle = "Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.genbench-1.15",
doi = "10.18653/v1/2023.genbench-1.15",
pages = "185--192",
abstract = "We present a new dataset consisting of various quantifier expressions to evaluate the generalization abilities of language models. The dataset contains 18,360 prompts encompassing diverse quantifiers, forming the basis of a new framework for assessing semantic understanding in this domain. We test the effectiveness of our dataset using Pythia models, ranging from 410 million to 6.9 billion, showing that quantifier-based tasks can be challenging for current language models. We make our code and data publicly available, such that the dataset can be easily extended or updated based on different evaluation needs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhifei-wang-steinert-threlkeld-2023-gqg">
<titleInfo>
<title>GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leroy</namePart>
<namePart type="family">Zhifei Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shane</namePart>
<namePart type="family">Steinert-Threlkeld</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verna</namePart>
<namePart type="family">Dankers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khuyagbaatar</namePart>
<namePart type="family">Batsuren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustuv</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Kazemnejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new dataset consisting of various quantifier expressions to evaluate the generalization abilities of language models. The dataset contains 18,360 prompts encompassing diverse quantifiers, forming the basis of a new framework for assessing semantic understanding in this domain. We test the effectiveness of our dataset using Pythia models, ranging from 410 million to 6.9 billion, showing that quantifier-based tasks can be challenging for current language models. We make our code and data publicly available, such that the dataset can be easily extended or updated based on different evaluation needs.</abstract>
<identifier type="citekey">zhifei-wang-steinert-threlkeld-2023-gqg</identifier>
<identifier type="doi">10.18653/v1/2023.genbench-1.15</identifier>
<location>
<url>https://aclanthology.org/2023.genbench-1.15</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>185</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models
%A Zhifei Wang, Leroy
%A Steinert-Threlkeld, Shane
%Y Hupkes, Dieuwke
%Y Dankers, Verna
%Y Batsuren, Khuyagbaatar
%Y Sinha, Koustuv
%Y Kazemnejad, Amirhossein
%Y Christodoulopoulos, Christos
%Y Cotterell, Ryan
%Y Bruni, Elia
%S Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhifei-wang-steinert-threlkeld-2023-gqg
%X We present a new dataset consisting of various quantifier expressions to evaluate the generalization abilities of language models. The dataset contains 18,360 prompts encompassing diverse quantifiers, forming the basis of a new framework for assessing semantic understanding in this domain. We test the effectiveness of our dataset using Pythia models, ranging from 410 million to 6.9 billion, showing that quantifier-based tasks can be challenging for current language models. We make our code and data publicly available, such that the dataset can be easily extended or updated based on different evaluation needs.
%R 10.18653/v1/2023.genbench-1.15
%U https://aclanthology.org/2023.genbench-1.15
%U https://doi.org/10.18653/v1/2023.genbench-1.15
%P 185-192
Markdown (Informal)
[GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models](https://aclanthology.org/2023.genbench-1.15) (Zhifei Wang & Steinert-Threlkeld, GenBench-WS 2023)
ACL