@inproceedings{wang-etal-2024-large-language-models,
title = "How can large language models become more human?",
author = "Wang, Daphne and
Sadrzadeh, Mehrnoosh and
Stanojevi{\'c}, Milo{\v{s}} and
Chow, Wing-Yee and
Breheny, Richard",
editor = "Kuribayashi, Tatsuki and
Rambelli, Giulia and
Takmaz, Ece and
Wicke, Philipp and
Oseki, Yohei",
booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.cmcl-1.14",
pages = "166--176",
abstract = "Psycholinguistic experiments reveal that efficiency of human language use is founded on predictions at both syntactic and lexical levels. Previous models of human prediction exploiting LLMs have used an information theoretic measure called \textit{surprisal}, with success on naturalistic text in a wide variety of languages, but under-performance on challenging text such as garden path sentences. This paper introduces a novel framework that combines the lexical predictions of an LLM with the syntactic structures provided by a dependency parser. The framework gives rise to an \textit{Incompatibility Fraction}. When tested on two garden path datasets, it correlated well with human reading times, distinguished between easy and hard garden path, and outperformed surprisal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-large-language-models">
<titleInfo>
<title>How can large language models become more human?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daphne</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehrnoosh</namePart>
<namePart type="family">Sadrzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miloš</namePart>
<namePart type="family">Stanojević</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wing-Yee</namePart>
<namePart type="family">Chow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Breheny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuki</namePart>
<namePart type="family">Kuribayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Rambelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Wicke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Oseki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Psycholinguistic experiments reveal that efficiency of human language use is founded on predictions at both syntactic and lexical levels. Previous models of human prediction exploiting LLMs have used an information theoretic measure called surprisal, with success on naturalistic text in a wide variety of languages, but under-performance on challenging text such as garden path sentences. This paper introduces a novel framework that combines the lexical predictions of an LLM with the syntactic structures provided by a dependency parser. The framework gives rise to an Incompatibility Fraction. When tested on two garden path datasets, it correlated well with human reading times, distinguished between easy and hard garden path, and outperformed surprisal.</abstract>
<identifier type="citekey">wang-etal-2024-large-language-models</identifier>
<location>
<url>https://aclanthology.org/2024.cmcl-1.14</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>166</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How can large language models become more human?
%A Wang, Daphne
%A Sadrzadeh, Mehrnoosh
%A Stanojević, Miloš
%A Chow, Wing-Yee
%A Breheny, Richard
%Y Kuribayashi, Tatsuki
%Y Rambelli, Giulia
%Y Takmaz, Ece
%Y Wicke, Philipp
%Y Oseki, Yohei
%S Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-large-language-models
%X Psycholinguistic experiments reveal that efficiency of human language use is founded on predictions at both syntactic and lexical levels. Previous models of human prediction exploiting LLMs have used an information theoretic measure called surprisal, with success on naturalistic text in a wide variety of languages, but under-performance on challenging text such as garden path sentences. This paper introduces a novel framework that combines the lexical predictions of an LLM with the syntactic structures provided by a dependency parser. The framework gives rise to an Incompatibility Fraction. When tested on two garden path datasets, it correlated well with human reading times, distinguished between easy and hard garden path, and outperformed surprisal.
%U https://aclanthology.org/2024.cmcl-1.14
%P 166-176
Markdown (Informal)
[How can large language models become more human?](https://aclanthology.org/2024.cmcl-1.14) (Wang et al., CMCL-WS 2024)
ACL
- Daphne Wang, Mehrnoosh Sadrzadeh, Miloš Stanojević, Wing-Yee Chow, and Richard Breheny. 2024. How can large language models become more human?. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 166–176, Bangkok, Thailand. Association for Computational Linguistics.