@inproceedings{amouyal-etal-2025-lm,
title = "When the {LM} misunderstood the human chuckled: Analyzing garden path effects in humans and language models",
author = "Amouyal, Samuel Joseph and
Meltzer-Asscher, Aya and
Berant, Jonathan",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.403/",
doi = "10.18653/v1/2025.acl-long.403",
pages = "8235--8253",
ISBN = "979-8-89176-251-0",
abstract = "Modern Large Language Models (LLMs) have shown human-like abilities in many language tasks, sparking interest in comparing LLMs' and humans' language processing. In this paper, we try to answer two questions: 1. What makes garden-path sentences hard to understand for humans? 2. Do the same reasons make garden-path sentences hard for LLMs as well? Based on psycholinguistic research, we formulate hypotheses on why garden-path sentences are hard, and test these hypotheses on human participants and a large suite of LLMs using comprehension questions. Our findings reveal that both LLMs and humans struggle with specific syntactic complexities, with some models showing high correlation with human comprehension. To complement our findings, we test LLM comprehension of garden-path constructions with paraphrasing and text-to-image generation tasks, and find that the results mirror the sentence comprehension question results, further validating our findings on LLM understanding of these constructions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amouyal-etal-2025-lm">
<titleInfo>
<title>When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="given">Joseph</namePart>
<namePart type="family">Amouyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aya</namePart>
<namePart type="family">Meltzer-Asscher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Modern Large Language Models (LLMs) have shown human-like abilities in many language tasks, sparking interest in comparing LLMs’ and humans’ language processing. In this paper, we try to answer two questions: 1. What makes garden-path sentences hard to understand for humans? 2. Do the same reasons make garden-path sentences hard for LLMs as well? Based on psycholinguistic research, we formulate hypotheses on why garden-path sentences are hard, and test these hypotheses on human participants and a large suite of LLMs using comprehension questions. Our findings reveal that both LLMs and humans struggle with specific syntactic complexities, with some models showing high correlation with human comprehension. To complement our findings, we test LLM comprehension of garden-path constructions with paraphrasing and text-to-image generation tasks, and find that the results mirror the sentence comprehension question results, further validating our findings on LLM understanding of these constructions.</abstract>
<identifier type="citekey">amouyal-etal-2025-lm</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.403</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.403/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>8235</start>
<end>8253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models
%A Amouyal, Samuel Joseph
%A Meltzer-Asscher, Aya
%A Berant, Jonathan
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F amouyal-etal-2025-lm
%X Modern Large Language Models (LLMs) have shown human-like abilities in many language tasks, sparking interest in comparing LLMs’ and humans’ language processing. In this paper, we try to answer two questions: 1. What makes garden-path sentences hard to understand for humans? 2. Do the same reasons make garden-path sentences hard for LLMs as well? Based on psycholinguistic research, we formulate hypotheses on why garden-path sentences are hard, and test these hypotheses on human participants and a large suite of LLMs using comprehension questions. Our findings reveal that both LLMs and humans struggle with specific syntactic complexities, with some models showing high correlation with human comprehension. To complement our findings, we test LLM comprehension of garden-path constructions with paraphrasing and text-to-image generation tasks, and find that the results mirror the sentence comprehension question results, further validating our findings on LLM understanding of these constructions.
%R 10.18653/v1/2025.acl-long.403
%U https://aclanthology.org/2025.acl-long.403/
%U https://doi.org/10.18653/v1/2025.acl-long.403
%P 8235-8253
Markdown (Informal)
[When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models](https://aclanthology.org/2025.acl-long.403/) (Amouyal et al., ACL 2025)
ACL