@inproceedings{bollepally-etal-2026-representational,
title = "Representational Similarity Alignment of Figurative Language in Humans and Large Language Models",
author = "Bollepally, Samhita and
Sloman-Moll, Aurora and
Yamauchi, Takashi and
Motamedrasa, Neeka",
editor = "Sousa-Silva, Rui and
Lopes Cardoso, Henrique and
Koponen, Maarit and
Pareja-Lora, Antonio",
booktitle = "Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era ({LUHME} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.luhme-1.5/",
pages = "70--88",
ISBN = "979-8-89176-471-2",
abstract = "Large language models (LLMs) often produce judgments similar to those of humans, but their interpretation of figurative language remains unclear. We compared human participants and four instruction-tuned LLMs (GPT-4, Gemma-2-9B, Llama-3.2, and Mistral-7B) on their ratings of 240 dialogue-based sentences spanning six linguistic traits: conventionality, sarcasm, funny, emotion, idiomacy, and Gen Z slang. While humans and LLMs aligned strongly at the surface level, differences emerged in representational similarity patterns, particularly for idiomacy and Gen Z slang. GPT-4 showed the closest alignment to humans, though all models differed at the representational level, suggesting that similar outputs may arise from different underlying language representations. We also examined the relationship between model scale and representational similarity using the Gemma model series (Gemma-2-9B-IT, Gemma-3-27B-IT, and Gemma-4-31B-IT), and found that representational similarity patterns were largely unaffected by model size."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bollepally-etal-2026-representational">
<titleInfo>
<title>Representational Similarity Alignment of Figurative Language in Humans and Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samhita</namePart>
<namePart type="family">Bollepally</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurora</namePart>
<namePart type="family">Sloman-Moll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Yamauchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neeka</namePart>
<namePart type="family">Motamedrasa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Sousa-Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henrique</namePart>
<namePart type="family">Lopes Cardoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Pareja-Lora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-471-2</identifier>
</relatedItem>
<abstract>Large language models (LLMs) often produce judgments similar to those of humans, but their interpretation of figurative language remains unclear. We compared human participants and four instruction-tuned LLMs (GPT-4, Gemma-2-9B, Llama-3.2, and Mistral-7B) on their ratings of 240 dialogue-based sentences spanning six linguistic traits: conventionality, sarcasm, funny, emotion, idiomacy, and Gen Z slang. While humans and LLMs aligned strongly at the surface level, differences emerged in representational similarity patterns, particularly for idiomacy and Gen Z slang. GPT-4 showed the closest alignment to humans, though all models differed at the representational level, suggesting that similar outputs may arise from different underlying language representations. We also examined the relationship between model scale and representational similarity using the Gemma model series (Gemma-2-9B-IT, Gemma-3-27B-IT, and Gemma-4-31B-IT), and found that representational similarity patterns were largely unaffected by model size.</abstract>
<identifier type="citekey">bollepally-etal-2026-representational</identifier>
<location>
<url>https://aclanthology.org/2026.luhme-1.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>70</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Representational Similarity Alignment of Figurative Language in Humans and Large Language Models
%A Bollepally, Samhita
%A Sloman-Moll, Aurora
%A Yamauchi, Takashi
%A Motamedrasa, Neeka
%Y Sousa-Silva, Rui
%Y Lopes Cardoso, Henrique
%Y Koponen, Maarit
%Y Pareja-Lora, Antonio
%S Proceedings of the 3rd Workshop on Language Understanding in the Human-Machine Era (LUHME 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-471-2
%F bollepally-etal-2026-representational
%X Large language models (LLMs) often produce judgments similar to those of humans, but their interpretation of figurative language remains unclear. We compared human participants and four instruction-tuned LLMs (GPT-4, Gemma-2-9B, Llama-3.2, and Mistral-7B) on their ratings of 240 dialogue-based sentences spanning six linguistic traits: conventionality, sarcasm, funny, emotion, idiomacy, and Gen Z slang. While humans and LLMs aligned strongly at the surface level, differences emerged in representational similarity patterns, particularly for idiomacy and Gen Z slang. GPT-4 showed the closest alignment to humans, though all models differed at the representational level, suggesting that similar outputs may arise from different underlying language representations. We also examined the relationship between model scale and representational similarity using the Gemma model series (Gemma-2-9B-IT, Gemma-3-27B-IT, and Gemma-4-31B-IT), and found that representational similarity patterns were largely unaffected by model size.
%U https://aclanthology.org/2026.luhme-1.5/
%P 70-88
Markdown (Informal)
[Representational Similarity Alignment of Figurative Language in Humans and Large Language Models](https://aclanthology.org/2026.luhme-1.5/) (Bollepally et al., LUHME 2026)
ACL