Language models align with brain regions that represent concepts across modalities

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ryskina, Maria, Tuckute, Greta, Fung, Alexander, Malkin, Ashley, Fedorenko, Evelina
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915447667949568
author Ryskina, Maria
Tuckute, Greta
Fung, Alexander
Malkin, Ashley
Fedorenko, Evelina
author_facet Ryskina, Maria
Tuckute, Greta
Fung, Alexander
Malkin, Ashley
Fedorenko, Evelina
contents Cognitive science and neuroscience have long faced the challenge of disentangling representations of language from representations of conceptual meaning. As the same problem arises in today's language models (LMs), we investigate the relationship between LM--brain alignment and two neural metrics: (1) the level of brain activation during processing of sentences, targeting linguistic processing, and (2) a novel measure of meaning consistency across input modalities, which quantifies how consistently a brain region responds to the same concept across paradigms (sentence, word cloud, image) using an fMRI dataset (Pereira et al., 2018). Our experiments show that both language-only and language-vision models predict the signal better in more meaning-consistent areas of the brain, even when these areas are not strongly sensitive to language processing, suggesting that LMs might internally represent cross-modal conceptual meaning.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11536
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Language models align with brain regions that represent concepts across modalities
Ryskina, Maria
Tuckute, Greta
Fung, Alexander
Malkin, Ashley
Fedorenko, Evelina
Computation and Language
Cognitive science and neuroscience have long faced the challenge of disentangling representations of language from representations of conceptual meaning. As the same problem arises in today's language models (LMs), we investigate the relationship between LM--brain alignment and two neural metrics: (1) the level of brain activation during processing of sentences, targeting linguistic processing, and (2) a novel measure of meaning consistency across input modalities, which quantifies how consistently a brain region responds to the same concept across paradigms (sentence, word cloud, image) using an fMRI dataset (Pereira et al., 2018). Our experiments show that both language-only and language-vision models predict the signal better in more meaning-consistent areas of the brain, even when these areas are not strongly sensitive to language processing, suggesting that LMs might internally represent cross-modal conceptual meaning.
title Language models align with brain regions that represent concepts across modalities
topic Computation and Language
url https://arxiv.org/abs/2508.11536