Fine-grained Analysis of Brain-LLM Alignment through Input Attribution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915553769160704 |
|---|---|
| author | Proietti, Michela Capobianco, Roberto Toneva, Mariya |
| author_facet | Proietti, Michela Capobianco, Roberto Toneva, Mariya |
| contents | Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-grained input attribution method to identify the specific words most important for brain-LLM alignment, and leverage it to study a contentious research question about brain-LLM alignment: the relationship between brain alignment (BA) and next-word prediction (NWP). Our findings reveal that BA and NWP rely on largely distinct word subsets: NWP exhibits recency and primacy biases with a focus on syntax, while BA prioritizes semantic and discourse-level information with a more targeted recency effect. This work advances our understanding of how LLMs relate to human language processing and highlights differences in feature reliance between BA and NWP. Beyond this study, our attribution method can be broadly applied to explore the cognitive relevance of model predictions in diverse language processing tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12355 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-grained Analysis of Brain-LLM Alignment through Input Attribution Proietti, Michela Capobianco, Roberto Toneva, Mariya Computation and Language Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-grained input attribution method to identify the specific words most important for brain-LLM alignment, and leverage it to study a contentious research question about brain-LLM alignment: the relationship between brain alignment (BA) and next-word prediction (NWP). Our findings reveal that BA and NWP rely on largely distinct word subsets: NWP exhibits recency and primacy biases with a focus on syntax, while BA prioritizes semantic and discourse-level information with a more targeted recency effect. This work advances our understanding of how LLMs relate to human language processing and highlights differences in feature reliance between BA and NWP. Beyond this study, our attribution method can be broadly applied to explore the cognitive relevance of model predictions in diverse language processing tasks. |
| title | Fine-grained Analysis of Brain-LLM Alignment through Input Attribution |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.12355 |