analiza aiqbench
The paper uses an ensemble of open-source LLMs to produce interpretable, word-level semantic features that account for context, and reports that these features predict language-region brain activity better than non-contextual baselines. For AI readers, the main takeaway is a methodological one: LLM-derived representations are being evaluated as models of human neural processing, with variance partitioning used to separate their contribution from syntactic features. The evidence is behavioral and neural-encoding based, so the claims about "meaning" in the brain should be read as predictive correlations rather than mechanistic explanations.
SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics
arXiv:2610.21518v1 Announce Type: new Abstract: Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varies in natural settings. To enable the study of real-world linguistic meaning in the brain, we introduce SCRIBE, a framework grounded in a neuroscience-informed semantic space that leverages an ensemble of open-source large language models to generate interpretable, word-level semantic representations of arbitrary text. In a behavioral study with 921 participants, we show that human semantic feature judgments vary systematically with context, and that SCRIBE captures these shifts, reaching 75-81% of the estimated human noise ceiling. Using brain activity recorded while participants listen to naturalistic stories, we further demonstrate that SCRIBE predicts neural responses in language-selective brain regions, significantly outperforming non-contextual semantic representations. Variance partitioning reveals that SCRIBE explains unique brain-predictive information beyond syntactic features, suggesting that its representations capture aspects of linguistic meaning not accounted for by the measured syntactic features. Together, these findings establish SCRIBE as a scalable and interpretable foundation for studying natural language semantics in the brain.
Abstract:Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varies in natural settings. To enable the study of real-world linguistic meaning in the brain, we introduce SCRIBE, a framework grounded in a neuroscience-informed semantic space that leverages an ensemble of open-source large language models to generate interpretable, word-level semantic representations of arbitrary text. In a behavioral study with 921 participants, we show that human semantic feature judgments vary systematically with context, and that SCRIBE captures these shifts, reaching 75-81% of the estimated human noise ceiling. Using brain activity recorded while participants listen to naturalistic stories, we further demonstrate that SCRIBE predicts neural responses in language-selective brain regions, significantly outperforming non-contextual semantic representations. Variance partitioning reveals that SCRIBE explains unique brain-predictive information beyond syntactic features, suggesting that its representations capture aspects of linguistic meaning not accounted for by the measured syntactic features. Together, these findings establish SCRIBE as a scalable and interpretable foundation for studying natural language semantics in the brain.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2610.21518 [cs.AI]
(or arXiv:2610.21518v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.21518 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 269 cuvinte
Subiecte conexe
Decomposing Brain-LLM Alignment with Interpretable Semantic Representations
arXiv · 17 oct. 2026
AI-powered metadata correction and harmonization
AWS · 24 aug. 2026
IdiomX A Multilingual Benchmark for Idiom Understanding, Retrieval, and Interpretation
arXiv · 3 iun. 2026
Modernizing and scaling support operations with generative AI on AWS
AWS · 2 sept. 2026