Article

Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models

2025-07-10

Abstract excerpt

Recent studies have demonstrated that fine-tuning language models with brain data can improve their semantic understanding, although these findings have so far been limited to English. Interestingly, similar to the shared multilingual embedding space of pretrained multilingual language models, human studies provide strong evidence for a shared semantic system in bilingual individuals. Here, we investigate whether...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: efe95fdf-d707-5572-ab0c-7c3352aa91ee
DOI: 10.1101/2025.07.07.662360

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language ModelsDOI 10.1101/2025.07.07.662360Read

Shared functional specialization in transformer-based language models and the human brainSemantic proximity Read

Language processing in brains and deep neural networks: computational convergence and its limitsSemantic proximity Read

Driving and suppressing the human language network using large language modelsSemantic proximity Read

A Comparative Survey of Large Language Models: Foundation, Instruction-Tuned, and Multimodal VariantsSemantic proximity Read

Efficient neural encoding as revealed by bilingualismSemantic proximity Read

The neural architecture of language: Integrative modeling converges on predictive processingSemantic proximity Read

Hierarchical Semantic Encoding for Contextual Understanding in Large Language ModelsSemantic proximity Read

Dynamic Contextual Interpolation for More Efficient Model Generalization in Large Language ModelsSemantic proximity Read

Semantic Contextual Embedding for Domain-Specific Task Transfer in Large Language ModelsSemantic proximity Read

Engineering A Large Language Model From ScratchSemantic proximity Read

Unified Efficient Fine-Tuning Techniques for Open-Source Large Language ModelsSemantic proximity Read

Semantic Calibration of Contextual Embedding in Large Language Model Generative Pathways Using Contextual-Distillation MechanismsSemantic proximity Read