arXiv cs.CL
·
18 hours ago
Researchers benchmarked Llama 3.2 and other language models for decoding continuous language from fMRI brain signals and improving neural language decoding pipelines. An improved ridge regression encoding pipeline achieved 0.149 METEOR and 0.200 BLEU-1 scores, representing an 11% relative improvement over baseline, while a Llama-3.2-based approach achieved 42.86% top-1 accuracy but showed no improvement when fMRI inputs were zeroed. The work demonstrates that large language models alone do not improve fMRI decoding performance without neural data, indicating that blind-control evaluation is essential for validating brain-computer interface approaches.
arXiv cs.CL
·
18 hours ago
Researchers developed a multi-feature fusion framework for reconstructing semantic information from non-invasive brain recordings by combining static word embeddings (W2V) with dynamic contextual representations (GPT). The framework evaluated two integration approaches (linear concatenation and non-linear cross-attention), with cross-attention fusion achieving state-of-the-art performance in semantic reconstruction and text generation tasks. The approach addresses the representational mismatch between neural signals and semantic features by simulating how the brain simultaneously integrates word attributes and context during language comprehension.
arXiv cs.AI
·
18 hours ago
Researchers found that as large language models improve during training, their internal representations increasingly predict brain activity in the left hemisphere more than the right, and this asymmetry emerges specifically alongside the model's acquisition of formal linguistic abilities. The correlation between model predictions and fMRI brain activity shows measurable improvement in predicting left-hemisphere activity as the OLMo-2 7B model progresses through training checkpoints, while arithmetic and world knowledge tasks do not produce this asymmetry. This left-right asymmetry pattern held across two LLM families (OLMo-2 and Pythia) and three languages (English, French, and Chinese), suggesting that brain-like linguistic lateralization in neural activity emerges when models develop formal grammar competence.
