Research map / Large language models / Language, safety and interpretability
Inducing brain-relevant bias in natural language processing models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Fine-tune pretrained BERT end-to-end to predict a participant's fMRI activity instead of fitting only a linear readout | BERT · fMRI 20 vs. 20 classification | accuracy | Helped |
| Fine-tune BERT on one participant, then fit a linear readout for another participant with the tuned parameters frozen | BERT participant-transfer model · fMRI 20 vs. 20 classification on other participants | accuracy | Helped |
| Pretrain the brain-relevant representation by jointly fine-tuning on MEG participants before fine-tuning on fMRI | BERT MEG-transfer model · fMRI 20 vs. 20 classification | accuracy | Mixed |
| Jointly fine-tune one model on multiple MEG and fMRI participants | BERT fully joint model · fMRI 20 vs. 20 classification | accuracy | Helped |
| Fine-tune on brain recordings using the MEG-transfer model | BERT MEG-transfer model · GLUE dev tasks | task metrics | Mixed |
| Fine-tune on brain recordings using the fully joint model | BERT fully joint model · GLUE dev tasks | task metrics | Mixed |
Closest papers by meaning
- Improving Semantic Understanding in Speech Language Models via Brain-tuning (ICLR 2025 · similarity 0.92)
- fMRI predictors based on language models of increasing complexity recover brain left lateralization (NeurIPS 2024 · similarity 0.90)
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models (NeurIPS 2025 · similarity 0.89)
- Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement (NeurIPS 2025 · similarity 0.89)
- Divergences between Language Models and Human Brains (NeurIPS 2024 · similarity 0.88)
- RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.