Research map / Large language models / Language, safety and interpretability
Joint processing of linguistic properties in brains and language 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 |
|---|---|---|---|
| Remove Sentence Length information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Remove TreeDepth information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Remove TopConstituents information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Remove Tense information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Remove Subject Number information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Remove Object Number information from BERT representations (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | Hurt |
| Use TopConstituents instead of the other tested linguistic properties to explain layerwise brain-alignment changes (ablation) | BERT · 21st year, whole brain | across-layer correlation: 0.451 | Helped |
| Use TreeDepth instead of the other tested linguistic properties to explain layerwise brain-alignment changes (ablation) | BERT · 21st year, whole brain | across-layer correlation: 0.443 | Helped |
| Remove a randomly generated property vector rather than a linguistic property (ablation) | BERT · 21st year fMRI story | brain alignment (Pearson correlation) | No clear effect |
Closest papers by meaning
- fMRI predictors based on language models of increasing complexity recover brain left lateralization (NeurIPS 2024 · similarity 0.91)
- Improving Semantic Understanding in Speech Language Models via Brain-tuning (ICLR 2025 · similarity 0.90)
- Divergences between Language Models and Human Brains (NeurIPS 2024 · similarity 0.89)
- Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain (NeurIPS 2025 · similarity 0.89)
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models (NeurIPS 2025 · similarity 0.88)
- TopoLM: brain-like spatio-functional organization in a topographic language model (ICLR 2025 · similarity 0.88)
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.