Search Results for author:
Found 2 papers, 1 papers with code
Instruction-tuning Aligns LLMs to the Human Brain
To identify the factors underlying LLM-brain alignment, we compute correlations between the brain alignment of LLMs and various model properties, such as model size, various problem-solving abilities, and performance on tasks requiring world knowledge spanning various domains.
Training language models to summarize narratives improves brain alignment
We show that training language models for deeper narrative understanding results in richer representations that have improved alignment to human brain activity.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
