Research
Human brains track who did what to whom in ways AI language models don’t, fMRI study suggests
PsyPost · By Eric W. Dolan ·
The Brief
- A neuroimaging study published in eLife examined how the brain processes sentence meaning.
- The study reports that human brains track who did what to whom in ways AI language models do not.
- The findings were covered by PsyPost on 2026-11-09.
Why it matters
The result bears on whether current AI language models process sentence meaning the way human brains do, which matters for researchers using language models as models of cognition.
Who’s affected
- cognitive neuroscientists
- researchers using AI language models as models of human language processing
- #fmri
- #language processing
- #neuroscience
- #ai language models
- #sentence meaning
Modern artificial intelligence chatbots can write essays and hold conversations that closely mimic human communication, raising the question of whether they process language like the human brain. A new neuroimaging study published in eLife suggests that when sentence meaning…
Timeline
PsyPost reports on the eLife fMRI study
PsyPost – Psychology News
Human brains track who did what to whom in ways AI language models don’t, fMRI study suggests