Researchers use an LLM to label drug experience heatmaps, benchmarked against blinded human expert
Josikinz · x · 2026-10-03
A drug study mapped relationships between receptor affinities and subjective experiences, using an LLM to synthesize grab-bags of experience themes for labeling PLSR components, with a blinded human expert performing the same task in parallel. The authors shared a heatmap overview of observed covariances, a notable example of LLM-assisted scientific annotation validated against human blind review.
Related event: NLP and LLMs Map Psychedelic Subjective Experiences(4 posts)→
More from Research
- Math PhD Trains AI to Crack Open Research Problems, Reports Progress in Arithmetic Physics — shuchaobi · 2026-10-03
- childes-db 2026.1 Released: Child Language Database Grows to 24.2M Utterances with New Annotations — najoungkim · 2026-10-03
- SETA Terminal Agent Training Suite Accepted at NeurIPS, Open-Sources 4,500+ Verifiable RL Environments — Thom_Wolf · 2026-10-03
- MedARC journal club: pretraining foundation models for intracranial EEG — iScienceLuvr · 2026-10-03
- Mosaic: exact constrained decoding for diffusion LLMs via finite automata, NeurIPS paper — StefanoErmon · 2026-10-03
- NYU Researchers Challenge Anthropic's Claim That LLMs Can Introspect — tallinzen · 2026-10-03