Pre-LLM NLP predicts which psychedelic drug a trip report describes, far above chance
Josikinz · x · 2026-10-03
Researchers show that old-school pre-LLM NLP can identify the substance behind de-identified psychedelic trip reports an order of magnitude better than chance. Mispredictions are non-random too: subjectively similar drugs like MDA get mistaken for MDMA. After validating discrimination via report embeddings, they built a PLSR-based mapping of covariance between biochemistry and subjective experience, comparing drugs' positions in a multidimensional effect space.
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