aceEvaluating Harm Reduction Advice From Large Language Models
Introduction: Large language models (LLM) and generative Artificial Intelligence are increasingly providing health information. We have applied a novel method to evaluate the harm reduction information generated by popular LLMs. We focused on the filtration of oral medications for injection and the availability of local harm reduction services. Methods: We designed a scoring rubric to evaluate the accuracy of the information provided by each LLM and applied it to four unique, commonly used LLMs. Results: Gemini…
Gemini 2.5 Flash and ChatGPT-4o gave comprehensive, accurate micron filter instructions and correct local harm reduction service information, in a non-judgmental manner.
DeepSeek R1 Distill and Llama 4 gave little or no filter instructions, some models generated misinformation, and some refused questions because of built-in safety parameters.
The study tested only four LLMs on a limited set of harm reduction topics, and the models also produced misinformation, so the findings do not show that any model is a safe replacement for specialist advice.
Evidence
- Peer-reviewedDrug and Alcohol Review2026-11-01
How should this claim be treated?
Truvace Impact Record TRV-2026-1608, v1: “Evaluating Harm Reduction Advice From Large Language Models.” Truvace, 2026-10-16. /record/TRV-2026-1608 (accessed at citation time). sha256 a8ac93a5f3866b31…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1608 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.