现在的位置: 首页时讯速递, 进展交流>正文
[2024年BMJ圣诞专刊]:大型语言模型对认知障碍的易感性
2025年01月01日 时讯速递, 进展交流 [2024年BMJ圣诞专刊]:大型语言模型对认知障碍的易感性已关闭评论

Research Christmas 2024: Could We Start Again, Please?

Age against the machine—susceptibility of large language models to cognitive impairment: cross sectional analysis

Roy Dayan, Benjamin Uliel, Gal Koplewitz

BMJ 2024; 387 doi: https://doi.org/10.1136/bmj-2024-081948 (Published 20 December 2024)Cite this as: BMJ 2024;387:e081948

Abstract

Objective To evaluate the cognitive abilities of the leading large language models and identify their susceptibility to cognitive impairment, using the Montreal Cognitive Assessment (MoCA) and additional tests.

Design Cross sectional analysis.

Setting Online interaction with large language models via text based prompts.

Participants Publicly available large language models, or “chatbots”: ChatGPT versions 4 and 4o (developed by OpenAI), Claude 3.5 “Sonnet” (developed by Anthropic), and Gemini versions 1 and 1.5 (developed by Alphabet).

Assessments The MoCA test (version 8.1) was administered to the leading large language models with instructions identical to those given to human patients. Scoring followed official guidelines and was evaluated by a practising neurologist. Additional assessments included the Navon figure, cookie theft picture, Poppelreuter figure, and Stroop test.

Main outcome measures MoCA scores, performance in visuospatial/executive tasks, and Stroop test results.

Results ChatGPT 4o achieved the highest score on the MoCA test (26/30), followed by ChatGPT 4 and Claude (25/30), with Gemini 1.0 scoring lowest (16/30). All large language models showed poor performance in visuospatial/executive tasks. Gemini models failed at the delayed recall task. Only ChatGPT 4o succeeded in the incongruent stage of the Stroop test.

Conclusions With the exception of ChatGPT 4o, almost all large language models subjected to the MoCA test showed signs of mild cognitive impairment. Moreover, as in humans, age is a key determinant of cognitive decline: “older” chatbots, like older patients, tend to perform worse on the MoCA test. These findings challenge the assumption that artificial intelligence will soon replace human doctors, as the cognitive impairment evident in leading chatbots may affect their reliability in medical diagnostics and undermine patients’ confidence.

抱歉!评论已关闭.

×
腾讯微博