LLMs factor in unrelated information when recommending medical treatments
June 23, 2025
June 23, 2025
CAMBRIDGE, Massachusetts, June 23 -- The Massachusetts Institute of Technology issued the following news:
* * *
LLMs factor in unrelated information when recommending medical treatments
*
A large language model (LLM) deployed to make treatment recommendations can be tripped up by nonclinical information in patient messages, like typos, extra white space, missing gender markers, or the use of uncertain, dramatic, and informal language, according . . .
* * *
LLMs factor in unrelated information when recommending medical treatments
*
A large language model (LLM) deployed to make treatment recommendations can be tripped up by nonclinical information in patient messages, like typos, extra white space, missing gender markers, or the use of uncertain, dramatic, and informal language, according . . .