Marzyeh Ghassemi
Artificial Intelligence
A greater method for identifying overconfident large language models
Large language models (LLMs) can generate credible but inaccurate responses, so researchers...
Artificial Intelligence
Why it’s critical to maneuver beyond overly aggregated machine-learning metrics
MIT researchers have identified significant examples of machine-learning model failure when those...
Artificial Intelligence
MIT scientists investigate memorization risk within the age of clinical AI
What's patient privacy for? The Hippocratic Oath, considered one in all the...
Artificial Intelligence
Researchers discover a shortcoming that makes LLMs less reliable
Large language models (LLMs) sometimes learn the flawed lessons, in accordance with...
Artificial Intelligence
Charting the long run of AI, from safer answers to faster considering
Adoption of recent tools and technologies occurs when users largely perceive them...
Artificial Intelligence
LLMs consider unrelated information when recommending medical treatments
A big language model (LLM) deployed to make treatment recommendations might be...
Artificial Intelligence
Study shows vision-language models can’t handle queries with negation words
Imagine a radiologist examining a chest X-ray from a brand new patient....
Artificial Intelligence
Study reveals AI chatbots can detect race, but racial bias reduces response empathy
With the quilt of anonymity and the corporate of strangers, the appeal...
Recent posts
