Large language models and the perils of their hallucinations

By Razvan Azamfirei, S. Kudchadkar, J. Fackler. Critical Care, 2023

310 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A study of generative large language model for medical research and healthcare (2023, unknown): “…facilitate documentation of patient reports (e.g., a progress report) 3,4 , improving diagnostic accuracy 5 , and assisting in various clinical care 6,7 , while at the same time concerning the hallucinations and fabrications 7,8 , bias and stereotype 9 , and risks of patient privacy and ethics 10 .”
Augmenting large language models with chemistry tools (2023, background): “The most notable of these, that have also been discussed in recent publications 105–108 regarding the applications of LLMs, are hallucination, difficulty of evaluating results, and reproducibility.”
Communicative Agents for Software Development (2023, methodology): “Similar to hallucinations encountered when using LLMs for natural language querying [2], directly generating entire software systems using LLMs can result in severe code hallucinations, such as incomplete implementation, missing dependencies, and undiscovered bugs.”