You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
GPT-3.5 and GPT-4 are the two most widely used large language model (LLM)services. However, when and how these models are updated over time is opaque.Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 onfour diverse tasks: 1) solving math problems, 2) answering sensitive/dangerousquestions, 3) generating code and 4) visual reasoning. We find that theperformance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time.For example, GPT-4 (March 2023) was very good at identifying prime numbers(accuracy 97.6%) but GPT-4 (June 2023) was very poor on these same questions(accuracy 2.4%). Interestingly GPT-3.5 (June 2023) was much better than GPT-3.5(March 2023) in this task. GPT-4 was less willing to answer sensitive questionsin June than in March, and both GPT-4 and GPT-3.5 had more formatting mistakesin code generation in June than in March. Overall, our findings shows that thebehavior of the same LLM service can change substantially in a relatively shortamount of time, highlighting the need for continuous monitoring of LLM quality.
URL
Affiliations
Abstract
Translation (by gpt-3.5-turbo)
Summary (by gpt-3.5-turbo)
The text was updated successfully, but these errors were encountered: