MemPrompt: Memory-assisted Prompt Editing with User Feedback. (arXiv:2201.06009v6 [cs.CL] UPDATED)

Large LMs such as GPT-3 are powerful, but can commit mistakes that are
obvious to humans. For example, GPT-3 would mistakenly interpret "What word is
similar to good?" to mean a homophone, while the user intended a synonym. Our
goal is to effectively correct such errors via user interactions with the
system but without retraining, which will be prohibitively costly. We pair
GPT-3 with a growing memory of recorded cases where the model misunderstood the
user's intents, along with user …

arxiv feedback memory user feedback