Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement. (arXiv:2204.13074v2 [cs.CL] UPDATED)

Our goal is a teachable reasoning system for question-answering (QA), where a
user can interact with faithful answer explanations, and correct its errors so
that the system improves over time. Our approach is to augment a QA model with
a dynamic memory of user feedback, containing user-supplied corrections to
erroneous model beliefs that users identify during interaction. Retrievals from
memory are used as additional context for QA, to help avoid previous mistakes
in similar new situations - a novel application …

arxiv continual feedback improvement memory reasoning systems user feedback