Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
This addresses the problem of enabling users to interactively correct and improve AI systems, particularly for question-answering tasks, though it is incremental as it builds on existing memory-based and continuous learning approaches.
The paper tackles the problem of creating teachable reasoning systems for question-answering by augmenting a QA model with a dynamic memory of user feedback, which allows the system to improve over time without retraining. The results show that with simulated feedback on only 25% of training examples, the system reaches within 1% of an upper-bound performance, and real-user experiments demonstrate over 15% improvement on a hidden test set.
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 of memory-based continuous learning. With simulated feedback, we find that our system (called TeachMe) continually improves with time, and without model retraining, requiring feedback on only 25% of training examples to reach within 1% of the upper-bound (feedback on all examples). Similarly, in experiments with real users, we observe a similar trend, with performance improving by over 15% on a hidden test set after teaching. This suggests new opportunities for using frozen language models in an interactive setting where users can inspect, debug, and correct the model's beliefs, leading to improved system's performance over time.