A retrieval method that uses semantically similar wrong answers as anchors to find corrective correct demonstrations improves few-shot in-context learning accuracy on seven reasoning datasets.
Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Failures Are the Stepping Stones to Success: Enhancing Few-Shot In-Context Learning by Leveraging Negative Samples
A retrieval method that uses semantically similar wrong answers as anchors to find corrective correct demonstrations improves few-shot in-context learning accuracy on seven reasoning datasets.