Failure-Driven Reminding for Incremental Learning

By C. Riesbeck. 1981

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

1. Niket Tandon
2. Aman Madaan
3. Yiming Yang
4. Peter Clark
5. David B. Leake

Citations in the corpus

• Memory-assisted prompt editing to improve GPT-3 after deployment (2022, background): “The idea of failure-driven reminding and dynamic memory date back several decades, e.g., (Schank, 1983; Riesbeck, 1981).”
• Goal-Based Explanation Evaluation (1991, background): “They are beyond the scope of this paper; for a discussion of some of those issues, see (Kedar-Cabelli, 1987), which examines how the purpose of finding objects to use in plans guides selection of concepts to explain, or (Schank, 1982; Riesbeck, 1981; Hammond, 1989; Leake, 1991), which address how th”
• Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedback (2021, unknown): “This can be viewed as a modern approach to failuredriven reminding, an essential theme in earlier AI and Cognitive Science research (Riesbeck, 1981; Schank and Leake, 1989; Ross, 1984).”