Iterative refinement algorithms

We develop algorithms for iteratively refining outputs at inference time, allowing for efficient search that takes advantage of feedback. Examples include Self-Correction and Self-Refinement.

Related publications

2023

  1. Self-Refine: Iterative Refinement with Self-Feedback
    Aman Madaan, Niket Tandon, Prakhar Gupta, and 13 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
  2. Generating Sequences by Learning to Self-Correct
    Sean Welleck, Ximing Lu, Peter West, and 4 more authors
    In The Eleventh International Conference on Learning Representations , 2023

2020

  1. A Generalized Framework of Sequence Generation with Application to Undirected Sequence Models
    Elman Mansimov, Alex Wang, Sean Welleck, and 1 more author
    2020