2022
Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits
NeurIPS 2022accept
We present Second Thoughts, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thoughts not only…