Risultati di ricerca
1 gen 2023 · Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits. Ruibo Liu, Chenyan Jia, Ge Zhang, Ziyu Zhuang, Tony X Liu, Soroush Vosoughi. We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values.
- arXiv:2301.00355 [cs.CL]
1 gen 2023 · Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits | Papers With Code. 1 Jan 2023 · Ruibo Liu , Chenyan Jia , Ge Zhang , Ziyu Zhuang , Tony X Liu , Soroush Vosoughi ·. Edit social preview. We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values.
- Ruibo Liu
Abstract. 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 addi-tional refinement through reinforcement learning, SECOND THOUGHTS not only achieves superior performance in three value alignment benchmark datasets but also shows strong human-value transfer learning ability in few-shot scenarios.
Abstract. 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 achieves superior performance in ...
1 gen 2023 · Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits. January 2023. License. CC BY-NC-ND 4.0. Authors: Ruibo Liu. Chenyan Jia. Stanford University. Ge Zhang....
