AIConfPaper
← Search

Ziyu Zhuang

2 accepted papers

2022

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
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…

Cited by 38Source ↗PDF ↗Scholar ↗
2022

SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation

Longxuan Ma, Ziyu Zhuang, Weinan Zhang, Mingda Li, Ting Liu
COLING 2022main

This paper introduces a novel Self-supervised Fine-grained Dialogue Evaluation framework (SelF-Eval). The core idea is to model the correlation between turn quality and the entire dialogue quality. We first propose a novel automatic data construction method that can automatically assign fine-grained…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗