2 papers
cs.CL2023
Self-Detoxifying Language Models via Toxification Reversal
Chak Tou Leong, Yi Cheng, Jiashuo Wang +2
Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can b…
cs.CL2023
Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation
Jian Wang, Yi Cheng, Dongding Lin +2
Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversati…