Detoxifying Large Language Models via Localized Feature Editing with Sparse Autoencoders
Yuhu Shang, Xiang Cheng, Dianyun Wang et al.
· 0 citations
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
#natural language process...
Oct 2025
Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
This work introduces a type-induced commitment-communication mechanism that grounds Bayesian Persuasion in natural language dialogue without pre-commitment, and implements two variants: Semi-Formal-Natural-Language (SFNL) and Fully-Natural-Language (FNL), evaluating them against strong baselines and human judges.
Buwei He, Yang Liu, Zhaowei Zhang et al.
· arXiv.org · 1 citation