opt-ProFS-toxicity
27 downloads
0 likes
on Hugging Face
updated
Papers using or citing this model 2
-
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to...
-
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
Recent alignment algorithms such as direct preference optimization (DPO) have been developed to improve the safety of large language models (LLMs) by training these models to match human behaviors exemplified by preference data....