most citedA Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

4 citations · 5 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2024★ 4 cited

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity

Andrew Lee, Xiaoyan Bai, Itamar Pres +3

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 model…

cs.CL2022

Using Paraphrases to Study Properties of Contextual Embeddings

Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea

We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase…