How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Yushi Yang, Filip Sondej, Harry Mayne, Andrew Lee, Adam Mahdi. How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 29524-29543, Association for Computational Linguistics, 2025. [doi]

This author has not been identified. Look up 'Yushi Yang' in GoogleThis author has not been identified. Look up 'Filip Sondej' in GoogleThis author has not been identified. Look up 'Harry Mayne' in GoogleThis author has not been identified. Look up 'Andrew Lee' in GoogleThis author has not been identified. Look up 'Adam Mahdi' in Google

runs on WebDSL