2 papers
cs.CL2025
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
Rheeya Uppaal, Apratim Dey, Yiting He +2
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…
cs.CL2025
How Useful is Continued Pre-Training for Generative Unsupervised Domain Adaptation?
Rheeya Uppaal, Yixuan Li, Junjie Hu
Recent breakthroughs in scale have enabled the emergence of powerful generative language models, and the ability to fine-tune these models on various tasks by casting them into pro…