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…
math.MG2024
Stability of the log-Brunn-Minkowski inequality in the case of many hyperplane symmetries
Karoly Boroczky, Apratim De
In the case of symmetries with respect to n independent linear hyperplanes, a stability version of the logarithmic Brunn-Minkowski inequality and the logarithmic Minkowski inequali…