2 papers
cs.LG2024
Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts
Taneesh Gupta, Rahul Madhavan, Xuchao Zhang +3
Direct Preference Optimization (DPO) has become a popular approach for aligning language models using pairwise preferences. However, in practical post-training pipelines, on-policy…
cs.CL2024
CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling
Taneesh Gupta, Shivam Shandilya, Xuchao Zhang +5
Reward modeling in large language models is susceptible to reward hacking, causing models to latch onto superficial features such as the tendency to generate lists or unnecessarily…