2 papers
cs.CL2024
Arena-Lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons
Seonil Son, Ju-Min Oh, Heegon Jin +3
As Large Language Models (LLMs) expand across domains, LLM judges have become essential for systems evaluation. Current benchmarks typically compare system outputs against baseline…
cs.CL2024
Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult
Cheolhun Jang
Preference optimization methods typically begin training with a well-trained SFT model as a reference model. In RLHF and DPO, a regularization term is used during the preference op…