Skip to content
conftrace_

human-labeled preference data

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

generative large language model (1) discriminative fine-tuning (1) reward model (1) optimization algorithm (1) probabilistic framework (1)

Papers

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data ICML 2025