Maximizing mutual information between prompts and responses improve LLM personalization with no additional data or human oversight

概要

arXiv:2603.19294v2 Announce Type: replace-cross Abstract: While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new high-quality data…