InfoPO's mutual information derivation fails: its rejected-response regularizer is constant in expectation, leaving plain supervised fine-tuning on chosen responses.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
InfoPO: On Mutual Information Maximization for Large Language Model Alignment
InfoPO's mutual information derivation fails: its rejected-response regularizer is constant in expectation, leaving plain supervised fine-tuning on chosen responses.