y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#distribution-preference-optimization News & Analysis

1 article tagged with #distribution-preference-optimization. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AINeutralarXiv – CS AI · 6h ago6/10
🧠

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

Researchers introduce DiPO (Distribution Preference Optimization), a novel algorithm for LLM unlearning that operates at the token distribution level rather than full response level. The method addresses limitations in existing approaches like NPO by constructing preference signals through selective amplification of model logits, achieving superior performance on benchmark tests while maintaining model utility.