PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
Paper • 2608.30597 • Published • 27
Sujin Kim
niirhv
AI & ML interests
None yet
Recent Activity
upvoted a paper 14 days ago
PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization upvoted a paper 19 days ago
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation upvoted a paper 25 days ago
Language Models Can Control Their Own AttentionOrganizations
None yet