Search

Qifan Wang

K-order Ranking Preference Optimization for Large Language Models
Agentic Feedback Loop Modeling Improves Recommendation and User Simulation
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
Direct Multi-Turn Preference Optimization for Language Agents

Published with Wowchemy — the free, open source website builder that empowers creators.