Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering.
Hongyu YangLiyang HeMin HouShuanghong ShenRui LiJiahui HouJianhui MaJunda ZhaoPublished in: CoRR (2024)
Keyphrases
- question answering
- user preferences
- multi perspective
- user feedback
- candidate answers
- d scene
- information retrieval
- natural language processing
- user profiles
- preference model
- question classification
- user behavior
- collaborative filtering
- passage retrieval
- recommender systems
- cross language
- qa clef
- information extraction
- natural language
- ranking functions
- answer validation
- syntactic information
- answering questions
- high quality
- question answering systems
- semantic roles
- answer extraction
- learning to rank
- information retrieval systems
- optical flow