method · first seen 13 Oct 2026
preference-based alignment
Aligning language models to human preferences using comparison or ranking feedback.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Rank-Aware Differentially Private Release of Listwise Preferences for LLM AlignmentPapers · 13 Oct 2026 · Junwei Chen, Manjiang Yu, Pengpeng Qiao, Yang Cao
Latest sources
- Rank-Aware Differentially Private Release of Listwise Preferences for LLM AlignmentPapers · 13 Oct 2026 · Junwei Chen, Manjiang Yu, Pengpeng Qiao, Yang Cao