Tag
Proposes Reliability-Guided Preference Optimization (RGPO) to handle inconsistent human feedback in LLM alignment by estimating annotator reliability and dynamically modulating training based on consensus, achieving superior performance over standard RLHF methods.
This paper proposes AHEAD, a cross-annotator learning framework for multi-class label aggregation that uses graph neural networks to model annotator reliability, achieving significant accuracy improvements on 10 real-world datasets spanning NLP, CV, Video, and Audio.