Performance-Driven Demonstration Selection for In-Context Learning
Performance-Driven Demonstration Selection (PDDS), which directly aligns demonstration selection with ICL performance, is proposed, which formulates selection as predicting the target LLM’s downstream task performance for a given query–in-context pair, replacing proxy heuristics with a performance-aware objec-tive.
Wenqiang Wang, Mingbo Yang, Aiping Zhang et al.
· 0 citations