Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs
Similarity-based retrieval is the dominant rule for conditioning large language models (LLMs) in in-context learning, retrieval-augmented generation, and prompt-based time series forecasting. The rule concentrates on near-duplicate candidates, an issue that has motivated diversity-aware retrieval but remains unexamined...
D. Ji, Minkyoung Kim, Dongkuk Kim et al.
· 0 citations