AI RESEARCH
GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks
arXiv CS.CL
•
ArXi:2605.07454v1 Announce Type: new In-context learning enables large language models to adapt to new tasks, but their performance is highly sensitive to the selected examples. Finding effective nstrations is particularly difficult in domain-specific, low-data settings where high-quality examples are scarce. We propose GRaSp, a three-stage framework for automatic in-context example optimization.