Search Results for author:
Found 1 papers, 0 papers with code
Decomposing Label Space, Format and Discrimination: Rethinking How LLMs Respond and Solve Tasks via In-Context Learning
Counter-intuitively, we find that the demonstrations have a marginal impact on provoking discriminative knowledge of language models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
