Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Fotouhi, Milad"'
Autor:
Fotouhi, Milad, Bahadori, Mohammad Taha, Feyisetan, Oluwaseyi, Arabshahi, Payman, Heckerman, David
We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based approach tha
Externí odkaz:
http://arxiv.org/abs/2408.11852