recomp: improving retrieval-augmented lms with compression and selective augmentation (1) 썸네일형 리스트형 [논문이해] RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation 논문명: RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation논문 링크: https://arxiv.org/abs/2310.04408 RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective AugmentationRetrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning h.. 이전 1 다음
