Si Sun

Rethinking Dense Retrieval's Few-Shot Ability

2023 · arXiv (Cornell University)

Few-shot dense retrieval (DR) aims to effectively generalize to novel search scenarios by learning a few samples. Despite its importance, there is little study on specialized datasets and standardized evaluation protocols. As a result, current …

UniMem: Towards a Unified View of Long-Context Large Language Models

2024 · arXiv (Cornell University)

Long-context processing is a critical ability that constrains the applicability of large language models (LLMs). Although there exist various methods devoted to enhancing the long-context processing ability of LLMs, they are developed in an isolated …