Daiting Shi
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Thinking as Compression (TaC), a novel paradigm showing that the inherent reasoning process of a large language model can naturally compress long context inputs, outperforming dedicated compression methods.
The paper introduces Thinking as Compression (TaC), a novel paradigm showing that the inherent reasoning process of a large language model can naturally compress long context inputs, outperforming dedicated compression methods.
The authors present Querit-Reranker, a family of multilingual cross-encoder rerankers that can adapt to new target distributions with minimal task-specific relevance annotations.
Papers
Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation
Yunfei Zhong, Jun Yang, Wei Huang, Yinqiong Cai +6 more
The authors present Querit-Reranker, a family of multilingual cross-encoder rerankers that can adapt to new target distributions with minimal task-specific relevance annotations.