Showing 2024Show all
3 papers · 1 filter
cs.CL2024
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
Yihang Wang, Xu Huang, Bowen Tian +6
Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in…
cs.CL2024
QUITO: Accelerating Long-Context Reasoning through Query-Guided Context Compression
Wenshan Wang, Yihang Wang, Yixing Fan +2
In-context learning (ICL) capabilities are foundational to the success of large language models (LLMs). Recently, context compression has attracted growing interest since it can la…
cs.CL2024
Token-Efficient Leverage Learning in Large Language Models
Yuanhao Zeng, Min Wang, Yihang Wang +1
Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and th…