7 papers · 1 filter
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation
Shuaiyi Li, Zhisong Zhang, Yan Wang +5
Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios su…
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing
Shuaiyi Li, Zhisong Zhang, Yang Deng +6
Although existing model editing methods perform well in recalling exact edit facts, they often struggle in complex scenarios that require deeper semantic understanding rather than…
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +6
Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…
Large Language Models for Information Retrieval: A Survey
Yutao Zhu, Huaying Yuan, Shuting Wang +7
As a primary means of information acquisition, information retrieval (IR) systems, such as search engines, have integrated themselves into our daily lives. These systems also serve…
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models
Zhisong Zhang, Yan Wang, Xinting Huang +5
Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used m…
A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression
Chenlong Deng, Zhisong Zhang, Kelong Mao +4
In this work, we provide a thorough investigation of gist-based context compression methods to improve long-context processing in large language models. We focus on two key questio…