3 citations · 3 across the 6 of their papers we have counts for
7 papers
Attention Needs to Focus: A Unified Perspective on Attention Allocation
Zichuan Fu, Wentao Song, Guojing Li +6
The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanis…
A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
Yimin Deng, Yuxia Wu, Yejing Wang +9
Temporal knowledge graph reasoning aims to predict future events with knowledge of existing facts and plays a key role in various downstream tasks. Previous methods focused on eith…
Model Merging for Knowledge Editing
Zichuan Fu, Xian Wu, Guojing Li +6
Large Language Models (LLMs) require continuous updates to maintain accurate and current knowledge as the world evolves. While existing knowledge editing approaches offer various s…
Training-free LLM Merging for Multi-task Learning
Zichuan Fu, Xian Wu, Yejing Wang +6
Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen…
Sliding Window Attention Training for Efficient Large Language Models
Zichuan Fu, Wentao Song, Yejing Wang +7
Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity…
Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
Derong Xu, Xinhang Li, Ziheng Zhang +7
Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in…