1 citations · 1 across the 4 of their papers we have counts for
4 papers
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
Jiaang Li, Zhendong Mao, Quan Wang +2
Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhi…
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
Jiaang Li, Quan Wang, Zhongnan Wang +2
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for…
Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation
Jiaang Li, Quan Wang, Yi Liu +2
Representation Learning on Knowledge Graphs (KGs) is essential for downstream tasks. The dominant approach, KG Embedding (KGE), represents entities with independent vectors and fac…
Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers
Jiaang Li, Quan Wang, Zhendong Mao
Relation prediction on knowledge graphs (KGs) is a key research topic. Dominant embedding-based methods mainly focus on the transductive setting and lack the inductive ability to g…