CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical c...
Cheng-Yen Li, Xuanjun Chen, Claire Lin et al.
· ACM Transactions on Intellig... · 0 citations