From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems

Researchers demonstrate that coreference resolution significantly improves Retrieval-Augmented Generation (RAG) systems by reducing ambiguity in document retrieval and enhancing question-answering performance. The study finds that smaller language models benefit more from disambiguation processes, with mean pooling strategies showing superior context capturing after coreference resolution.

• →Coreference resolution enhances both document retrieval effectiveness and generative performance in RAG systems.
• →Mean pooling demonstrates superior context capturing ability after applying coreference resolution in retrieval tasks.
• →Smaller language models benefit more from disambiguation processes due to their limited capacity for handling referential ambiguity.
• →Coreferential complexity in retrieved documents introduces ambiguity that disrupts in-context learning in RAG systems.
• →The research provides guidance for improving retrieval and generation in knowledge-intensive AI applications.