Papers by Kin Kwan Leung

1 papers
Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems (2026.eacl-long)

Copied to clipboard

Challenge: Existing work on RAG errors has not accounted for the complexity of real-world RAG systems and their failure modes.
Approach: They propose a taxonomy of error types that can occur in realistic RAG systems and an auto-evaluation method that can be used to track errors during development.
Outcome: The proposed method can be used in practice to track and address errors during development.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations