Papers by Byeongcheol Kang
CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG (2026.findings-acl)
Copied to clipboard
| Challenge: | Multilingual retrieval-augmented generation is inadequate for culturally grounded queries . Across two cultural QA benchmarks, CORAL achieves a 3.58%p accuracy improvement on low-resource languages . |
| Approach: | They propose a multilingual retrieval-augmented generation approach that enables iterative refinement of both the retrieval space and the retrieving probe based on the quality of the evidence. |
| Outcome: | Using CORAL, researchers find that culturally grounded queries can be improved . if retrieved documents are insufficient, the system reselects them and rewrites the query . |