Papers by Joongmin Shin
HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to document-based Opendomain Question Answering (ODQA) use flat text chunks or page-level images to locate the correct document. |
| Approach: | They propose a hierarchical tree-based multimodal retrieval framework that elevates document hierarchy to a first-class retrieval signal. |
| Outcome: | The proposed framework outperforms page- and chunk-based baselines on ODQA benchmarks and improves retrieval recall by 12.9% and end-to-end QA performance by 6.8%. |
MultiDocFusion : Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing text chunking methods neglect complex and long industrial document structures, causing information loss and reduced answer quality. |
| Approach: | They propose a multimodal chunking pipeline that detects document regions and extracts text from them via OCR. |
| Outcome: | Extensive tests show that MultiDocFusion improves retrieval precision by 8–15% and ANLS QA scores by 2–3% compared to baselines. |