检索说明
- 查询:GraphRAG evidence retrieval
- 年份过滤:2025-
- 单查询上限:20
- 发现日期:2026-11-12
Semantic Scholar 候选元数据
- 作者:Seonok Kim
- 年份:2026
- Venue:arXiv.org
- DOI:10.48550/arXiv.2607.16208
- arXiv:2607.16208
- S2 citationCount(当前快照):0
- 来源线索:https://doi.org/10.48550/arXiv.2607.16208
摘要(未核验)
Graph-grounded multimodal question answering organizes text, tables, and images in a structured evidence graph, yet end-to-end accuracy depends on which multimodal assets are ranked highly enough to enter downstream reasoning; for graph-linked images, single-vector bi-encoder similarity can discard patch- and token-level structure needed for fine-grained alignment. We evaluate replacing the visual candidate-ranking operator over graph-linked image nodes with late-interaction MaxSim-style multi-vector scoring in the ColBERT/ColPali lineage, while keeping offline graph construction, text- and table-side retrieval, structured extraction, and downstream reasoning unchanged. On MultimodalQA, this change is associated with improved retrieval-stage point estimates for graph-linked image candidates and downstream QA gains, with larger movement where visual evidence matters most and mixed trends on text-dominant questions; we interpret the pattern as mechanism-level evidence for graph-linked visual evidence inclusion, while broader validation and finer graph-level diagnostics remain important future work.
转为正式文献前的核验清单
- [ ] 从论文、出版社、会议、ACL Anthology、OpenReview 或 arXiv 页面核对标题、作者、年份和版本。
- [ ] 核对 DOI、venue、正式链接和是否存在撤稿/版本变化。
- [ ] 阅读正文后补充方法、证据边界、结果和与现有研究的关系。
Semantic Scholar 记录用于发现候选,不是正式一手引文,也不支持对结果覆盖范围或研究质量的穷尽性判断。