Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval

arXiv:2608.00183v2 Announce Type: replace-cross Abstract: Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense…

Read the full story at arXiv cs.AI ↗