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

arXiv: https://arxiv.org/abs/2608.00183 · HTML: https://mlsanity.com/paper/2608.00183/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Sparse, Dense, and Attentional Representations for Text Retrieval](https://mlsanity.com/paper/2005.00181/) (2020)
- [FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.15800/) (2025)
- [From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets](https://mlsanity.com/paper/2605.28359/) (2026)
- [The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents](https://mlsanity.com/paper/2605.08060/) (2026)
- [GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases](https://mlsanity.com/paper/2605.30237/) (2026)
- [Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened](https://mlsanity.com/paper/2607.13083/) (2026)
- [Item Response Theory based Ensemble in Machine Learning](https://mlsanity.com/paper/1911.04616/) (2019)
- [CURE:Circuit-Aware Unlearning for LLM-based Recommendation](https://mlsanity.com/paper/2604.04982/) (2026)
- [The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management](https://mlsanity.com/paper/2605.23071/) (2026)
- [Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach](https://mlsanity.com/paper/2605.23924/) (2026)
- [CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation](https://mlsanity.com/paper/2604.05113/) (2026)
- [Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting](https://mlsanity.com/paper/2606.18367/) (2026)
- [Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market](https://mlsanity.com/paper/2606.12843/) (2026)
- [DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation](https://mlsanity.com/paper/2606.28725/) (2026)
- [Local MDI+: Local Feature Importances for Tree-Based Models](https://mlsanity.com/paper/2506.08928/) (2025)
- [Revealing Treatment Non-Adherence Bias in Clinical Machine Learning Using Large Language Models](https://mlsanity.com/paper/2502.19625/) (2025)
- [When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost](https://mlsanity.com/paper/2607.24010/) (2026)
- [M3TR: Temporal Retrieval Enhanced Multi-Modal Micro-video Popularity Prediction](https://mlsanity.com/paper/2411.15455/) (2024)
- [Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation](https://mlsanity.com/paper/2607.21518/) (2026)

## Built on by (most cited first, 1 of 1)

- [Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification](https://mlsanity.com/paper/2608.17247/) (2026)

## Abstract (arXiv)

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 hybrid retrieval on FinDER, a benchmark of expert-annotated questions over corporate 10-K filings. Our first finding is methodological: if the retrieval unit is larger than the dense encoder's input window, the dense model never sees a large share of the labeled evidence, confounding comparison against a full-text sparse baseline. We measure this directly and reduce the imbalance with windows chosen for the encoder budget. On this corpus, fusing BM25 and a compact dense encoder improves reference-level Hit@10 by roughly 28 percent over either component, and training-free, untuned reciprocal rank fusion exceeds the equal-weight blend in an exploratory comparison. We then ask whether choosing the fusion weight per query helps: an oracle over the interpolation-weight grid shows headroom of 21.8 percent, yet none of the three lightweight adaptive routers (a score-confidence heuristic, a random forest over query features, and a ridge regressor over query embeddings) establishes a statistically reliable improvement over the fixed blend under company-grouped cross-validation with cluster-robust inference. Simple fusion is a strong baseline here, and we discuss why per-query weighting does not capture the available headroom.