mlsanityData to 14 Oct 2026

Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents

arXiv 2604.14222 ↗First posted 14 Apr 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Legal and financial RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win rate. Concurrently, the PageIndex framework [2] demonstrated 98.7% accuracy on FinanceBench through purely reasoning-based retrieval. This paper extends their work by: (i) implementing and evaluating three retrieval architectures: Vector RAG, Tree Reasoning, and the proposed Adaptive Hybrid Retrieval (AHR) across financial, legal, and medical domains; (ii) introducing a four-tier query complexity benchmark; and (iii) employing GPT-4-powered LLM-as-judge evaluation. Experiments reveal that Tree Reasoning achieves the highest overall score (0.900), but no single paradigm dominates across all tiers: Vector RAG wins on multi-document synthesis (Tier 4, score 0.900), while the Hybrid AHR achieves the best performance on cross-reference (0.850) and multi-section queries (0.929). Cross-reference recall reaches 100% for tree-based and hybrid approaches versus 91.7% for vector search, quantifying a critical capability gap. Validation on FinanceBench (150 expert-annotated questions on real SEC 10-K and 10-Q filings) confirms and strengthens these findings: Tree Reasoning scores 0.938, Hybrid AHR 0.901, and Vector RAG 0.821, with the Tree--Vector quality gap widening to 11.7 percentage points on real-world documents. These findings support the development of adaptive retrieval systems that dynamically select strategies based on query complexity and document structure. All code and data are publicly available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 51 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

27 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off26 Mar

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  9. 2017Billion-scale similarity search with GPUscited by 2,497
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  11. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  12. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
14 more
  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  2. 2019Passage Re-ranking with BERTcited by 645
  3. 2023Active Retrieval Augmented Generationcited by 516
  4. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  5. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  6. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  7. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  8. 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
  9. 2021LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysiscited by 58
  10. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  11. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 47
  12. 2024Financial Report Chunking for Effective Retrieval Augmented Generationcited by 46
  13. 2024RAG-Fusion: a New Take on Retrieval-Augmented Generationcited by 42
  14. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models
  2. 2026HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings
  3. 2026MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
  4. 2025Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
  5. 2026From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents
  6. 2026Hierarchical Reranking for Scalable Financial RAG System
  7. 2026Agentic Retrieval-Augmented Generation for Financial Document Question Answering
  8. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answering