Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval

• URL: http://arxiv.org/abs/2603.26815v1
• Date: Thu, 26 Mar 2026 18:05:38 GMT
• Title: Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval
• Abstract summary: Hybrid Document-Routed Retrieval (HDRR) is a two-stage architecture that uses SFR as a document filter followed by chunk-based retrieval scoped to the identified document(s)<n> Experimental results demonstrate that HDRR achieves the best performance on every metric.
• Score: 7.563079821809866
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) systems for financial document question answering typically follow a chunk-based paradigm: documents are split into fragments, embedded into vector space, and retrieved via similarity search. While effective in general settings, this approach suffers from cross-document chunk confusion in structurally homogeneous corpora such as regulatory filings. Semantic File Routing (SFR), which uses LLM structured output to route queries to whole documents, reduces catastrophic failures but sacrifices the precision of targeted chunk retrieval. We identify this robustness-precision trade-off through controlled evaluation on the FinDER benchmark (1,500 queries across five groups): SFR achieves higher average scores (6.45 vs. 6.02) and fewer failures (10.3% vs. 22.5%), while chunk-based retrieval (CBR) yields more perfect answers (13.8% vs. 8.5%). To resolve this trade-off, we propose Hybrid Document-Routed Retrieval (HDRR), a two-stage architecture that uses SFR as a document filter followed by chunk-based retrieval scoped to the identified document(s). HDRR eliminates cross-document confusion while preserving targeted chunk precision. Experimental results demonstrate that HDRR achieves the best performance on every metric: an average score of 7.54 (25.2% above CBR, 16.9% above SFR), a failure rate of only 6.4%, a correctness rate of 67.7% (+18.7 pp over CBR), and a perfect-answer rate of 20.1% (+6.3 pp over CBR, +11.6 pp over SFR). HDRR resolves the trade-off by simultaneously achieving the lowest failure rate and the highest precision across all five experimental groups.

Related papers

• HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries [1.5965246343492343]
  HIRA is a training-free, on-premises retrieval-augmented cascade for document classification in regulated deployments.<n>Confident documents are classified directly by retrieval; uncertain or visually confusable documents are passed to a locally hosted verifier.<n>On a private 80-class trade-finance corpus, HIRA processes the full 30,233-document production stream while requesting human correction for only 1,945 documents.
  arXiv  Detail & Related papers  (2026-08-22T06:19:19Z)
• The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context [45.88028371034407]
  We report a controlled case study in code repair, not a new phenomenon.<n>We toggle one flag (one-chunk-perfile deduplication) on an otherwise identical stack.<n>We map where it holds: it reverses on a lexical BM25 (3.2pp, significant cross-paradigm interaction)<n>We show that at a tight fixed budget, do not hard-deduplicate by file, and A/B packing policies against the task, not the metric flag was tuned.
  arXiv  Detail & Related papers  (2026-08-14T19:22:50Z)
• TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models [40.42873860258522]
  We propose TrustRoboReward, a multi-paradigm reward modeling framework equipped with Preference-Ordered Isotonic Score Editing (POISE)<n>POISE rectifies pointwise scores and eliminates cross-paradigm reversal conflicts unresolved by TrustJudge.<n>Qwen3-VL-4B trained with POISE achieves an overall reward score of 77.96%, nearly matching GPT-5-mini (78.09%, gap 0.13%) and outperforming the strongest RoboReward-4B baseline by 10.13%.
  arXiv  Detail & Related papers  (2026-08-09T05:25:22Z)
• CalibratedRubric: Task-Adaptive Rubric Banks for Open-Ended LLM Evaluation [11.869490719319577]
  CalibratedRubric is a task-adaptive framework that combines type-specific scoring, Bayesian rubric-measurability filtering, and item response theory (IRT)-based bank assembly.<n>Across financial, healthcare, general, and legal benchmarks, measurability filtering improves human-gold agreement.<n>IRT-based greedy selection improves cross-fitted rank fidelity over random selection.
  arXiv  Detail & Related papers  (2026-07-31T10:21:56Z)
• Architecture-Adaptive Uncertainty Fusion for Deepfake Detection [0.9940728137241215]
  Deepfake detection systems achieve near-perfect accuracy on benchmarks, yet forensic deployment demands reliable prediction uncertainty.<n>We propose Correlation-d Fusion (COF), an architecture-adaptive framework that fuses five complementary uncertainty sources.<n>COF requires no model modifications and only 42 s of weight optimization, compared to 20--45 h for a 5-model Deep Ensemble.
  arXiv  Detail & Related papers  (2026-06-04T19:28:55Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering [32.10503220086596]
  Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing.<n>No prior study has evaluated PDF processing frameworks by their impact on downstream question-answering accuracy.<n>We compare four open-source PDF-to-Markdown conversion frameworks, Docling, MinerU, Marker, and DeepSeek OCR, across 19 pipeline configurations.
  arXiv  Detail & Related papers  (2026-03-30T14:40:58Z)
• DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality [49.62610727661819]
  Existing fact-checkers are primarily designed for general-domain, factoid-style atomic claims.<n>We propose Audit-then-Score (AtS), where benchmark labels and rationales are explicitly revisable.<n>We instantiate AtS as DeepFact-Bench, a versioned DRR factuality benchmark with auditable rationales.
  arXiv  Detail & Related papers  (2026-03-06T05:05:57Z)
• From Black Box to Glass Box: Cross-Model ASR Disagreement to Prioto Review in Ambient AI Scribe Documentation [43.148402136307716]
  Cross-model disagreement among heterogeneous ASR systems can act as a reference-free uncertainty signal.<n>We transcribed 50 publicly available medical audio clips with eight ASR systems spanning commercial APIs and open-source engines.<n>Low-agreement regions were enriched for content disagreements, with the content fraction increasing from 53.9% to 73.9% across quintiles of high-risk mass.
  arXiv  Detail & Related papers  (2026-03-02T13:02:13Z)
• Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks [17.117706938140078]
  We propose RRD, a principled framework for rubric refinement built on a decompose-filter cycle.<n> RRD decomposes coarse rubrics into fine-grained, discriminative criteria, expanding coverage while sharpening separation between responses.<n>It delivers large, consistent gains across both evaluation and training.
  arXiv  Detail & Related papers  (2026-02-04T23:16:09Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models [0.0]
  We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering.<n>We measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs.<n>Our findings reveal that applying advanced RAG techniques to financial Q&A systems improves retrieval accuracy, answer quality, and has cost-performance tradeoffs to be considered in production.
  arXiv  Detail & Related papers  (2025-11-22T20:06:25Z)
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data? [82.09573568241724]
  EssenceBench is a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA)<n>Our approach yields superior compression results with lower reconstruction error and markedly higher efficiency.<n>On the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.
  arXiv  Detail & Related papers  (2025-10-12T05:38:10Z)
• An Auditable Pipeline for Fuzzy Full-Text Screening in Systematic Reviews: Integrating Contrastive Semantic Highlighting and LLM Judgment [0.0]
  Full-text screening is the major bottleneck of systematic reviews.<n>We present a scalable, auditable pipeline that reframes inclusion/exclusion as a fuzzy decision problem.
  arXiv  Detail & Related papers  (2025-08-17T17:41:50Z)
• Classification or Prompting: A Case Study on Legal Requirements Traceability [4.629156733452248]
  Legal requirements traceability is a key task where engineers must analyze technical requirements against target artifacts.<n>In this paper, we investigate two automated solutions based on language models, including large ones (LLMs)<n>The first solution, Kashif, is a classifier that leverages sentence transformers and semantic similarity.<n>The second solution, RICE_LRT, prompts a recent generative LLM based on RICE, a prompt engineering framework.
  arXiv  Detail & Related papers  (2025-02-07T13:33:40Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
  Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)
• LLMs Can Patch Up Missing Relevance Judgments in Evaluation [56.51461892988846]
  We use large language models (LLMs) to automatically label unjudged documents. We simulate scenarios with varying degrees of holes by randomly dropping relevant documents from the relevance judgment in TREC DL tracks. Our method achieves a Kendall tau correlation of 0.87 and 0.92 on an average for Vicuna-7B and GPT-3.5 Turbo respectively.
  arXiv  Detail & Related papers  (2024-05-08T00:32:19Z)
• End-to-End Sensitivity-Based Filter Pruning [49.61707925611295]
  We present a sensitivity-based filter pruning algorithm (SbF-Pruner) to learn the importance scores of filters of each layer end-to-end. Our method learns the scores from the filter weights, enabling it to account for the correlations between the filters of each layer.
  arXiv  Detail & Related papers  (2022-04-15T10:21:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.