From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents

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.

We study retrieval-augmented generation (RAG) for questions about French PDF documents when both the answer and its supporting document pages are evaluated. Five system variants add dense retrieval, rank fusion, reranking, and query decomposition to a BM25 baseline. On 595 challenge questions, the complete system scores 0.4450 MRR@10 and 0.4013 Recall@10, compared with 0.3430 and 0.2994 for BM25. Dense retrieval alone and a simple lexical--dense fusion both underperform BM25. Reranking improves the hybrid system, whereas adding query decomposition produces the largest further gain, with higher latency and more detected output artifacts. The complete system slightly exceeds the reported anonymous overall mean on two answer metrics but falls below it on most page-retrieval metrics. These results identify accurate page selection, rather than semantic retrieval in isolation, as the main opportunity for improvement in this setting.

Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings. We study a frequent failure mode in which the correct document is retrieved but the page or chunk that contains the answer is missed, leading the generator to extrapolate from incomplete context. Despite its practical significance, this within-document retrieval failure mode has received limited systematic attention in the Financial Question Answering (QA) literature. We evaluate retrieval at multiple levels of granularity, document, page, and chunk level, and introduce an oracle based analysis to provide empirical upper bounds on retrieval and generative performance. On a 150 question subset of FinanceBench, we reproduce and compare diverse retrieval strategies including dense, sparse, hybrid, and hierarchical methods with reranking and query reformulation. Across methods, gains in document discovery tend to translate into stronger page recall, yet oracle performance still suggests headroom for page and chunk level retrieval. To target this gap, we introduce a domain fine-tuned page scorer that treats pages as an intermediate retrieval unit between documents and chunks. Unlike prior passage-based hierarchical retrieval, we fine-tune a bi-encoder specifically for page-level relevance on financial filings, exploiting the semantic coherence of pages. Overall, our results demonstrate a significant improvement in page recall and chunk retrieval.