FinRED creates an expert-validated benchmark and rubric for financial LLM safety that maps regulatory standards to specific threats and reduces critical false negatives in evaluation from 28 to 12.
Financial report chunking for effective retrieval augmented generation
12 Pith papers cite this work, alongside 16 external citations. Polarity classification is still indexing.
12
Pith papers citing it
16
external citations · external index
representative citing papers
LEDGER provides a corpus of 4,999 annual reports with 31 labeled KPIs and three benchmarks for page-level retrieval, needle-in-haystack lookup, and full KPI extraction from long documents.
IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraBench benchmark.
SHM-Agents is an LLM-plus-specialist-agent framework that claims to execute a wide range of SHM tasks end-to-end via natural language on data from a long-span cable-stayed bridge.
Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.
Systematic tests show that specific PDF parsers combined with overlapping chunking strategies better preserve structure and improve RAG answer correctness on financial QA benchmarks including the new TableQuest dataset.
RefineRAG achieves 90% attack success on NQ by generating toxic seeds then optimizing them via retriever-in-the-loop word refinement, outperforming prior methods on effectiveness and naturalness.
Using LLM extraction on 681 papers, the authors build a public knowledge graph showing financial NLP moved from LLM adoption to limitation-aware, modular system design between 2022 and 2025.
MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
Structured memory improves precision on deterministic financial calculations while retrieval-augmented generation outperforms in conversational settings, supporting a hybrid deployment framework for resource-constrained SMEs.
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.
citing papers explorer
-
FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming
FinRED creates an expert-validated benchmark and rubric for financial LLM safety that maps regulatory standards to specific threats and reduces critical false negatives in evaluation from 28 to 12.
-
LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction
LEDGER provides a corpus of 4,999 annual reports with 31 labeled KPIs and three benchmarks for page-level retrieval, needle-in-haystack lookup, and full KPI extraction from long documents.
-
IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review
IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraBench benchmark.
-
SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring
SHM-Agents is an LLM-plus-specialist-agent framework that claims to execute a wide range of SHM tasks end-to-end via natural language on data from a long-span cable-stayed bridge.
-
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
Tree reasoning outperforms vector search on complex document queries but a hybrid approach balances results across tiers, with validation showing an 11.7-point gap on real finance documents.
-
Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG
Systematic tests show that specific PDF parsers combined with overlapping chunking strategies better preserve structure and improve RAG answer correctness on financial QA benchmarks including the new TableQuest dataset.
-
RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement
RefineRAG achieves 90% attack success on NQ by generating toxic seeds then optimizing them via retriever-in-the-loop word refinement, outperforming prior methods on effectiveness and naturalness.
-
MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)
Using LLM extraction on 681 papers, the authors build a public knowledge graph showing financial NLP moved from LLM adoption to limitation-aware, modular system design between 2022 and 2025.
-
MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
-
MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
MimirRAG, a multi-agent RAG framework with metadata integration and table-aware chunking, reaches 89.3% accuracy on FinanceBench and outperforms prior baselines for financial document retrieval.
-
Architecture Matters More Than Scale: A Comparative Study of Retrieval and Memory Augmentation for Financial QA Under SME Compute Constraints
Structured memory improves precision on deterministic financial calculations while retrieval-augmented generation outperforms in conversational settings, supporting a hybrid deployment framework for resource-constrained SMEs.
-
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
Cluster-based semantic chunking does not outperform fixed-size or recursive chunking for RAG on academic theses, and RAGAs faithfulness shows limited reliability in this setup.