Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
1122 · Aug 202419922001200920172026
4 results for “GraphRAG”
Enhancing Startup Success Predictions in Venture Capital: A GraphRAG Augmented Multivariate Time Series Methodq-fin.CP

Enhances VC startup success predictions using graph augmented time series models.

problem Challenges in predicting startup success due to limited financial data and subjective forecasts.
method Integrates inter-company relationships into time series analysis using GraphRAG.
result Significantly outperforms previous models in startup success predictions.
Venture CapitalStartup SuccessGraphRAGTime SeriesInter-Company Relationships
2024-08-18abs ↗pdf ↗
HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extractioncs.CL

HybridRAG combines KGs and vector retrieval for financial document Q&A.

problem Challenges in extracting and interpreting financial text data.
method Integrates Knowledge Graphs and Vector Retrieval Augmented Generation.
result HybridRAG outperforms traditional methods in Q&A systems for financial documents.
HybridRAGKnowledge GraphsVector RetrievalFinancial DocumentsQ&A Systems
2024-08-09abs ↗pdf ↗
HabitatAgent: An End-to-End Multi-Agent System for Housing Consultationcs.LG

HabitatAgent offers a multi-agent system for transparent housing consultation.

problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.
Housing ConsultationMulti-Agent SystemEnd-to-EndTransparencyMulti-Constraint Handling
2026-04-01abs ↗pdf ↗
FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systemscs.CL

Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.

problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
hallucination detectionfinancial QAknowledge graphAI reliabilitySEC filings
2026-03-11abs ↗pdf ↗