mlsanityData to 14 Oct 2026

Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model

arXiv 2509.03527 ↗First posted 25 Aug 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

In the paper, we consider multilevel multitask analysis of cryptocurrency news using a fine-tuned Mistral 7B large language model with retrieval-augmented generation (RAG). On the first level of analytics, the fine-tuned model generates graph and text summaries with sentiment scores as well as JSON representations of summaries. Higher levels perform hierarchical stacking that consolidates sets of graph-based and text-based summaries as well as summaries of summaries into comprehensive reports. The combination of graph and text summaries provides complementary views of cryptocurrency news. The model is fine-tuned with 4-bit quantization using the PEFT/LoRA approach. The representation of cryptocurrency news as knowledge graph can essentially eliminate problems with large language model hallucinations. The obtained results demonstrate that the use of fine-tuned Mistral 7B LLM models for multilevel cryptocurrency news analysis can conduct informative qualitative and quantitative analytics, providing important insights.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 43 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

26 of 43 references.

References · 26

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  4. 20218-bit Optimizers via Block-wise Quantizationcited by 403
  5. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  6. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  7. 2023FinGPT: Open-Source Financial Large Language Modelscited by 253
  8. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  9. 2023Large Language Models on Graphs: A Comprehensive Surveycited by 192
  10. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  11. 2024Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answeringcited by 96
  12. 2023Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Surveycited by 92
14 more
  1. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  2. 2023ChatGPT Informed Graph Neural Network for Stock Movement Predictioncited by 41
  3. 2020Graph Enhanced Representation Learning for News Recommendationcited by 30
  4. 2024Knowledge Graphs, Large Language Models, and Hallucinations: An NLP Perspectivecited by 29
  5. 2024A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applicationscited by 17
  6. 2024Advancing Graph Representation Learning with Large Language Models: A Comprehensive Survey of Techniquescited by 16
  7. 2023Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Modelcited by 10
  8. 2024Large Language Model Enhanced Knowledge Representation Learning: A Surveycited by 7
  9. 2022Methods of Informational Trends Analytics and Fake News Detection on Twittercited by 6
  10. 2023Financial News Analytics Using Fine-Tuned Llama 2 GPT Modelcited by 6
  11. 2024Relation Extraction with Fine-Tuned Large Language Models in Retrieval Augmented Generation Frameworkscited by 6
  12. 2022Forming Predictive Features of Tweets for Decision-Making Supportcited by 5
  13. 2022Bitcoin Price Predictive Modeling Using Expert Correctioncited by 2
  14. 2025AI Approaches to Qualitative and Quantitative News Analytics on NATO Unitycited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Graph-Augmented Retrieval for Cross-Entity Financial Sentiment Analysis: A Comparative Study
  2. 2025CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
  3. 2025LLM-Powered Multi-Agent System for Automated Crypto Portfolio Management
  4. 2026Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)
  5. 2025An Adaptive Multi Agent Bitcoin Trading System
  6. 2026Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
  7. 2026PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting
  8. 2024Enhancing literature review with LLM and NLP methods. Algorithmic trading case