We present FinLLaMA-RAG, a Retrieval-Augmented Generation (RAG) framework built on LLaMA 3 to address complex document-level question answering. The model integrates dense retrieval, contextual fusion, and multi-hop reasoning to extract accurate, coherent answers from long and cross-referenced documents. Designed with high-stakes applications in mind, FinLLaMA-RAG supports automated tax compliance, financial fraud investigation, and regulatory reporting. Through joint optimization of retrieval and generation, it achieves strong results across several financial QA datasets. This work contributes to the development of explainable and reliable AI tools for financial and policy-oriented document analysis.

This paper presents a novel Retrieval-Augmented Generation (RAG) framework tailored for complex question answering tasks, addressing challenges in multi-hop reasoning and contextual understanding across lengthy documents. Built upon LLaMA 3, the framework integrates a dense retrieval module with advanced context fusion and multi-hop reasoning mechanisms, enabling more accurate and coherent response generation. A joint optimization strategy combining retrieval likelihood and generation cross-entropy improves the model's robustness and adaptability. Experimental results show that the proposed system outperforms existing retrieval-augmented and generative baselines, confirming its effectiveness in delivering precise, contextually grounded answers.

Credit scoring is vital in the financial industry,assessing the risk of lending to credit card applicants. Traditionalcredit scoring methods face challenges with large datasets anddata imbalance between creditworthy and non-creditworthy applicants.This paper introduces an advanced machine learningand deep learning framework to improve the accuracy andreliability of credit card approval predictions. We utilized extensivedatasets of user application records and credit history,implementing a comprehensive preprocessing strategy, featureengineering, and model integration. Our methodology combinesneural networks with an ensemble of base models, includinglogistic regression, support vector machines, k-nearest neighbors,decision trees, random forests, and gradient boosting. The ensembleapproach addresses data imbalance using Synthetic MinorityOver-sampling Technique (SMOTE) and mitigates overfittingrisks. Experimental results show that our integrated modelsurpasses traditional single-model approaches in precision, recall,F1-score, AUC, and Kappa, providing a robust and scalablesolution for credit card approval predictions. This researchunderscores the potential of advanced machine learning techniquesto transform credit risk assessment and financial decisionmaking.

With the rapid growth of financial data, extracting accurate and contextually relevant information remains a challenge. Existing financial question-answering (QA) models struggle with domain-specific terminology, long-document processing, and answer consistency. To address these issues, this paper proposes the Intelligent-Aware Transformer (IAT), a financial QA system based on GLM4-9B-Chat, integrating a multi-level information aggregation framework. The system employs a Financial-Specific Attention Mechanism (FSAM) to enhance focus on key financial terms, a Dynamic Context Embedding Layer (DCEL) to improve long-document processing, and a Hierarchical Answer Aggregator (HAA) to ensure response coherence. Additionally, Knowledge-Augmented Textual Entailment (KATE) strengthens the model's generalization by inferring implicit financial knowledge. Experimental results demonstrate that IAT surpasses existing models in financial QA tasks, exhibiting superior adaptability in long-text comprehension and domain-specific reasoning. Future work will explore computational optimizations, advanced knowledge integration, and broader financial applications.