The field of financial forecasting and decision-making is rapidly advancing with the development of innovative models and techniques that prioritize explainability and reliability. Recent research has focused on improving the transparency and trustworthiness of large language models (LLMs) in financial applications, such as stock movement prediction and credit risk assessment. Notable developments include the integration of LLMs with symbolic reasoning and probabilistic mechanisms to enhance interpretability and predictive performance. Furthermore, the use of techniques like SHAP and GroupSHAP has enabled the identification of influential features and the quantification of their contributions to predictions, leading to more informed decision-making. Overall, the field is moving towards the development of more transparent, reliable, and trustworthy AI systems for financial forecasting and decision-making. Noteworthy papers include RETuning, which proposes a method to enhance the prediction ability of LLMs in financial tasks, and H3M-SSMoEs, which introduces a novel hypergraph-based multimodal architecture for stock movement prediction. Additionally, the paper on Bayesian Network Fusion of Large Language Models for Sentiment Analysis demonstrates the effectiveness of probabilistic fusion for interpretable sentiment classification.
Advances in Explainable Financial Forecasting and Decision-Making
Sources
Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning
Towards Explainable Personalized Recommendations by Learning from Users' Photos
RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models
Framework for Machine Evaluation of Reasoning Completeness in Large Language Models For Classification Tasks
LLM-AR: LLM-powered Automated Reasoning Framework
LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs
Rule-Based Explanations for Retrieval-Augmented LLM Systems
P1GPT: a multi-agent LLM workflow module for multi-modal financial information analysis
GroupSHAP-Guided Integration of Financial News Keywords and Technical Indicators for Stock Price Prediction
Evaluating Large Language Models for Stance Detection on Financial Targets from SEC Filing Reports and Earnings Call Transcripts
Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier
H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts
Predicate Renaming via Large Language Models
Interpreting LLMs as Credit Risk Classifiers: Do Their Feature Explanations Align with Classical ML?
Towards Explainable and Reliable AI in Finance
Bayesian Network Fusion of Large Language Models for Sentiment Analysis