Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI

2026-05-12

AI Summary

Current financial AI systems lack persistent, cross-verifiable, and dialogue-capable explanation mechanisms, hindering regulatory compliance and trustworthiness. This work proposes a human-centered explainable AI (XAI) framework tailored for financial sentiment analysis, which, for the first time, persistently stores explanations generated by multiple XAI techniques—such as LIME, occlusion, and saliency heatmaps—as structured metadata paired with natural language summaries. By integrating retrieval-augmented generation (RAG), the framework enables conversational fusion, traceability, and validation of multi-method explanations. Incorporating an explanatory triangulation mechanism and constrained prompt engineering within the EXTRA-BRAIN pipeline, our approach reduces hallucination rates by 36% and increases method citation accuracy by 73%, substantially enhancing the faithfulness and usability of generated explanations.

Abstract

Financial institutions increasingly require AI explanations that are persistent, cross-validated across methods, and conversationally accessible to human decision-makers. We present an architecture for human-centered explainable AI in financial sentiment analysis that combines three contributions. First, we treat XAI artifacts -- LIME feature attributions, occlusion-based word importance scores, and saliency heatmaps -- as persistent, searchable objects in distributed S3-compatible storage with structured metadata and natural-language summaries, enabling semantic retrieval over explanation history and automatic index reconstruction after system failures. Second, we enable multi-method explanation triangulation, where a retrieval-augmented generation (RAG) assistant compares and synthesizes results from multiple XAI methods applied to the same prediction, allowing users to assess explanation robustness through natural-language dialogue. Third, we evaluate the faithfulness of generated explanations using automated checks over grounding completeness, hallucinated claims, and method-attribution behavior. We demonstrate the architecture on an EXTRA-BRAIN financial sentiment analysis pipeline using FinBERT predictions and present evaluation results showing that constrained prompting reduces hallucination rate by 36\% and increases method-attribution citations by 73\% compared to naive prompting. We discuss implications for trustworthy, human-centered AI services in regulated financial environments.

Problem

• Explainable AI
• Financial AI
• Persistent Explanations
• Multi-Method Triangulation
• Conversational XAI

Innovation

• Explainable AI (XAI)
• multi-method triangulation
• retrieval-augmented generation (RAG)
• persistent explanation storage
• faithfulness evaluation