Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI

TL;DR

This paper introduces a human-centered explainable AI architecture for financial sentiment analysis that combines persistent explanation storage, multi-method explanation triangulation, and automated faithfulness evaluation.

Contribution

It presents a novel architecture integrating persistent explanation artifacts, multi-method comparison via RAG, and automated faithfulness checks for trustworthy financial AI.

Findings

Structured storage of explanations enables semantic retrieval and system robustness.

Multi-method explanation comparison improves user assessment of explanation robustness.

Automated faithfulness checks reduce hallucinations and improve explanation attribution.

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.