Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918496510672896 |
|---|---|
| author | Makridis, Georgios Fatouros, Georgios Soldatos, John Katsis, George Kyriazis, Dimosthenis |
| author_facet | Makridis, Georgios Fatouros, Georgios Soldatos, John Katsis, George Kyriazis, Dimosthenis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11687 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI Makridis, Georgios Fatouros, Georgios Soldatos, John Katsis, George Kyriazis, Dimosthenis Artificial Intelligence 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. |
| title | Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.11687 |