Paper: arXiv 2509.02388

Authors: N. Jean, G. Le Pera

Abstract

Explainability in AI and ML models is critical for fostering trust, ensuring accountability, and enabling informed decision making in high stakes domains. Yet this objective is often unmet in practice. This paper proposes a general purpose framework that bridges state of the art explainability techniques with Malle’s five category model of behavior explanation: Knowledge Structures, Simulation/Projection, Covariation, Direct Recall, and Rationalization. The framework is designed to be applicable across AI assisted decision making systems, with the goal of enhancing transparency, interpretability, and user trust. We demonstrate its practical relevance through real world case studies, including credit risk assessment and regulatory analysis powered by large language models (LLMs). By aligning technical explanations with human cognitive mechanisms, the framework lays the groundwork for more comprehensible, responsible, and ethical AI systems.

Complexity vs Empirical Score

  • Math Complexity: 1.5/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: The paper focuses on a conceptual framework bridging social theory (Malle’s model) with AI explainability, involving minimal advanced mathematics and no direct backtesting, datasets, or code, leaning towards theoretical discussion.

Research Flowchart

  flowchart TD
  A["<b>Research Goal</b><br>Bridge XAI techniques<br>with human cognition<br>for better trust & transparency"] --> B["<b>Methodology</b><br>Integrate Malle's 5-category<br>behavior explanation model"]
  B --> C["<b>Key Inputs</b><br>• Technical XAI methods<br>• Human cognitive models<br>• Domain datasets"]
  C --> D["<b>Computational Process</b><br>Framework alignment &<br>mapping across domains"]
  D --> E["<b>Key Outcomes</b><br>1. Enhanced transparency<br>2. Improved user trust<br>3. Responsible AI systems"]
  
  E --> F["<b>Case Studies</b><br>Credit Risk & LLM<br>Regulatory Analysis"]

Cited References (17)

  1. Machine Explanations and Human Understanding (2022) — link
  2. How the Mind Explains Behavior: Folk Explanations, Meaning, and Social Interaction (2004)
  3. ALibi: Algorithms for Explainability (2024) — link
  4. Qdrant: High-Performance Vector Search Engine (2024) — link
  5. AI Conversation Planning (2024) — link
  6. Responsible AI: Overview and Best Practices (2024) — link
  7. Explainability and Trust in AI (2024) — link
  8. Effect of Confidence and Explanation on Trust Calibration in AI-Assisted Decision Making (2020) — link
and 9 more
  1. Explainable Machine Learning in Credit Risk Management (2020) — link
  2. A Survey of Methods for Explaining Black Box Models (2018) — link
  3. Explainable AI in Credit Scoring Models (2024) — link
  4. Explainable Artificial Intelligence: A Systematic Review (2018) — link
  5. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (2019) — link
  6. Explainable AI in Finance: A Systematic Literature Review (2024) — link
  7. Explainable Automated Machine Learning for Credit Decisions: Enhancing Human Artificial Intelligence Collaboration in Financial Engineering (2024) — link
  8. Analyzing Machine Learning Models for Credit Scoring with Explainable AI and Optimizing Investment Decisions (2022) — link
  9. Machine Learning Approach for Credit Scoring (2020)

0 of 17 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.