Bridging Human Cognition and AI: A Framework for Explainable Decision-Making Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908515643162624 |
|---|---|
| author | Jean, N. Pera, G. Le |
| author_facet | Jean, N. Pera, G. Le |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Human Cognition and AI: A Framework for Explainable Decision-Making Systems Jean, N. Pera, G. Le Statistical Finance 62P20, 68T05, 62P20 I.2.7; G.3; H.5.m 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. |
| title | Bridging Human Cognition and AI: A Framework for Explainable Decision-Making Systems |
| topic | Statistical Finance 62P20, 68T05, 62P20 I.2.7; G.3; H.5.m |
| url | https://arxiv.org/abs/2509.02388 |