# Designing explainable artificial intelligence with active inference: A framework for transparent introspection and decision-making

arXiv: https://arxiv.org/abs/2306.04025 · HTML: https://mlsanity.com/paper/2306.04025/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 104 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 22 of 22)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [The Forgotten Margins of AI Ethics](https://mlsanity.com/paper/2205.04221/) (2022)
- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [Introspective Learning : A Two-Stage Approach for Inference in Neural Networks](https://mlsanity.com/paper/2209.08425/) (2022)
- [Deep Learning Models for Global Coordinate Transformations that Linearize PDEs](https://mlsanity.com/paper/1911.02710/) (2019)
- [A Transparency Index Framework for AI in Education](https://mlsanity.com/paper/2206.03220/) (2022)
- [Comparing Software Developers with ChatGPT: An Empirical Investigation](https://mlsanity.com/paper/2305.11837/) (2023)
- [Bayesian Mechanics for Stationary Processes](https://mlsanity.com/paper/2106.13830/) (2021)
- [The human-AI relationship in decision-making: AI explanation to support people on justifying their decisions](https://mlsanity.com/paper/2102.05460/) (2021)
- [AI Reliance and Decision Quality: Fundamentals, Interdependence, and the Effects of Interventions](https://mlsanity.com/paper/2304.08804/) (2023)
- [Awareness as inference in a higher-order state space](https://mlsanity.com/paper/1906.00728/) (2019)
- [Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study](https://mlsanity.com/paper/2008.02964/) (2020)
- [Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences](https://mlsanity.com/paper/2011.02338/) (2020)
- [Rejecting Cognitivism: Computational Phenomenology for Deep Learning](https://mlsanity.com/paper/2302.09071/) (2023)
- [The inner screen model of consciousness: applying the free energy principle directly to the study of conscious experience](https://mlsanity.com/paper/2305.02205/) (2023)
- [Efficient Interdependent Systems Recovery Modeling with DeepONets](https://mlsanity.com/paper/2206.10829/) (2022)
- [Enactive Artificial Intelligence: Subverting Gender Norms in Robot-Human Interaction](https://mlsanity.com/paper/2301.08741/) (2023)

## Built on by (most cited first, 6 of 6)

- [On efficient computation in active inference](https://mlsanity.com/paper/2307.00504/) (2023)
- [Resolving uncertainty on the fly: Modeling adaptive driving behavior as active inference](https://mlsanity.com/paper/2311.06417/) (2023)
- [On Predictive planning and counterfactual learning in active inference](https://mlsanity.com/paper/2403.12417/) (2024)
- [Deep hybrid models: infer and plan in a dynamic world](https://mlsanity.com/paper/2402.10088/) (2024)
- [A memory-based active inference model of DishBrain-like adaptive behaviour](https://mlsanity.com/paper/2508.06980/) (2025)
- [BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in Mobile Networks](https://mlsanity.com/paper/2602.14033/) (2026)

## Abstract (arXiv)

This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle. We first provide a brief overview of active inference, and in particular, of how it applies to the modeling of decision-making, introspection, as well as the generation of overt and covert actions. We then discuss how active inference can be leveraged to design explainable AI systems, namely, by allowing us to model core features of ``introspective'' processes and by generating useful, human-interpretable models of the processes involved in decision-making. We propose an architecture for explainable AI systems using active inference. This architecture foregrounds the role of an explicit hierarchical generative model, the operation of which enables the AI system to track and explain the factors that contribute to its own decisions, and whose structure is designed to be interpretable and auditable by human users. We outline how this architecture can integrate diverse sources of information to make informed decisions in an auditable manner, mimicking or reproducing aspects of human-like consciousness and introspection. Finally, we discuss the implications of our findings for future research in AI, and the potential ethical considerations of developing AI systems with (the appearance of) introspective capabilities.