Composable Building Blocks for Controllable and Transparent Interactive AI Systems

• URL: http://arxiv.org/abs/2506.02262v1
• Date: Mon, 02 Jun 2025 21:10:51 GMT
• Title: Composable Building Blocks for Controllable and Transparent Interactive AI Systems
• Authors: Sebe Vanbrabant, Gustavo Rovelo Ruiz, Davy Vanacken,
• Abstract summary: Black box problem of AI models continues to spread throughout interactive system as a whole.<n>XAI techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models.<n>We propose an approach to represent interactive systems as sequences of structural building blocks.
• Score: 0.8192907805418583
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.

Related papers

• AI Flow: Perspectives, Scenarios, and Approaches [51.38621621775711]
  We introduce AI Flow, a framework that integrates cutting-edge IT and CT advancements.<n>First, device-edge-cloud framework serves as the foundation, which integrates end devices, edge servers, and cloud clusters.<n>Second, we introduce the concept of familial models, which refers to a series of different-sized models with aligned hidden features.<n>Third, connectivity- and interaction-based intelligence emergence is a novel paradigm of AI Flow.
  arXiv  Detail & Related papers  (2025-06-14T12:43:07Z)
• Explanation-Driven Interventions for Artificial Intelligence Model Customization: Empowering End-Users to Tailor Black-Box AI in Rhinocytology [3.4705962607086973]
  This article presents a novel End-User Development (EUD) approach for black-box AI models.<n>The proposed method advances Human-Centered AI (HCAI), promoting a symbiotic relationship between humans and adaptive, user-tailored AI systems.
  arXiv  Detail & Related papers  (2025-04-07T08:44:48Z)
• AI Automatons: AI Systems Intended to Imitate Humans [54.19152688545896]
  There is a growing proliferation of AI systems designed to mimic people's behavior, work, abilities, likenesses, or humanness.<n>The research, design, deployment, and availability of such AI systems have prompted growing concerns about a wide range of possible legal, ethical, and other social impacts.
  arXiv  Detail & Related papers  (2025-03-04T03:55:38Z)
• Characterizing and modeling harms from interactions with design patterns in AI interfaces [0.19116784879310028]
  We argue that design features of interfaces with adaptive AI systems can have cascading impacts, driven by feedback loops. We propose Design-Enhanced Control of AI systems (DECAI) to structure and facilitate impact assessments of AI interface designs.
  arXiv  Detail & Related papers  (2024-04-17T13:30:45Z)
• Towards a general framework for improving the performance of classifiers using XAI methods [0.0]
  This paper proposes a framework for automatically improving the performance of pre-trained Deep Learning (DL) classifiers using XAI methods. We will call auto-encoder-based and encoder-decoder-based, and discuss their key aspects.
  arXiv  Detail & Related papers  (2024-03-15T15:04:20Z)
• Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning [50.47568731994238]
  Key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL) This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies.
  arXiv  Detail & Related papers  (2023-12-22T17:57:57Z)
• Online Learning and Planning in Cognitive Hierarchies [10.28577981317938]
  We extend an existing formal framework to model complex integrated reasoning behaviours of robotic systems. New framework allows for a more flexible modelling of the interactions between different reasoning components.
  arXiv  Detail & Related papers  (2023-10-18T23:53:51Z)
• A Reference Architecture for Designing Foundation Model based Systems [28.826700360670515]
  There is a broad consensus that foundations models will be the fundamental building blocks for future AI systems. incorporating foundations models into AI systems raises significant concerns about responsible and safe AI. The paper proposes a pattern-oriented reference architecture for designing responsible foundation-model-based systems.
  arXiv  Detail & Related papers  (2023-04-13T05:01:03Z)
• Conceptual Modeling and Artificial Intelligence: Mutual Benefits from Complementary Worlds [0.0]
  We are interested in tackling the intersection of the two, thus far, mostly isolated approached disciplines of CM and AI. The workshop embraces the assumption, that manifold mutual benefits can be realized by i) investigating what Conceptual Modeling (CM) can contribute to AI, and ii) the other way around.
  arXiv  Detail & Related papers  (2021-10-16T18:42:09Z)
• A User-Centred Framework for Explainable Artificial Intelligence in Human-Robot Interaction [70.11080854486953]
  We propose a user-centred framework for XAI that focuses on its social-interactive aspect. The framework aims to provide a structure for interactive XAI solutions thought for non-expert users.
  arXiv  Detail & Related papers  (2021-09-27T09:56:23Z)
• Towards an Interface Description Template for AI-enabled Systems [77.34726150561087]
  Reuse is a common system architecture approach that seeks to instantiate a system architecture with existing components. There is currently no framework that guides the selection of necessary information to assess their portability to operate in a system different than the one for which the component was originally purposed. We present ongoing work on establishing an interface description template that captures the main information of an AI-enabled component.
  arXiv  Detail & Related papers  (2020-07-13T20:30:26Z)
• Distributed and Democratized Learning: Philosophy and Research Challenges [80.39805582015133]
  We propose a novel design philosophy called democratized learning (Dem-AI) Inspired by the societal groups of humans, the specialized groups of learning agents in the proposed Dem-AI system are self-organized in a hierarchical structure to collectively perform learning tasks more efficiently. We present a reference design as a guideline to realize future Dem-AI systems, inspired by various interdisciplinary fields.
  arXiv  Detail & Related papers  (2020-03-18T08:45:10Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.