Machine Learning and Knowledge Engineering for Accountable and Verifiable Systems (AAAI-MAKE 2027)

Status: Symposium proposal in preparation. Pending AAAI acceptance (notification December 8, 2026).

As AI systems become more autonomous, interconnected, and embedded in consequential processes, establishing accountability and verifiability becomes a system-level challenge.

Machine learning (ML) provides adaptive capabilities but does not, by itself, make the knowledge, assumptions, decisions, and actions of complex systems inspectable. Knowledge engineering (KE) contributes explicit representations, ontologies, rules, constraints, provenance, and reasoning methods that can support traceability and verification. Their integration opens promising paths toward systems whose behavior can be justified, evaluated, and challenged.

MAKE 2027 will bring together researchers and practitioners to investigate how ML and KE can jointly support accountable and verifiable systems. The symposium welcomes formal and empirical approaches to verification; structured and interpretable representations; provenance and auditable reasoning; neurosymbolic and hybrid architectures; accountable agents and multi-agent systems; and human oversight in socio-technical environments. Rather than assuming that entire AI systems can be mathematically guaranteed, it will examine which properties, components, decisions, and claims can be verified, under what assumptions, and with what limitations.

Topics

MAKE 2027 serves as a platform to shape the next generation of hybrid AI by bridging the gap between machine learning and knowledge engineering. It emphasizes grounding AI agents in explicit semantics and structured knowledge to achieve reliable, explainable, and human-aligned intelligence. Relevant topics include, but are not limited to:

• Structured knowledge representations, ontologies, rules, constraints, and provenance for accountability
• Formal specification, autoformalization, verification, and runtime assurance of hybrid AI systems
• Empirical verification, testing, validation, benchmarking, and evidence of system behavior
• Traceable, interpretable, and auditable reasoning, decisions, and actions
• Neurosymbolic architectures combining learning, reasoning, and knowledge engineering
• Accountable LLM-based agents, multi-agent systems, tool use, and orchestration
• Human–AI interaction, human oversight, responsibility allocation, and governance mechanisms
• World models, situated or embodied intelligence, and verification in dynamic environments
• Applications, case studies, datasets, and challenges demonstrating accountability and verifiability

Format & Keynotes

The 2.5-day event will follow the traditional AAAI Spring Symposium Series schedule, with a diverse mixture of keynotes and morning and afternoon sessions.

Submission

Organizing Committee

Andreas Martin (primary contact, 📧), FHNW, Olten, Switzerland

Pedro A. Colon-Hernandez, Hypha, New York, NY, USA

Maaike de Boer, TNO, The Hague, Netherlands

Hans-Georg Fill, University of Fribourg, Switzerland

Aurona Gerber, Stellenbosch University, South Africa

Leilani H. Gilpin, University of California, Santa Cruz, CA, USA

Pascal Hitzler, Kansas State University, Manhattan, KS, USA

Jane Yung-jen Hsu, Chang Gung University, Taoyuan, Taiwan

Yen-Ling Kuo, University of Virginia, Charlottesville, VA, USA

Emanuele Laurenzi, FHNW, Olten, Switzerland

Alessandro Oltramari, Carnegie Bosch Institute, Pittsburgh, PA, USA

Thomas Schmid, Martin Luther University Halle-Wittenberg, Germany

Paulo Shakarian, Syracuse University, NY, USA

Reinhard Stolle, Fraunhofer IKS, München, Germany

Frank van Harmelen, Vrije Universiteit Amsterdam, Netherlands