ReaLearn (Trustworthy AI Lab)

Welcome !

ReaLearn (Trustworthy AI Lab) is a research group at the AI So-Go-Chi (Convergence Knowledge) Center, Tohoku University, run by Teeradaj Racharak, aimed to address research questions lied in between pure (logic) reasoning and pure (machine) learning for Trustworthy AI.

At ReaLearn, our study covers two mainstreams of AI, namely, (1) Knowledge Representation and Reasoning (KRR) and (2) Machine Learning (ML). Our ultimate goal is to build AI systems that humans can trust! We welcome anyone who share common interests to join or collaborate with us.

Additional Useful Links

Mentoring plan for prospective and current researchers (including students)
- For some of our poster exhibitions, please visit the Showcase page.

Research Topics

KRR for Trustworthy AI, e.g.,
- Description Logic and Explanation for Ontology and Knowledge Graph applications
- Argumentation and Explanation for Practical Reasoning
- Human-friendly Explanation Formalisms
- Implementation of XAI system, e.g., Virtual Knowledge Graph
Integration of KRR and ML for Trustworthy AI, e.g.,
- Knowledge Graph Embedding (i.e. Knowledge Graph meets ML)
- Ontology Embedding (i.e. Ontology meets ML)
- Neural-symbolic Learning (i.e. Symbolic Reasoning meets ML)
- Argument Mining (i.e. Argumentation meets ML)
- Fairness, Accountability, and Transparency (FAccT)
- Knowledge-aware Machine Learning
Any topics involved the development of Trustable AI systems are always welcome!

For more details, please visit the Research page.

News and Highlights

(For all events in the past, see this page)

October 19, 2025: Our paper "PromptOps: Automated Tool for Testing Trustworthiness of LLMs" is accepted by APSEC 2025
October 15, 2025: Our paper "AI Literacy in Code: Identifying and Explaining ChatGPT-Generated Programs in Educational Settings" is accepted by Standards-Based AI Innovation for the Learning Ecosystem (Global Scientific Publishing)
October 12, 2025: Our paper "Generative AI for Requirements Engineering: A Systematic Literature Review" is accepted by In Software - Practice and Experience
September 25, 2025: Our paper "Benchmarking Temporal Reasoning: Can Large Language Models Navigate Time When Stories Refuse to Follow a Straight Line?" is accepted by FoRLM@NeurIPS 2025
September 25, 2025: Our paper "Time Tells: Temporal Event Ordering in Frontier LLMs — Performance, Limitations, and Human Comparison" is accepted by PACLIC 2025
September 25, 2025: Our paper "Natural Language Explanation in Code Clone Detection using LLM-based Post Hoc Explainer" is accepted by APSEC 2025
August 28, 2025: Our paper "JSimELHExplainer: A Robust JAVA Library for Explainable Semantic Similarity for ELH Description Logic Ontology" is accepted by ISWC 2025
August 28, 2025: Our paper "Human-Friendly Explanation for Ontology-based Concept Similarity: Design and Development" is accepted by ISWC 2025
August 27, 2025: Our paper "Find a Contrary in Hotel Reviews Booking.com: A Corpus Creation for Contrary Mining Task of Assumption-based Argument Mining" is accepted by DS&AI 2025
June 20, 2025: Our paper "GSR-Fusion: A Deep Multimodal Fusion Architecture for Robust Sign Language Recognition Using RGB, Skeleton, and Graph-based Modalities" is accepted by IEEE Access
May 25, 2025: Our paper "A New Integrated Neurosymbolic Approach for Crop-Yield Prediction Using Environmental Data and Satellite Imagery at Field Scale" is accepted by AI in Geosciences
April 27, 2025: Our paper "Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning" is accepted by NLDB 2025

For more details, please visit the Events & News page or follow us on Twitter @ReaLearnPeople.

Page updated

Google Sites

Report abuse