← Go back

TRR 318 (Phase 2)

Funded project (January 2026 - June 2029)

TRR 318 "Constructing Explainability"

About the project

The scope of the EU right to explanation has fueled the need to improve eXplainable Artificial Intelligence capacities aiming at strengthening the rights of individuals affected by AI-based recommendations. Among other purposes, explanations serve the right to contest an AI output and protect humans from being left out of control. However, explanations can only be functional if they are relevant. Yet, the current state of the art in XAI, is criticized for being driven by the requirements of developers rather than those of users (explainees). A key challenge is, thus, to make an explanation relevant for a particular explainee.

For the first funding period, TRR 318 proposed taking co-constructive interaction as an approach in XAI. We carried out theoretical and empirical basic research to understand the explanation processes and the involvement of explainees in human–human and human–AI interactions. We obtained insights into how explanatory dialogs are structured and unfold, and how users can be modeled to adapt explanations. Building on these insights, we have developed first XAI systems that involve the users: These interact co-constructively and adapt the explanation process incrementally. We further asked whether and in what situations users care about understanding AI’s function and outputs. Our results show that users’ explanatory needs are diverse and change dynamically.

Our research on the explainees’ active involvement in the explanation process and the relevant social aspects builds a strong foundation for the paradigm of sXAI (social XAI). We position ourselves as pushing explainable AI toward the development of explaining AI systems that provide an environment – a context that emerges during interaction – in which users can exercise their agency and build knowledge.

For the second funding period, we recognize that explanations need to be assessed within the context of explaining. Therefore, we will focus on the relevance of explanations and endow explaining algorithms with the ability to proactively and jointly construct a shared context and establish the relevant factors together with the explainee. Our innovative proposal is that the context itself is co-constructed as part of the interaction. Driven by AI’s growing ubiquity, our aim is to develop context-aware XAI systems that can co-construct the relevant context incrementally with the user both in and from an interaction. Therefore, we are extending our sXAI approach with a systematization into four types of contexts guiding us toward more relevant, flexible, and versatile XAI applications in contrast to current technology.

In the long term, we envision investigating autonomous co-constructive XAI in the real world to gain insights into how human interlocutors (co-)adapt their behavior in co-constructive sociotechnical settings, thereby generating novel practices. These insights will complement our theoretical work concerned with a critical reflection on co-construction as a process.

Funding program

Deutsche Forschungsgemeinschaft (DFG, German Research Foundation): TRR 318/3 2026 – 438445824

Publications

MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA

By Nikit Srivastava, Daniel Vollmers, René Speck, Nikolaos Karalis, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

Knowledge Engineering and Knowledge Management (EKAW 2026), 2027, #inproceedings

ToT4ES: Tree of Thought for Entity Summarization

By Asep Fajar Firmansyah, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

EKAW 2026, 2026, #inproceedings

Rethinking Explanations: Formalizing Contrast in Description Logics

By Yasir Mahmood, Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Balram Tiwari

Explainable Artificial Intelligence - Fourth World Conference, xAI 2026, Proceedings, 2026, #inproceedings

MoE--LoRA Methods for Multilingual Adaptation: A Systematic Empirical Study

By Nikit Srivastava, Joel Dag, René Speck, Axel-Cyrille Ngonga Ngomo

EACL 2027 (Findings), 2026, #inproceedings

ATLAS: Adaptive Attribute-Aware Post-Hoc Alignment of Knowledge Graph Embeddings

By Duygu Ekinci Birol, N'Dah Jean Kouagou, Mohamed Ahmed Sherif, Axel-Cyrille Ngonga Ngomo

IEEE International Conference on Data Mining (ICDM) 2026, 2026, #inproceedings

ABox Abduction for Inconsistent Knowledge Bases under Repair Semantics

By Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan

Proceedings of KR 2026, 2026, #inproceedings

ASTRA: Adaptive Structure-Aware Post-Hoc Alignment of Knowledge Graph Embeddings

By Duygu Ekinci Birol, N'Dah Jean Kouagou, Shivam Sharma, Albert Khomich, Mohamed Ahmed Sherif, Axel-Cyrille Ngonga Ngomo

ECML PKDD 2026, 2026, #inproceedings

Can You Tell the Difference? Contrastive Explanations for ABox Entailments

By Patrick Koopmann, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, Balram Tiwari

Proceedings of the AAAI Conference on Artificial Intelligence, 2026, #article

Ontology-Aware Prompting for Knowledge Graph Construction from Text

By Balram Tiwari, Italo Oliveira, Asep Fajar Firmansyah, Hamada M. Zahera, Frank Hopfgartner, Axel-Cyrille Ngonga Ngomo

SEMANTiCS 2026, 2026, #inproceedings

SECEA: Self Configuring Matcher Framework For Entity And Knowledge Graph Alignment

By Alexander Becker, Axel-Cyrille Ngonga Ngomo, Mohamed Ahmed Sherif

The Semantic Web -- ISWC 2026, 2026, #inproceedings

Structure-Aware Encodings of Argumentation Properties for Clique-width

By Yasir Mahmood, Markus Hecher, Johanna Groven, Johannes K. Fichte

Proceedings of the AAAI Conference on Artificial Intelligence, 2026, #article

Diversity of Extensions in Abstract Argumentation

By Johannes K. Fichte, Markus Hecher, Yasir Mahmood, Zhengjun Wang

Proceedings of IJCAI 2026, 2026, #inproceedings

Beyond CUDA OOM: Sharded Training for the Entire DBpedia and Wikidata Knowledge Graph Embeddings

By Shivam Sharma, Albert Khomich, Rupesh Sapkota, Caglar Demir, Axel-Cyrille Ngonga Ngomo, Mohamed Ahmed Sherif

2026 IEEE International Conference on Big Data (BigData), 2026, #inproceedings

Facets in Argumentation: A Formal Approach to Argument Significance

By Johannes Klaus Fichte, Nicolas Fröhlich, Markus Hecher, Victor Lagerkvist, Yasir Mahmood, Arne Meier, Jonathan Persson

The 34th International Joint Conference on Artificial Intelligence, IJCAI 2025, 2025, #inproceedings

Dung's Argumentation Framework: Unveiling the Expressive Power with Inconsistent Databases

By Yasir Mahmood, Markus Hecher, Axel-Cyrille Ngonga Ngomo

AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, 2025, #inproceedings

ANTS: Abstractive Entity Summarization in Knowledge Graphs

By Asep Fajar Firmansyah, Hamada M. Zahera, Mohamed Ahmed Sherif, Diego Moussallem, Axel-Cyrille Ngonga Ngomo

The Semantic Web – 22nd International Conference, ESWC 2025, Portoroz, Slovenia, June 1-5, 2025, Proceedings, 2025, #inproceedings

Why not? Developing ABox Abduction Beyond Repairs

By Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan

Proceedings of the 38th International Workshop on Description Logics - DL 2025, Opole, Poland, September 3-6, 2025, 2025, #inproceedings

Multilingual Relation Extraction: A Survey

By Manzoor Ali, René Speck, Hamada M. Zahera, Muhammad Saleem, Diego Moussallem, Axel-Cyrille Ngonga Ngomo

IEEE Access, 2025, #article

ROCES: Robust Class Expression Synthesis in Description Logics via Iterative Sampling

By N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 2024, #inproceedings

AutoCL: AutoML for Concept Learning

By Jiayi Li, Sheetal Satheesh, Stefan Heindorf, Diego Moussallem, René Speck, Axel-Cyrille Ngonga Ngomo

Explainable Artificial Intelligence, 2024, #inproceedings

IndEL: Indonesian Entity Linking Benchmark Dataset for General and Specific Domains

By Ria Hari Gusmita, Muhammad Faruq, Diego Mousallem, Axel-Cyrille Ngonga Ngomo

NLDB, 2024, #inproceedings

Rejection in Abstract Argumentation: Harder Than Acceptance?

By Johannes Klaus Fichte, Markus Hecher, Yasir Mahmood, Arne Meier

ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain - Including 13th Conference on Prestigious Applications of Intelligent Systems (PAIS 2024), 2024, #inproceedings

Quantitative Claim-Centric Reasoning in Logic-Based Argumentation

By Markus Hecher, Yasir Mahmood, Arne Meier, Johannes Schmidt

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24, 2024, #inproceedings

Enhancing Relation Extraction Through Augmented Data: Large Language Models Unleashed

By Manzoor Ali, Muhammad Sohail Nisar, Muhammad Saleem, Diego Moussallem, Axel-Cyrille Ngonga Ngomo

NLDB24, 2024, #inproceedings

Universal Knowledge Graph Embeddings

By N'Dah Jean Kouagou, Caglar Demir, Hamada M. Zahera, Adrian Wilke, Stefan Heindorf, Jiayi Li, Axel-Cyrille Ngonga Ngomo

Companion Proceedings of the ACM on Web Conference 2024, 2024, #inproceedings

Enhancing Answers Verbalization using Large Language Models

By Daniel Vollmers, Parth Sharma, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

SEMANTiCS2024, 2024, #inproceedings

UniQ-Gen: Unified Query Generation across Multiple Knowledge Graphs

By Daniel Vollmers, Nikit Srivastava, Hamada M. Zahera, Diego Moussallem, Axel-Cyrille Ngonga Ngomo

EKAW 2024, 2024, #inproceedings

Computing Repairs Under Functional and Inclusion Dependencies via Argumentation

By Yasir Mahmood, Jonni Virtema, Timon Barlag, Axel-Cyrille Ngonga Ngomo

Foundations of Information and Knowledge Systems - 13th International Symposium, FoIKS 2024, Sheffield, UK, Proceedings, 2024, #inproceedings

ESLM: Improving Entity Summarization by Leveraging Language Models

By Asep Fajar Firmansyah, Diego Mousallem, Axel-Cyrille Ngonga Ngomo

The Semantic Web, 2024, #inproceedings

Neural Class Expression Synthesis (Extended Abstract)

By N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo

NeSy 2023, 17th International Workshop on Neural-Symbolic Learning and Reasoning, Certosa di Pontignano, Siena, Italy, 2023, #inproceedings

Learning Permutation-Invariant Embeddings for Description Logic Concepts

By Caglar Demir, Axel-Cyrille Ngonga Ngomo

Advances in Intelligent Data Analysis XXI: 21st International Symposium on Intelligent Data Analysis, IDA 2023, Louvain-la-Neuve, Belgium, April 12--14, 2023, Proceedings, 2023, #inproceedings

Neuro-Symbolic Class Expression Learning

By Caglar Demir, Axel-Cyrille Ngonga Ngomo

The 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023, 2023, #inproceedings

Neural Class Expression Synthesis in ALCHIQ(D)

By N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo

Machine Learning and Knowledge Discovery in Databases, 2023, #inproceedings

Neural Class Expression Synthesis

By N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo

The Semantic Web - 20th International Conference, ESWC 2023, Hersonissos, Crete, Greece, May 28 - June 1, 2023, Proceedings, 2023, #inproceedings

Quantitative Reasoning and Structural Complexity for Claim-Centric Argumentation

By Johannes Klaus Fichte, Markus Hecher, Yasir Mahmood, Arne Meier

The 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023, 2023, #inproceedings

Clifford Embeddings – A Generalized Approach for Embedding in Normed Algebras

By Caglar Demir, Axel-Cyrille Ngonga Ngomo

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2023, 2023, #inproceedings

MARS: Multi-hop Adaptive Retrieval and SPARQL Generation for KGQA

By Nikit Srivastava, Daniel Vollmers, René Speck, Nikolaos Karalis, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

Knowledge Engineering and Knowledge Management (EKAW 2026), 2027, #inproceedings

ToT4ES: Tree of Thought for Entity Summarization

By Asep Fajar Firmansyah, Hamada M. Zahera, Axel-Cyrille Ngonga Ngomo

EKAW 2026, 2026, #inproceedings

Rethinking Explanations: Formalizing Contrast in Description Logics

By Yasir Mahmood, Arnab Sharma, Axel-Cyrille Ngonga Ngomo, Balram Tiwari

Explainable Artificial Intelligence - Fourth World Conference, xAI 2026, Proceedings, 2026, #inproceedings

MoE--LoRA Methods for Multilingual Adaptation: A Systematic Empirical Study

By Nikit Srivastava, Joel Dag, René Speck, Axel-Cyrille Ngonga Ngomo

EACL 2027 (Findings), 2026, #inproceedings

ATLAS: Adaptive Attribute-Aware Post-Hoc Alignment of Knowledge Graph Embeddings

By Duygu Ekinci Birol, N'Dah Jean Kouagou, Mohamed Ahmed Sherif, Axel-Cyrille Ngonga Ngomo

IEEE International Conference on Data Mining (ICDM) 2026, 2026, #inproceedings