Prof. Dr. Jens Lehmann
Principal Scientist, Amazon AGI (Artificial General Intelligence)
Honorary Professor at TU Dresden
Member of InfAI
Offices
Amazon
Jens Lehmann
Amazon Development Center Germany GmbH
Großenhainer Str. 5a
01097 Dresden
InfAI
Jens Lehmann c/o Nadine Jochimsen
Institut für Angewandte Informatik (InfAI)
Goerdelerring 9
04109 Leipzig
Top Publications
Bridging language models and knowledge graphs with controlled natural languages Journal Article
In: Knowl. Based Syst., vol. 337, pp. 115405, 2026.
Advancing Safe Mechanical Ventilation Using Offline RL with Hybrid Actions and Clinically Aligned Rewards Proceedings Article
In: Fortieth AAAI Conference on Artificial Intelligence, Thirty-Eighth Conference on Innovative Applications of Artificial Intelligence, Sixteenth Symposium on Educational Advances in Artificial Intelligence, AAAI 2026, Singapore, January 20-27, 2026, pp. 39548–39557, AAAI Press, 2026.
Optimizing Prompts Efficiently with Iterative Determinantal Point Processes Proceedings Article
In: Proceedings of the 18th International Conference on Agents and Artificial Intelligence, ICAART 2026 - Volume 3, Marbella, Spain, March 5-7, 2026, pp. 2159–2170, SCITEPRESS, 2026.
Test-Time Confidence Quantification Using Q-Ensembles for Offline RL Journal Article
In: IEEE Access, vol. 14, pp. 61867–61880, 2026.
Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation Proceedings Article
In: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026, pp. 41311–41334, Association for Computational Linguistics, 2026.
Graph Regularized Deep Symmetric Nonnegative Matrix Factorization Journal Article
In: Knowl. Based Syst., vol. 350, pp. 116556, 2026.
Graph Query Generation with Constraint-Guided Large Language Agents Proceedings Article
In: 42nd IEEE International Conference on Data Engineering, ICDE 2026, Montreal, QC, Canada, May 4-8, 2026, pp. 3813–3819, IEEE, 2026.
CLEP (Version 0.0.6) Miscellaneous
urlhttps://doi.org/10.5281/zenodo.17433821, 2025, (Accessed on YYYY-MM-DD.).
CLEP (Version 0.0.5) Miscellaneous
urlhttps://doi.org/10.5281/zenodo.15038203, 2025, (Accessed on YYYY-MM-DD.).
CLEP (Version 0.0.5) Miscellaneous
urlhttps://doi.org/10.5281/zenodo.15113734, 2025, (Accessed on YYYY-MM-DD.).
SimE: A Knowledge Graph Embedding Model to Encode Self-Similar Structures Through Algebraic and Geometric Transformations Journal Article
In: IEEE Access, vol. 13, pp. 74701–74719, 2025.
BALI - A Benchmark for Accelerated Language Model Inference Journal Article
In: IEEE Access, vol. 13, pp. 98976–98989, 2025.
ICU Mechanical Ventilation Data Imputation Proceedings Article
In: Artificial Intelligence Applications and Innovations - 21st IFIP WG 12.5 International Conference, AIAI 2025, Limassol, Cyprus, June 26-29, 2025, Proceedings, Part III, pp. 140–154, Springer, 2025.
Learning Temporal Knowledge Graphs via Time-Sensitive Graph Attention Journal Article
In: IEEE Access, vol. 13, pp. 178517–178526, 2025.
ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation Proceedings Article
In: The Semantic Web - ISWC 2025 - 24th International Semantic Web Conference, Nara, Japan, November 2-6, 2025, Proceedings, Part I, pp. 290–308, Springer, 2025.
CLEP (Version 0.0.4) Miscellaneous
urlhttps://doi.org/10.5281/zenodo.12743058, 2024, (Accessed on YYYY-MM-DD.).
CLEP (Version 0.0.3) Miscellaneous
urlhttps://doi.org/10.5281/zenodo.10830122, 2024, (Accessed on YYYY-MM-DD.).
Knowledge GeoGebra: Leveraging Geometry of Relation Embeddings in Knowledge Graph Completion Proceedings Article
In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy, pp. 9832–9842, ELRA and ICCL, 2024.
Deep Nonnegative Matrix Factorization with Joint Global and Local Structure Preservation Journal Article
In: Expert Syst. Appl., vol. 249, pp. 123645, 2024.
Large Language Models for Scientific Question Answering: An Extensive Analysis of the SciQA Benchmark Proceedings Article
In: The Semantic Web - 21st International Conference, ESWC 2024, Hersonissos, Crete, Greece, May 26-30, 2024, Proceedings, Part I, pp. 199–217, Springer, 2024.
Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources Journal Article
In: Trans. Assoc. Comput. Linguistics, vol. 12, pp. 786–802, 2024.
A Self-Representation Learning Method for Unsupervised Feature Selection using Feature Space Basis Journal Article
In: Trans. Mach. Learn. Res., vol. 2024, 2024.
MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources Proceedings Article
In: Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pp. 16110–16121, Association for Computational Linguistics, 2024.
Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding Proceedings Article
In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pp. 4225–4237, Association for Computational Linguistics, 2024.
REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking Proceedings Article
In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track, NAACL 2024, Mexico City, Mexico, June 16-21, 2024, pp. 119–130, Association for Computational Linguistics, 2024.
Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources Journal Article
In: Trans. Assoc. Comput. Linguistics, vol. 12, pp. 786–802, 2024.
X-Vent: ICU Ventilation with Explainable Model-Based Reinforcement Learning Proceedings Article
In: 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), pp. 4719–4726, IOS Press, 2024.
Investigating Multilingual Instruction-Tuning: Do Polyglot Models Demand for Multilingual Instructions? Proceedings Article
In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 16-16, 2024, pp. 20829–20855, Association for Computational Linguistics, 2024.
A Study of LFT Embeddings in the Second Order Clifford Algebra Cl(R(^2),textordmasculine) Journal Article
In: IEEE Access, vol. 12, pp. 187741–187755, 2024.
Evaluating Large Language Model Literature Reviews in Interdisciplinary Science: A Systems Biology Perspective Proceedings Article
In: Joint Proceedings of Posters, Demos, Workshops, and Tutorials of the 24th International Conference on Knowledge Engineering and Knowledge Management (EKAW-PDWT 2024) co-located with 24th International Conference on Knowledge Engineering and Knowledge Management (EKAW 2024), Amsterdam, Netherlands, November 26-28, 2024, CEUR-WS.org, 2024.
Assessing Large Language Models for SPARQL Query Generation in Scientific Question Answering Proceedings Article
In: Proceedings of the Special Session on Harmonising Generative AI and Semantic Web Technologies (HGAIS 2024) co-located with the 23rd International Semantic Web Conference (ISWC 2024), Baltimore, Maryland, November 13, 2024, CEUR-WS.org, 2024.
Benchmarking in Neuro-Symbolic AI Proceedings Article
In: Learning and Reasoning - 4th International Joint Conference on Learning and Reasoning, IJCLR 2024, and 33rd International Conference on Inductive Logic Programming, ILP 2024, Nanjing, China, September 20-22, 2024, Proceedings, pp. 238–249, Springer, 2024.
Temporal relevance for representing learning over temporal knowledge graphs Journal Article
In: Semantic Web, vol. 15, no. 6, pp. 2695–2711, 2024.
Toward the Multilingual Semantic Web: Multilingual Ontology Matching and Assessment Journal Article
In: IEEE Access, vol. 11, pp. 8581–8599, 2023.
ExPAD: An Explainable Distributed Automatic Anomaly Detection Framework over Large KGs Proceedings Article
In: 17th IEEE International Conference on Semantic Computing, ICSC 2023, Laguna Hills, CA, USA, February 1-3, 2023, pp. 204–211, IEEE, 2023.
Geometric Algebra Based Embeddings for Static and Temporal Knowledge Graph Completion Journal Article
In: IEEE Trans. Knowl. Data Eng., vol. 35, no. 5, pp. 4838–4851, 2023.
LogicENN: A Neural Based Knowledge Graphs Embedding Model With Logical Rules Journal Article
In: IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 6, pp. 7050–7062, 2023.
SimE4KG: Distributed and Explainable Multi-Modal Semantic Similarity Estimation for Knowledge Graphs Journal Article
In: Int. J. Semantic Comput., vol. 17, no. 2, pp. 199–221, 2023.
Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories Proceedings Article
In: Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 7165–7179, Association for Computational Linguistics, 2023.
Efficient computation of comprehensive statistical information of large OWL datasets: a scalable approach Journal Article
In: Enterp. Inf. Syst., vol. 17, no. 7, 2023.
Direct Fact Retrieval from Knowledge Graphs without Entity Linking Proceedings Article
In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, pp. 10038–10055, Association for Computational Linguistics, 2023.
Distinct Geometrical Representations for Temporal and Relational Structures in Knowledge Graphs Proceedings Article
In: Machine Learning and Knowledge Discovery in Databases: Research Track - European Conference, ECML PKDD 2023, Turin, Italy, September 18-22, 2023, Proceedings, Part III, pp. 601–616, Springer, 2023.
Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering Proceedings Article
In: ECAI 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Kraków, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems (PAIS 2023), pp. 1348–1356, IOS Press, 2023.
Retention is All You Need Proceedings Article
In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United Kingdom, October 21-25, 2023, pp. 4752–4758, ACM, 2023.
Integrating Knowledge Graph Embeddings and Pre-trained Language Models in Hypercomplex Spaces Proceedings Article
In: The Semantic Web - ISWC 2023 - 22nd International Semantic Web Conference, Athens, Greece, November 6-10, 2023, Proceedings, Part I, pp. 388–407, Springer, 2023.
INVITE: a Testbed of Automatically Generated Invalid Questions to Evaluate Large Language Models for Hallucinations Proceedings Article
In: Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pp. 5422–5429, Association for Computational Linguistics, 2023.
mReFinED: An Efficient End-to-End Multilingual Entity Linking System Proceedings Article
In: Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pp. 15080–15089, Association for Computational Linguistics, 2023.
Anomaly Detection for Numerical Literals in Knowledge Graphs: A Short Review of Approaches Proceedings Article
In: Sixth IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023, Laguna Hills, CA, USA, September 25-27, 2023, pp. 46–53, IEEE, 2023.
Spatial concept learning and inference on geospatial polygon data Journal Article
In: Knowl. Based Syst., vol. 241, pp. 108233, 2022.
DistAD: A Distributed Generic Anomaly Detection Framework over Large KGs Proceedings Article
In: 16th IEEE International Conference on Semantic Computing, ICSC 2022, Laguna Hills, CA, USA, January 26-28, 2022, pp. 243–250, IEEE, 2022.
Recent Blog Posts
AI Can Now Adapt to New Tasks. Can It Also Improve Itself?
Large language models now adapt to new tasks, as the ARC-AGI-3 benchmark shows. In a new study, we asked whether they can also improve their own harness for this benchmark. They build harnesses well, but their improvements rarely transfer to games they have not seen. We discuss why and what that means for AI research.
Beyond Boundaries: A Human-like Approach for Question Answering over Structured and Unstructured Information Sources
Title Together with my co-authors, we are excited to share our work on an easy [...]
The Next 66 Years of Artificial Intelligence
[Disclosure: The post below reflects a personal opinion and is not linked in [...]

