Sonja Schimmler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Sonja Schimmler has a total of 151 co-authors. Here are the top co-authors by number of shared publications:
- Zongxiong Chen
Fraunhofer FOKUS, Berlin, Germany
10 shared publications - Manfred Hauswirth
Fraunhofer FOKUS, Berlin, Germany
7 shared publications Christian Schenk
Universität der Bundeswehr München, Germany, Neubiberg, Germany
5 shared publications- Uwe M. Borghoff
Institute for Software Technology, University of the Bundeswehr Munich, 85579 Neubiberg, Germany
5 shared publications - Bianca Wentzel
Fraunhofer FOKUS
4 shared publications - Fabian Kirstein
Fraunhofer FOKUS
3 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 461-473
Stop When It Matters: Detectability-Guided Microbenchmarking for Performance Regression Testing
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 461-473
Open AccessStop When It Matters: Detectability-Guided Microbenchmarking for Performance Regression Testing
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 959-964
Mixture of Orthogonal Decomposition for Semantically Generalisable Multimodal Deepfake Detection with Deepfake Manifold Disentanglement
Multimodal deepfakes have caused significant social issues and raised substantial security concerns. Generalisably detecting these multimodal deepfakes can be factored into two intricately intertwined subspaces, i.e., the semantic subspace and the forgery subspace. However, contemporary deepfake detection methods predominantly focus on pursuing generalisability within the forgery subspace, usually neglecting the influences of the semantic subspace. Additionally, existing deepfake detection algorithms categorise all deepfakes generated by various deepfake generation techniques under a single ''Fake'' category. This methodology may fail to account for the unique characteristics and extensive aspects of various deepfake generation techniques. To address all these challenges, we propose an innovative sparsely-gated Mixture of ORthogonal Decomposition (MoORD) deepfake detection model. Whilst the orthogonal decomposition parameter-efficient fine-tuning technique guarantees the generalisation performance of deepfake detection, the MoORD structure further enhances our model's semantic generalisability. Our MoORD model further learns product manifold representations to disentangle the ''Fake'' category into separate sub-categories of various deepfake generation techniques. Comprehensive experiments in 6 real-world deepfake detection datasets with 2 evaluation protocols demonstrate leading-edge generalisation performance in deepfake detection of our MoORD model over known and unknown semantic categories.
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 959-964
Open AccessMixture of Orthogonal Decomposition for Semantically Generalisable Multimodal Deepfake Detection with Deepfake Manifold Disentanglement
Multimodal deepfakes have caused significant social issues and raised substantial security concerns. Generalisably detecting these multimodal deepfakes can be factored into two intricately intertwined subspaces, i.e., the semantic subspace and the forgery subspace. However, contemporary deepfake detection methods predominantly focus on pursuing generalisability within the forgery subspace, usually neglecting the influences of the semantic subspace. Additionally, existing deepfake detection algorithms categorise all deepfakes generated by various deepfake generation techniques under a single ''Fake'' category. This methodology may fail to account for the unique characteristics and extensive aspects of various deepfake generation techniques. To address all these challenges, we propose an innovative sparsely-gated Mixture of ORthogonal Decomposition (MoORD) deepfake detection model. Whilst the orthogonal decomposition parameter-efficient fine-tuning technique guarantees the generalisation performance of deepfake detection, the MoORD structure further enhances our model's semantic generalisability. Our MoORD model further learns product manifold representations to disentangle the ''Fake'' category into separate sub-categories of various deepfake generation techniques. Comprehensive experiments in 6 real-world deepfake detection datasets with 2 evaluation protocols demonstrate leading-edge generalisation performance in deepfake detection of our MoORD model over known and unknown semantic categories.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2148-2160
LLM4JMH: Studying the Use of LLMs for Generating Java Performance Microbenchmarks
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2148-2160
Open AccessLLM4JMH: Studying the Use of LLMs for Generating Java Performance Microbenchmarks
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8661-8664
NERdME: A Named Entity Recognition Dataset for Indexing Research Artifacts in Code Repositories
Existing scholarly information extraction (SIE) datasets focus on scientific papers and overlook implementation-level details in code repositories. README files describe datasets, source code, and other implementation-level artifacts, however, their free-form Markdown offers little semantic structure, making automatic information extraction difficult. To address this gap, NERdME is introduced: 200 manually annotated README files with over νm10000 labeled spans and 10 entity types. Baseline results using large language models and fine-tuned transformers show clear differences between paper-level and implementation-level entities, indicating the value of extending SIE benchmarks with entity types available in README files. A downstream entity-linking experiment was conducted to demonstrate that entities derived from READMEs can support artifact discovery and metadata integration.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8661-8664
Open AccessNERdME: A Named Entity Recognition Dataset for Indexing Research Artifacts in Code Repositories
Existing scholarly information extraction (SIE) datasets focus on scientific papers and overlook implementation-level details in code repositories. README files describe datasets, source code, and other implementation-level artifacts, however, their free-form Markdown offers little semantic structure, making automatic information extraction difficult. To address this gap, NERdME is introduced: 200 manually annotated README files with over νm10000 labeled spans and 10 entity types. Baseline results using large language models and fine-tuned transformers show clear differences between paper-level and implementation-level entities, indicating the value of extending SIE benchmarks with entity types available in README files. A downstream entity-linking experiment was conducted to demonstrate that entities derived from READMEs can support artifact discovery and metadata integration.
- Open Access
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 57387-57408
Large Language Models for Continual Relation Extraction
Real-world data streams, such as news articles and social media posts, are dynamic and nonstationary, creating challenges for real-time structured representation via knowledge graphs, where relation extraction is a key component. Continual relation extraction (CRE) addresses this setting by incrementally learning new relations while preserving previously acquired knowledge. However, adapting models trained on stationary datasets to evolving data distributions remains a challenge. This work investigates the use of pretrained language models for CRE, focusing on large language models (LLMs) and the effectiveness of memory replay in mitigating forgetting. We evaluated decoder-only models and an encoder-decoder model on TACRED and FewRel in English. Our results show that memory replay is most beneficial for smaller instruction-tuned models (e.g., Flan-T5 Base) and base models such as Llama2-7Bhf. In contrast, the remaining instruction-tuned models in this work do not benefit from memory replay, yet some, like Mistral-7B, already achieve higher accuracies without it and surpass prior methods. We further observed that Llama models in this work are more prone to schema-level errors (predictions beyond predefined relations). To the best of our knowledge, this work provides the first reproducible benchmarksa for LLMs in CRE. It offers a novel analysis of knowledge retention and schema-level errors—dimensions that have not been systematically studied in earlier research.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 57387-57408
Open AccessLarge Language Models for Continual Relation Extraction
Real-world data streams, such as news articles and social media posts, are dynamic and nonstationary, creating challenges for real-time structured representation via knowledge graphs, where relation extraction is a key component. Continual relation extraction (CRE) addresses this setting by incrementally learning new relations while preserving previously acquired knowledge. However, adapting models trained on stationary datasets to evolving data distributions remains a challenge. This work investigates the use of pretrained language models for CRE, focusing on large language models (LLMs) and the effectiveness of memory replay in mitigating forgetting. We evaluated decoder-only models and an encoder-decoder model on TACRED and FewRel in English. Our results show that memory replay is most beneficial for smaller instruction-tuned models (e.g., Flan-T5 Base) and base models such as Llama2-7Bhf. In contrast, the remaining instruction-tuned models in this work do not benefit from memory replay, yet some, like Mistral-7B, already achieve higher accuracies without it and surpass prior methods. We further observed that Llama models in this work are more prone to schema-level errors (predictions beyond predefined relations). To the best of our knowledge, this work provides the first reproducible benchmarksa for LLMs in CRE. It offers a novel analysis of knowledge retention and schema-level errors—dimensions that have not been systematically studied in earlier research.
- Open Access
- 6 January 2026
- Published by MDPI AG in Preprints.org
Large Language Models for Continual Relation Extraction
Real-world data streams, such as news articles and social media posts, are dynamic and nonstationary, creating challenges for real-time structured representation via knowledge graphs, where relation extraction is a key component. Continual relation extraction (CRE) addresses this setting by incrementally learning new relations while preserving previously acquired knowledge. This work investigates the use of pretrained language models for CRE, focusing on large language models (LLMs) and the effectiveness of memory replay in mitigating forgetting. We evaluated decoder-only models and an encoder-decoder model on TACRED and FewRel in English. Our results show that memory replay is most beneficial for smaller instruction-tuned models (e.g., Flan-T5 Base) and base models such as Llama2-7B-hf. In contrast, the remaining instruction-tuned models in this work do not benefit from memory replay, yet some, like Mistral-7B, already achieve higher accuracies without it and surpass prior methods. We further observed that Llama models in this work are more prone to hallucinations. To the best of our knowledge, this work provides the first reproducible benchmarks for LLMs in CRE. It offers a novel analysis of knowledge retention and hallucination behavior—dimensions that have not been systematically studied in earlier research.
- 6 January 2026
- Published by MDPI AG in Preprints.org
Open AccessLarge Language Models for Continual Relation Extraction
Real-world data streams, such as news articles and social media posts, are dynamic and nonstationary, creating challenges for real-time structured representation via knowledge graphs, where relation extraction is a key component. Continual relation extraction (CRE) addresses this setting by incrementally learning new relations while preserving previously acquired knowledge. This work investigates the use of pretrained language models for CRE, focusing on large language models (LLMs) and the effectiveness of memory replay in mitigating forgetting. We evaluated decoder-only models and an encoder-decoder model on TACRED and FewRel in English. Our results show that memory replay is most beneficial for smaller instruction-tuned models (e.g., Flan-T5 Base) and base models such as Llama2-7B-hf. In contrast, the remaining instruction-tuned models in this work do not benefit from memory replay, yet some, like Mistral-7B, already achieve higher accuracies without it and surpass prior methods. We further observed that Llama models in this work are more prone to hallucinations. To the best of our knowledge, this work provides the first reproducible benchmarks for LLMs in CRE. It offers a novel analysis of knowledge retention and hallucination behavior—dimensions that have not been systematically studied in earlier research.
- Open Access
NFDI4DS Shared Tasks for Scholarly Document Processing
Shared tasks are powerful tools for advancing research through community-based standardised evaluation. As such, they play a key role in promoting findable, accessible, interoperable, and reusable (FAIR), as well as transparent and reproducible research practices. This paper presents an updated overview of twelve shared tasks developed and hosted under the German National Research Data Infrastructure for Data Science and Artificial Intelligence (NFDI4DS) consortium, covering a diverse set of challenges in scholarly document processing. Hosted at leading venues, the tasks foster methodological innovations and contribute open-access datasets, models, and tools for the broader research community, which are integrated into the consortium's research data infrastructure.
Open AccessNFDI4DS Shared Tasks for Scholarly Document Processing
Shared tasks are powerful tools for advancing research through community-based standardised evaluation. As such, they play a key role in promoting findable, accessible, interoperable, and reusable (FAIR), as well as transparent and reproducible research practices. This paper presents an updated overview of twelve shared tasks developed and hosted under the German National Research Data Infrastructure for Data Science and Artificial Intelligence (NFDI4DS) consortium, covering a diverse set of challenges in scholarly document processing. Hosted at leading venues, the tasks foster methodological innovations and contribute open-access datasets, models, and tools for the broader research community, which are integrated into the consortium's research data infrastructure.
- 15 June 2025
- Published by Springer Nature
- p. 233-245
GDCK: Efficient Large-Scale Graph Distillation Utilizing a Model-Free Kernelized Approach
- 15 June 2025
- Published by Springer Nature
- p. 233-245
GDCK: Efficient Large-Scale Graph Distillation Utilizing a Model-Free Kernelized Approach
- 28 January 2025
- Published by Springer Nature
- p. 202-206
Converter: Enhancing Interoperability in Research Data Management
- 28 January 2025
- Published by Springer Nature
- p. 202-206
Converter: Enhancing Interoperability in Research Data Management
- Open Access
- 11 September 2024
- Published by IOS Press
- p. 2-19
Exploring Prompt Generation Utilizing Graph Search Algorithms for Ontology Matching
The interoperability of domain ontologies, developed by domain experts, necessitates their alignment before attempting to match them. Within these ontologies, defined concepts often encounter an ambiguity problem stemming from the use of natural language. This interoperability issue raises the underlying ontology matching (OM) challenge. OM might be defined as the identification of correspondences or relationships between two or more entities, such as classes or properties among two or more ontologies. Rule-based ontology matching approaches, e.g., LogMap and AML have not outperformed machine learning based matchers on the Ontology Alignment Evaluation Initiative (OAEI) benchmark datasets, especially on the OAEI Conference track since 2020. Supervised machine or deep learning approaches produce the best results but require labeled training datasets. In the era of Large Language Models (LLMs), robust zero-shot prompting of LLMs can also return convincing responses. While prompt generation requires prompt template engineering by domain experts, contextual information about the concepts to be aligned can be retrieved by leveraging graph search algorithms. In this work, we explore how graph search algorithms, namely (i) Random Walk and (ii) Tree Traversal can be utilized to retrieve the contextual information to be incorporated into prompt templates. Through these algorithms, our approach refrains from considering all triples connected with a concept to be aligned in its contextual information creation. Our experiments show that including the retrieved contextual information in prompt templates improves the matcher’s performance. Additionally, our approach outperforms previous works leveraging zero-shot prompting.
- 11 September 2024
- Published by IOS Press
- p. 2-19
Open AccessExploring Prompt Generation Utilizing Graph Search Algorithms for Ontology Matching
The interoperability of domain ontologies, developed by domain experts, necessitates their alignment before attempting to match them. Within these ontologies, defined concepts often encounter an ambiguity problem stemming from the use of natural language. This interoperability issue raises the underlying ontology matching (OM) challenge. OM might be defined as the identification of correspondences or relationships between two or more entities, such as classes or properties among two or more ontologies. Rule-based ontology matching approaches, e.g., LogMap and AML have not outperformed machine learning based matchers on the Ontology Alignment Evaluation Initiative (OAEI) benchmark datasets, especially on the OAEI Conference track since 2020. Supervised machine or deep learning approaches produce the best results but require labeled training datasets. In the era of Large Language Models (LLMs), robust zero-shot prompting of LLMs can also return convincing responses. While prompt generation requires prompt template engineering by domain experts, contextual information about the concepts to be aligned can be retrieved by leveraging graph search algorithms. In this work, we explore how graph search algorithms, namely (i) Random Walk and (ii) Tree Traversal can be utilized to retrieve the contextual information to be incorporated into prompt templates. Through these algorithms, our approach refrains from considering all triples connected with a concept to be aligned in its contextual information creation. Our experiments show that including the retrieved contextual information in prompt templates improves the matcher’s performance. Additionally, our approach outperforms previous works leveraging zero-shot prompting.