Silja Renooij
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Silja Renooij has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Bart Verheij
University of Groningen
9 shared publications - Annet Onnes
Utrecht University
4 shared publications - Henry Prakken
Utrecht University, Utrecht, Netherlands
4 shared publications - Mehdi Dastani
Utrecht University, Utrecht, Netherlands
3 shared publications - Charlotte S. Vlek
Institute of Artificial Intelligence, University of Groningen, Groningen, Netherlands
2 shared publications - Cor Steging
Bernoulli Institute of Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, NETHERLANDS
2 shared publications
Latest Publications
- 24 September 2025
- Published by Springer Nature
- p. 46-60
Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks
- 24 September 2025
- Published by Springer Nature
- p. 46-60
Maximum Entropy-Based Quantification for Probability Elicitation in Bayesian Networks
- 24 September 2025
- Published by Springer Nature
- p. 3-16
Inverse Marginalisation for Safely Expanding Bayesian Networks
- 24 September 2025
- Published by Springer Nature
- p. 3-16
Inverse Marginalisation for Safely Expanding Bayesian Networks
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 455-459
Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 455-459
Open AccessParameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
- Open Access
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 83-92
Evaluating Methods for Scenario Reasoning using Bayesian Networks in Exhaustive and Non-Exhaustive Settings
- 16 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 83-92
Open AccessEvaluating Methods for Scenario Reasoning using Bayesian Networks in Exhaustive and Non-Exhaustive Settings
- Open Access
Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the basis of witness testimony, focusing on the underlying argument attack structure. We dynamically generate both linear and non-linear argument attack graphs of varying complexity and translate these into reasoning puzzles about witness testimony expressed in natural language. We show that state-of-the-art large language models often fail in these reasoning puzzles, already at low complexity. Obvious mistakes are made by the models, and their inconsistent performance indicates that their reasoning capabilities are brittle. Furthermore, at higher complexity, even state-of-the-art models specifically presented for reasoning capabilities make mistakes. We show the viability of using a parametrized benchmark with varying complexity to evaluate the reasoning capabilities of generative language models. As such, the findings contribute to a better understanding of the limitations of the reasoning capabilities of generative models, which is essential when designing responsible AI systems in the legal domain.
Open AccessParameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models
Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the basis of witness testimony, focusing on the underlying argument attack structure. We dynamically generate both linear and non-linear argument attack graphs of varying complexity and translate these into reasoning puzzles about witness testimony expressed in natural language. We show that state-of-the-art large language models often fail in these reasoning puzzles, already at low complexity. Obvious mistakes are made by the models, and their inconsistent performance indicates that their reasoning capabilities are brittle. Furthermore, at higher complexity, even state-of-the-art models specifically presented for reasoning capabilities make mistakes. We show the viability of using a parametrized benchmark with varying complexity to evaluate the reasoning capabilities of generative language models. As such, the findings contribute to a better understanding of the limitations of the reasoning capabilities of generative models, which is essential when designing responsible AI systems in the legal domain.
- 1 January 2024
- Published by Springer Nature
- p. 415-426
Extending Idioms for Bayesian Network Construction with Qualitative Constraints
- 1 January 2024
- Published by Springer Nature
- p. 415-426
Extending Idioms for Bayesian Network Construction with Qualitative Constraints
- 19 November 2023
- Published by Springer Nature
- p. 149-159
Normative Monitoring Using Bayesian Networks: Defining a Threshold for Conflict Detection
- 19 November 2023
- Published by Springer Nature
- p. 149-159
Normative Monitoring Using Bayesian Networks: Defining a Threshold for Conflict Detection
- Open Access
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 323-332
Using Agent-Based Simulations to Evaluate Bayesian Networks for Criminal Scenarios
- 19 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 323-332
Open AccessUsing Agent-Based Simulations to Evaluate Bayesian Networks for Criminal Scenarios
- Open Access
- 16 June 2023
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 160
Efficient search for relevance explanations using MAP-independence in Bayesian networks
- 16 June 2023
- Published by Elsevier in International Journal of Approximate Reasoning
- Vol. 160
Open AccessEfficient search for relevance explanations using MAP-independence in Bayesian networks
- Open Access
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Bayesian Network Conflict Detection for Normative Monitoring of Black-Box Systems
Bayesian networks are interpretable probabilistic models that can be constructed from both data and domain knowledge. They are applied in various domains and for different tasks, including that of anomaly detection, for which an easy to compute measure of data conflict exists. In this paper we consider the use of Bayesian networks to monitor input-output pairs of a black-box AI system, to establish whether the output is acceptable in the current context in which the AI system operates. A Bayesian network-based prescriptive, or normative, model is assumed that includes context variables relevant for deciding what is or is not acceptable. We analyse and adjust the conflict measure to make it applicable to our new type of monitoring setting.
- 8 May 2023
- Published by University of Florida George A Smathers Libraries in The International FLAIRS Conference Proceedings
- Vol. 36
Open AccessBayesian Network Conflict Detection for Normative Monitoring of Black-Box Systems
Bayesian networks are interpretable probabilistic models that can be constructed from both data and domain knowledge. They are applied in various domains and for different tasks, including that of anomaly detection, for which an easy to compute measure of data conflict exists. In this paper we consider the use of Bayesian networks to monitor input-output pairs of a black-box AI system, to establish whether the output is acceptable in the current context in which the AI system operates. A Bayesian network-based prescriptive, or normative, model is assumed that includes context variables relevant for deciding what is or is not acceptable. We analyse and adjust the conflict measure to make it applicable to our new type of monitoring setting.