Kristian González Barman

Hello! I’m Kristian, a philosopher of science and Principal Investigator at the Centre for Logic and Philosophy of Science at Ghent University, where I lead the FWO-funded project Explanation in Explainable AI.

My research sits at the intersection of philosophy of science, artificial intelligence, and scientific practice. I work on how explanations function in Explainable AI (XAI), what it means for AI systems to exhibit scientific understanding, and how mechanistic interpretability can help us open the black box of large language models. A through-line in my work is bridging philosophy and real scientific practice: developing benchmarks, guidelines, and conceptual tools that shape how researchers and practitioners actually build and evaluate AI systems.

Before coming to Ghent, I spent a year at the Institute for Science in Society at Radboud University, working at the crossroads of philosophy, physics, and computer science on scientific understanding through AI. My PhD (Ghent, 2023) focused on explanation in the engineering sciences, blending causal modelling, safety science, and the study of explanatory mechanisms in failure analysis.

I teach philosophy of science at master’s level across Ghent University, the University of Antwerp, and the Vrije Universiteit Brussel, and I supervise PhD research on functional explanation. I also collaborate on projects spanning physics benchmarking, responsible AI, and the philosophy of medical AI.

When not immersed in research, you can find me at the gym, playing the piano, or playing chess.

news

Mar 1, 2026	Invited talk at the LT3 Language and Translation Technology Team seminar (UGent): “Understanding LLMs for Science: From Benchmarks to Mechanisms.”
Sep 10, 2025	Invited talks at the University of Cincinnati, Purdue University, and Butler University in September 2025.
Mar 1, 2025	New paper accepted at the British Journal for the Philosophy of Science: “Distinctively Mathematical Explanations of Game Outcomes.”
Feb 1, 2025	Paper on RLHF pluralism published in Philosophy & Technology: “Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?”
Jan 15, 2025	“Large Physics Models” paper published in The European Physical Journal C — a collaborative roadmap for physics-specific AI.

selected publications

M&M
Towards a Benchmark for Scientific Understanding in Humans and Machines

Kristian Gonzalez Barman, Sascha Caron, Tom Claassen, and 1 more author

Minds and Machines 2024

Abs Bib HTML

Scientific understanding is a fundamental goal of science. However, there is currently no good way to measure the scientific understanding of agents, whether these be humans or Artificial Intelligence systems. Without a clear benchmark, it is challenging to evaluate and compare different levels of scientific understanding. In this paper, we propose a framework to create a benchmark for scientific understanding, utilizing tools from philosophy of science. We adopt a behavioral conception of understanding, according to which genuine understanding should be recognized as an ability to perform certain tasks. We extend this notion of scientific understanding by considering a set of questions that gauge different levels of scientific understanding, covering information retrieval, the capability to arrange information to produce an explanation, and the ability to infer how things would be different under different circumstances. The Scientific Understanding Benchmark (SUB), which is formed by a set of these tests, allows for the evaluation and comparison of different approaches. Benchmarking plays a crucial role in establishing trust, ensuring quality control, and providing a basis for performance evaluation. By aligning machine and human scientific understanding we can improve their utility, ultimately advancing scientific understanding and helping to discover new insights within machines.
@article{barman2023towards, title = {Towards a Benchmark for Scientific Understanding in Humans and Machines}, author = {Barman, Kristian Gonzalez and Caron, Sascha and Claassen, Tom and de Regt, Henk}, journal = {Minds and Machines}, volume = {34}, number = {1}, pages = {1--16}, year = {2024}, }
ETIN
Beyond transparency and explainability: on the need for adequate and contextualized user guidelines for LLM use

Kristian González Barman, Nathan Wood, and Pawel Pawlowski

Ethics and Information Technology 2024

Abs Bib HTML

Large language models (LLMs) such as ChatGPT present immense opportunities, but without proper training for users (and potentially oversight), they carry risks of misuse as well. We argue that current approaches focusing predominantly on transparency and explainability fall short in addressing the diverse needs and concerns of various user groups. We highlight the limitations of existing methodologies and propose a framework anchored on user-centric guidelines. In particular, we argue that LLM users should be given guidelines on what tasks LLMs can do well and which they cannot, which tasks require further guidance or refinement by the user, and context-specific heuristics. We further argue that (some) users should be taught to refine and elaborate adequate prompts, be provided with good procedures for prompt iteration, and be taught efficient ways to verify outputs. We suggest that for users, shifting away from looking at the technology itself, but rather looking at the usage of it within contextualized sociotechnical systems, can help solve many issues related to LLMs. We further emphasize the role of real-world case studies in shaping these guidelines, ensuring they are grounded in practical, applicable strategies. Like any technology, risks of misuse can be managed through education, regulation, and responsible development.
@article{barman2024beyond, title = {Beyond transparency and explainability: on the need for adequate and contextualized user guidelines for LLM use}, author = {Barman, Kristian Gonz{\'a}lez and Wood, Nathan and Pawlowski, Pawel}, journal = {Ethics and Information Technology}, volume = {26}, number = {3}, pages = {47}, year = {2024}, publisher = {Springer Netherlands Dordrecht}, }
P&T
Reinforcement learning from human feedback in LLMs: Whose culture, whose values, whose perspectives?

Kristian González Barman, Simon Lohse, and Henk W Regt

Philosophy & Technology 2025

Abs Bib HTML

We argue for the epistemic and ethical advantages of pluralism in Reinforcement Learning from Human Feedback (RLHF) in the context of Large Language Models (LLMs). Drawing on social epistemology and pluralist philosophy of science, we suggest ways in which RHLF can be made more responsive to human needs and how we can address challenges along the way. The paper concludes with an agenda for change, i.e. concrete, actionable steps to improve LLM development.
@article{gonzalez2025reinforcement, title = {Reinforcement learning from human feedback in LLMs: Whose culture, whose values, whose perspectives?}, author = {Gonz{\'a}lez Barman, Kristian and Lohse, Simon and de Regt, Henk W}, journal = {Philosophy \& Technology}, volume = {38}, number = {2}, pages = {1--26}, year = {2025}, publisher = {Springer}, }
EPJC
Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models

Kristian G Barman, Sascha Caron, Emily Sullivan, and 8 more authors

The European Physical Journal C 2025

Abs Bib HTML

This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs). These models, based on foundation models such as Large Language Models (LLMs) - trained on broad data - are tailored to address the demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection.
@article{barman2025large, title = {Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models}, author = {Barman, Kristian G and Caron, Sascha and Sullivan, Emily and de Regt, Henk W and de Austri, Roberto Ruiz and Boon, Mieke and F{\"a}rber, Michael and Fr{\"o}se, Stefan and Hasibi, Faegheh and Ipp, Andreas and others}, journal = {The European Physical Journal C}, volume = {85}, number = {9}, pages = {1066}, year = {2025}, }
BJPS
Distinctively Mathematical Explanations of Game Outcomes

Kristian G. Barman

British Journal for the Philosophy of Science 2025

Abs Bib HTML

The debate on distinctively mathematical explanations (DMEs) relies heavily on examples such as strawberry distribution and bridge crossing. I argue that "task-based" examples do not explain physical facts; rather, they explain outcomes of abstract games that follow predefined rules. The impossibility of these tasks stems from obeying the games’ rules. Modality holds due to the way the explanandum is formulated, rather than due to nomological or mathematical constraints. I develop an account of these examples as mathematical explanations of game outcomes rather than DMEs of physical facts, where mathematical models enable unification and counterfactual reasoning about game outcomes across instantiations, providing explanatory power. I then show how this account can provide insights on the range of valid counterfactual inferences enabled by these explanations.
@article{barman2025DME, title = {Distinctively Mathematical Explanations of Game Outcomes}, author = {Barman, Kristian G.}, journal = {British Journal for the Philosophy of Science}, pages = {1--18}, year = {2025}, }