Kristian González Barman

Hello! I’m Kristian, a philosopher of science working on explanation, causation, and explainable AI.

Currently, I’m a Postdoctoral Researcher at Ghent University, looking into how explanations work in Explainable AI. Previously, I spent a year at the ISIS institute in the Faculty of Science at Radboud University, engaging in interdisciplinary research that spanned philosophy, physics, and computer science, looking at the topic of scientific understanding through and by AI. My PhD focused on explanation in the engineering sciences, consisting of a blend of causal modelling, safety science, and the study of explanatory mechanisms in failure analysis.

My academic interests lie at the nexus of Causal Explanation, Explainable AI, Deep Learning, and the Philosophy of Science in Practice. When not immersed in research, I indulge in coffee research and consumption, programming, playing the piano, exploring blockchain technology applications, hitting the gym, and playing chess.

selected publications

ES

Accident Causation Models: The Good the Bad and the Ugly

Kristian González Barman

Engineering Studies 2023

Abs HTML

The main aim of this paper is to evaluate the evolution of Accident Causation Models (ACMs) from the perspective of philosophy of science. I use insights from philosophy of science to provide an epistemological analysis of the ways in which engineering scientists judge the value of different types of ACMs and to offer normative reflection on these judgements. I review three widespread ACMs and clarify their epistemic value: sequential models, epidemiological models, and systemic models. I first consider how they produce and ensure safety (‘usefulness’) relative to each other. This is evaluated in terms of the ability of models to afford a larger set of relevant counterfactual inferences. I take relevant inferences to be ones that provide safety (re)design information or suggest countermeasures (safety-design-interventions). I argue that systemic models are superior at providing said safety information. They achieve this, in part, by representing non-linear causal relationships. The second issue is whether we should retire linear and epidemiological models. I argue negatively. If the goal is to assign blame, linear models are better candidates. The reason is that they can provide semantic simplicity. Similarly, epidemiological models are better suited for the goal of audience communication because they can provide cognitive salience.
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 2023

Abs HTML

Scientific understanding is a fundamental goal of science, allowing us to explain the world. 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 and approaches to scientific understanding. In this Roadmap, we propose a framework to create a benchmark for scientific understanding, utilizing tools from philosophy of science. We adopt a behavioral notion according to which genuine understanding should be recognized as an ability to perform certain tasks. We extend this notion by considering a set of questions that can 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.
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 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.