Marko Tešić
Research Associate
Leverhulme Centre for the Future of Intelligence, University of Cambridge
I am a Research Associate at the Leverhulme Centre for the Future of Intelligence, University of Cambridge. I currently explore the capabilities of AI systems (primarily large language models) with the aim of mapping these capabilities onto the demands of occupational tasks. This research is carried out in collaboration with the OECD and experts in occupational psychology.
Previously, I was a Royal Academy of Engineering UK IC postdoctoral research fellow investigating the impact of explanations of AI predictions on our beliefs. I also studied people’s causal and probabilistic reasoning and have a strong interest in data analysis, causal modeling and Bayesian network analysis.
I received a Ph.D. in Psychology from Birkbeck’s Psychological Sciences department, an M.A. in Logic and Philosophy of Science from the Munich Center for Mathematical Philosophy, LMU and a B.A. in Philosophy from University of Belgrade, Serbia. See my CV for more info on my background, research and work experience.
I play the violin in Paprika: The Balkan and East European band and The Pico Players.
Publications
The impact of explanations as communicative acts on belief in a claim: The role of source reliability
Investigating the effects of (good) explanations and the explainer’s reliability on our beliefs in what is being explained.
Argument and explanation
We bring together two closely related, but distinct, notions: argument and explanation. We provide a review of relevant research on these notions, drawn both from the cognitive science and the artificial intelligence (AI) literatures. We identify key directions for future research, indicating areas where bringing together cognitive science and AI perspectives would be mutually beneficial.
Can counterfactual explanations of AI systems’ predictions skew lay users’ causal intuitions about the world? If so, can we correct for that?
We explore some of the undesirable effects of providing explanations of AI systems to human users and ways to mitigate such effects. We show how providing counterfactual explanations of AI systems’ predictions unjustifiably changes people’s beliefs about causal relationships in the real world. We also show how health warning style messaging can prevent such a change in beliefs.
On the transferability of insights from the psychology of explanation to explainable AI
A discussion of the consequences of directly applying the insights from the psychology of explanation (that mostly focuses on causal explanations) to explainable AI (where most AI systems are based on associations).
Explanation in AI systems
What do we do with our existing models when we encounter new variables to consider? Does the order in which we learn variables matter? The paper investigates two modeling strategies and experimentally tests how people reason when presented with new variables and in different orders.
The propensity interpretation of probability and diagnostic split in explaining away
Empirical testing of the effects of the propensity interpretation of probability and ‘diagnostic split’ reasoning in the context of explaining away.
Widening Access to Bayesian Problem Solving
An experimental exploration of whether a Bayesian network modeling tool helps lay people to find correct solutions to complex problems.
Sequential diagnostic reasoning with independent causes
What do we do with our existing models when we encounter new variables to consider? Does the order in which we learn variables matter? The paper investigates two modeling strategies and experimentally tests how people reason when presented with new variables and in different orders.
Explaining away: Significance of priors, diagnostic reasoning, and structural complexity
Investigating people’s reasoning in explaining away situations by manipulating the priors of causes and the structural complexity of the causal Baeysian networks.
Confirmation and the Generalized Nagel-Schaffner Model of Reduction: A Bayesian Analysis
Analyzing confirmation between theories in cases of intertheoretic reduction (e.g. reducing thermodynamics to statistical mechanics) using Bayesian networks.
Projects
Contact
My email address is marko dot tesic375 little monkey gmail dot com.