Building machines that learn and think with people
What do we want from machine intelligence? We envision machines that are not just tools
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …
for thought but partners in thought: reasonable, insightful, knowledgeable, reliable and …
Passive learning of active causal strategies in agents and language models
What can be learned about causality and experimentation from passive data? This question
is salient given recent successes of passively-trained language models in interactive …
is salient given recent successes of passively-trained language models in interactive …
[PDF][PDF] Good Explanations in Explainable Artificial Intelligence (XAI): Evidence from Human Explanatory Reasoning.
RMJ Byrne - IJCAI, 2023 - ijcai.org
Insights from cognitive science about how people understand explanations can be
instructive for the development of robust, user-centred explanations in eXplainable Artificial …
instructive for the development of robust, user-centred explanations in eXplainable Artificial …
Counterfactuals and the logic of causal selection.
Everything that happens has a multitude of causes, but people make causal judgments
effortlessly. How do people select one particular cause (eg, the lightning bolt that set the …
effortlessly. How do people select one particular cause (eg, the lightning bolt that set the …
What would have happened? Counterfactuals, hypotheticals and causal judgements
T Gerstenberg - … Transactions of the Royal Society B, 2022 - royalsocietypublishing.org
How do people make causal judgements? In this paper, I show that counterfactual
simulations are necessary for explaining causal judgements about events, and that …
simulations are necessary for explaining causal judgements about events, and that …
On the horizon: Interactive and compositional deepfakes
E Horvitz - Proceedings of the 2022 International Conference on …, 2022 - dl.acm.org
Over a five-year period, computing methods for generating high-fidelity, fictional depictions
of people and events moved from exotic demonstrations by computer science research …
of people and events moved from exotic demonstrations by computer science research …
How people reason with counterfactual and causal explanations for artificial intelligence decisions in familiar and unfamiliar domains
L Celar, RMJ Byrne - Memory & Cognition, 2023 - Springer
Few empirical studies have examined how people understand counterfactual explanations
for other people's decisions, for example,“if you had asked for a lower amount, your loan …
for other people's decisions, for example,“if you had asked for a lower amount, your loan …
Causal judgments about atypical actions are influenced by agents' epistemic states
A prominent finding in causal cognition research is people's tendency to attribute increased
causality to atypical actions. If two agents jointly cause an outcome (conjunctive causation) …
causality to atypical actions. If two agents jointly cause an outcome (conjunctive causation) …
Watchat: Explaining perplexing programs by debugging mental models
Often, a good explanation for a program's unexpected behavior is a bug in the programmer's
code. But sometimes, an even better explanation is a bug in the programmer's mental model …
code. But sometimes, an even better explanation is a bug in the programmer's mental model …
Predicting responsibility judgments from dispositional inferences and causal attributions
The question of how people hold others responsible has motivated decades of theorizing
and empirical work. In this paper, we develop and test a computational model that bridges …
and empirical work. In this paper, we develop and test a computational model that bridges …