Google DeepMind is calling for the moral behavior of large language models--such as what they do when called on to act as companions, therapists, medical advisors, and so on--to be scrutinized with the same kind of rigor as their ability to code or do math . As LLMs improve, people are asking them to play more and more sensitive roles in their lives. Agents are starting to take actions on people's behalf. LLMs may be able to influence human decision-making . And yet nobody knows how trustworthy this technology really is at such tasks. With coding and math, you have clear-cut, correct answers that you can check, William Isaac, a research scientist at Google DeepMind, told me when I met him and Julia Haas, a fellow research scientist at the firm, for an exclusive preview of their work, which is published in today. That's not the case for moral questions, which typically have a range of acceptable answers: "Morality is an important capability but hard to evaluate," says Isaac. "In the moral domain, there's no right and wrong," adds Haas.

Neuron interpretation offers valuable insights into how knowledge is structured within a deep neural network model.

Our focus in this paper is to solve causal inference problems using only observational data and (potentially partial) knowledge on the causal graph of the underlying structural causal model (SCM).

We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs.

We evaluate through thousands of human-agent interactions, demonstrating 15.4% absolute improvement in instruction execution accuracy

Ensemble approaches for uncertainty estimation have recently been applied to the tasks of misclassification detection, out-of-distribution input detection and adversarial attack detection. Prior Networks have been proposed as an approach to efficiently emulate an ensemble of models for classification by parameteris-ing a Dirichlet prior distribution over output distributions.