David Kinney

Donald Martin,, David Kinney

Deep learning is a powerful set of techniques for detecting complex patterns in data. However, when the causal structure of that process is underspecified, deep learning models can be brittle, lacking robustness to shifts in the distribution of the data-generating process. In this paper, we turn to loop polarity analysis as a tool for specifying the causal structure of a data-generating process, in order to encode a more robust understanding of the relationship between system structure and system behavior within the deep learning pipeline. We use simulated epidemic data based on an SIR model to demonstrate how measuring the polarity of the different feedback loops that compose a system can lead to more robust inferences on the part of neural networks, improving the out-of-distribution performance of a deep learning model and infusing a system-dynamics-inspired approach into the machine learning development pipeline.

Piyawat Lertvittayakumjorn, David Kinney, Vinodkumar Prabhakaran et al.

Generative large language models (LLMs) have demonstrated gaps in diverse cultural awareness across the globe. We investigate the effect of retrieval augmented generation and search-grounding techniques on LLMs' ability to display familiarity with various national cultures. Specifically, we compare the performance of standard LLMs, LLMs augmented with retrievals from a bespoke knowledge base (i.e., KB grounding), and LLMs augmented with retrievals from a web search (i.e., search grounding) on multiple cultural awareness benchmarks. We find that search grounding significantly improves the LLM performance on multiple-choice benchmarks that test propositional knowledge (e.g., cultural norms, artifacts, and institutions), while KB grounding's effectiveness is limited by inadequate knowledge base coverage and a suboptimal retriever. However, search grounding also increases the risk of stereotypical judgments by language models and fails to improve evaluators' judgments of cultural familiarity in a human evaluation with adequate statistical power. These results highlight the distinction between propositional cultural knowledge and open-ended cultural fluency when it comes to evaluating LLMs' cultural awareness.

David Kinney

An algorithm that outputs predictions about the state of the world will almost always be designed with the implicit or explicit goal of outputting accurate predictions (i.e., predictions that are likely to be true). In addition, the rise of increasingly powerful predictive algorithms brought about by the recent revolution in artificial intelligence has led to an emphasis on building predictive algorithms that are fair, in the sense that their predictions do not systematically evince bias or bring about harm to certain individuals or groups. This state of affairs presents two conceptual challenges. First, the goals of accuracy and fairness can sometimes be in tension, and there are no obvious normative guidelines for managing the trade-offs between these two desiderata when they arise. Second, there are many distinct ways of measuring both the accuracy and fairness of a predictive algorithm; here too, there are no obvious guidelines on how to aggregate our preferences for predictive algorithms that satisfy disparate measures of fairness and accuracy to various extents. The goal of this paper is to address these challenges by arguing that there are good reasons for using a linear combination of accuracy and fairness metrics to measure the all-things-considered value of a predictive algorithm for agents who care about both accuracy and fairness. My argument depends crucially on a classic result in the preference aggregation literature due to Harsanyi. After making this formal argument, I apply my result to an analysis of accuracy-fairness trade-offs using the COMPAS dataset compiled by Angwin et al.

David H. Wolpert, David Kinney

We present a computational model of mathematical reasoning according to which mathematics is a fundamentally stochastic process. That is, on our model, whether or not a given formula is deemed a theorem in some axiomatic system is not a matter of certainty, but is instead governed by a probability distribution. We then show that this framework gives a compelling account of several aspects of mathematical practice. These include: 1) the way in which mathematicians generate research programs, 2) the applicability of Bayesian models of mathematical heuristics, 3) the role of abductive reasoning in mathematics, 4) the way in which multiple proofs of a proposition can strengthen our degree of belief in that proposition, and 5) the nature of the hypothesis that there are multiple formal systems that are isomorphic to physically possible universes. Thus, by embracing a model of mathematics as not perfectly predictable, we generate a new and fruitful perspective on the epistemology and practice of mathematics.

David Kinney, David Watson

Discovering high-level causal relations from low-level data is an important and challenging problem that comes up frequently in the natural and social sciences. In a series of papers, Chalupka et al. (2015, 2016a, 2016b, 2017) develop a procedure for causal feature learning (CFL) in an effort to automate this task. We argue that CFL does not recommend coarsening in cases where pragmatic considerations rule in favor of it, and recommends coarsening in cases where pragmatic considerations rule against it. We propose a new technique, pragmatic causal feature learning (PCFL), which extends the original CFL algorithm in useful and intuitive ways. We show that PCFL has the same attractive measure-theoretic properties as the original CFL algorithm. We compare the performance of both methods through theoretical analysis and experiments.