Related papers: Fairer Software Made Easier (using "Keys")
Algorithms are increasingly used to aid, or in some cases supplant, human decision-making, particularly for decisions that hinge on predictions. As a result, two additional features in addition to prediction quality have generated interest:…
Simplicity is held by many to be the key to general intelligence. Simpler models tend to "generalise", identifying the cause or generator of data with greater sample efficiency. The implications of the correlation between simplicity and…
Control systems are sets of interconnected hardware and software components which regulate the behaviour of processes. The software of modern control systems rises for some years by requirements regarding the flexibility and functionality.…
Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate…
We propose a control-theoretic interpretation of recommender systems and use this perspective to analyze how fairness interventions shape long-term system behavior. Fairness concerns arise for both users and creators, ranging from opinion…
Computer programs are often factored into pure components -- simple, total functions from inputs to outputs -- and components that may have side effects -- errors, changes to memory, parallel threads, abortion of the current loop, etc. We…
Software analytics has been the subject of considerable recent attention but is yet to receive significant industry traction. One of the key reasons is that software practitioners are reluctant to trust predictions produced by the analytics…
As society transitions towards an AI-based decision-making infrastructure, an ever-increasing number of decisions once under control of humans are now delegated to automated systems. Even though such developments make various parts of…
Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The…
Explanation facilities are a particularly important feature of expert system frameworks. It is an area in which traditional rule-based expert system frameworks have had mixed results. While explanations about control are well handled,…
Context and Motivation: The increasing complexity of modern software systems often challenges users' abilities to interact with them. Taking established quality attributes such as usability and transparency into account can mitigate this…
Earlier work on machine learning for automated reasoning mostly relied on simple, syntactic features combined with sophisticated learning techniques. Using ideas adopted in the software verification community, we propose the investigation…
Which mechanisms are simple to play? When is it easy for participants to see that a mechanism is incentive-compatible? I will start by explaining how and why economists came to ask these questions. Then I will discuss three recent answers,…
When Requirements Engineering(RE) models are unreasonably complex, they cannot support efficient decision making. SHORT is a tool to simplify that reasoning by exploiting the "key" decisions within RE models. These "keys" have the property…
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against…
In today's world, we need to ensure that AI systems are fair and unbiased. Our study looked at tools designed to test the fairness of software to see if they are practical and easy for software developers to use. We found that while some…
Explaining the behaviour of intelligent systems will get increasingly and perhaps intractably challenging as models grow in size and complexity. We may not be able to expect an explanation for every prediction made by a brain-scale model,…
As algorithmic tools increasingly aid experts in making consequential decisions, the need to understand the precise factors that mediate their influence has grown commensurately. In this paper, we present a crowdsourcing vignette study…
Proponents of software verification have argued that simpler code is easier to verify: that is, that verification tools issue fewer false positives and require less human intervention when analyzing simpler code. We empirically validate…
AI-powered software tools are widely used to assist software engineers. However, there is still a need to understand the productivity benefits of such tools for software engineers. In addition to short-term benefits, there is a question of…