Muhammad Bilal Zafar

Pola Schwöbel, Luca Franceschi, Muhammad Bilal Zafar et al.

fmeval is an open source library to evaluate large language models (LLMs) in a range of tasks. It helps practitioners evaluate their model for task performance and along multiple responsible AI dimensions. This paper presents the library and exposes its underlying design principles: simplicity, coverage, extensibility and performance. We then present how these were implemented in the scientific and engineering choices taken when developing fmeval. A case study demonstrates a typical use case for the library: picking a suitable model for a question answering task. We close by discussing limitations and further work in the development of the library. fmeval can be found at https://github.com/aws/fmeval.

Till Speicher, Hoda Heidari, Nina Grgic-Hlaca et al.

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.

Juhi Kulshrestha, Muhammad Bilal Zafar, Lisette Espin-Noboa et al.

With the widespread adoption of social media sites like Twitter and Facebook, there has been a shift in the way information is produced and consumed. Earlier, the only producers of information were traditional news organizations, which broadcast the same carefully-edited information to all consumers over mass media channels. Whereas, now, in online social media, any user can be a producer of information, and every user selects which other users she connects to, thereby choosing the information she consumes. Moreover, the personalized recommendations that most social media sites provide also contribute towards the information consumed by individual users. In this work, we define a concept of information diet -- which is the topical distribution of a given set of information items (e.g., tweets) -- to characterize the information produced and consumed by various types of users in the popular Twitter social media. At a high level, we find that (i) popular users mostly produce very specialized diets focusing on only a few topics; in fact, news organizations (e.g., NYTimes) produce much more focused diets on social media as compared to their mass media diets, (ii) most users' consumption diets are primarily focused towards one or two topics of their interest, and (iii) the personalized recommendations provided by Twitter help to mitigate some of the topical imbalances in the users' consumption diets, by adding information on diverse topics apart from the users' primary topics of interest.

Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez et al.

Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services. These systems rely on complex learning methods and vast amounts of data to optimize the service functionality, satisfaction of the end user and profitability. However, there is a growing concern that these automated decisions can lead, even in the absence of intent, to a lack of fairness, i.e., their outcomes can disproportionately hurt (or, benefit) particular groups of people sharing one or more sensitive attributes (e.g., race, sex). In this paper, we introduce a flexible mechanism to design fair classifiers by leveraging a novel intuitive measure of decision boundary (un)fairness. We instantiate this mechanism with two well-known classifiers, logistic regression and support vector machines, and show on real-world data that our mechanism allows for a fine-grained control on the degree of fairness, often at a small cost in terms of accuracy.