Search for: All records

Large Language Models (LLMs) have become increasingly incorporated into everyday life for many internet users, taking on significant roles as advice givers in the domains of medicine, personal relationships, and even legal matters. The importance of these roles raise questions about how and what responses LLMs make in difficult political and moral domains, especially questions about possible biases. To quantify the nature of potential biases in LLMs, various works have applied Moral Foundations Theory (MFT), a framework that categorizes human moral reasoning into five dimensions: Harm, Fairness, Ingroup Loyalty, Authority, and Purity. Previous research has used the MFT to measure differences in human participants along political, national, and cultural lines. While there has been some analysis of the responses of LLM with respect to political stance in role-playing scenarios, no work so far has directly assessed the moral leanings in the LLM responses, nor have they connected LLM outputs with robust human data. In this paper we analyze the distinctions between LLM MFT responses and existing human research directly, investigating whether commonly available LLM responses demonstrate ideological leanings — either through their inherent responses, straightforward representations of political ideologies, or when responding from the perspectives of constructed human personas. We assess whether LLMs inherently generate responses that align more closely with one political ideology over another, and additionally examine how accurately LLMs can represent ideological perspectives through both explicit prompting and demographic-based role-playing. By systematically analyzing LLM behavior across these conditions and experiments, our study provides insight into the extent of political and demographic dependency in AI-generated responses. 

We consider the problem of determining a binary ground truth using advice from a group of independent reviewers (experts) who express their guess about a ground truth correctly with some independent probability (competence) 𝑝 . In this setting, when all reviewers 𝑖 are competent with 𝑝 ≥ 0.5, the Condorcet Jury Theorem tells us that adding more reviewers increases the overall accuracy, and if all 𝑝 ’s are known, then there exists an optimal weighting of the 𝑖 reviewers. However, in practical settings, reviewers may be noisy or incompetent, i.e., 𝑝𝑖 ≤ 0.5, and the number of experts may be small, so the asymptotic Condorcet Jury Theorem is not practically relevant. In such cases we explore appointing one or more chairs ( judges) who determine the weight of each reviewer for aggregation, creating multiple levels. However, these chairs may be unable to correctly identify the competence of the reviewers they oversee, and therefore unable to compute the optimal weighting. We give conditions on when a set of chairs is able to weight the reviewers optimally, and depending on the competence distribution of the agents, give results about when it is better to have more chairs or more reviewers. Through simulations we show that in some cases it is better to have more chairs, but in many cases it is better to have more reviewers. 

Fairness in recommender systems is a complex concept, involving multiple definitions, different parties for whom fairness is sought, and various scopes over which fairness might be measured. Re- searchers seeking fairness-aware systems have derived a variety of solutions, usually highly tailored to specific choices along each of these dimensions, and typically aimed at tackling a single fairness concern, i.e., a single definition for a specific stakeholder group and measurement scope. However, in practical contexts, there are a multiplicity of fairness concerns within a given recommendation application and solutions limited to a single dimension are therefore less useful. We explore a general solution to recommender system fairness using social choice methods to integrate multiple hetero- geneous definitions. In this paper, we extend group-fairness results from prior research to provider-side individual fairness, demon- strating in multiple datasets that both individual and group fairness objectives can be integrated and optimized jointly. We identify both synergies and tensions among different objectives with individ- ual fairness correlated with group fairness for some groups and anti-correlated with others. 

Online reviews provide valuable insights into the perceived quality of facets of a product or service. While aspect-based sentiment analysis has focused on extracting these facets from reviews, there is less work understanding the impact of each aspect on overall perception. This is particularly challenging given correlations among aspects, making it difficult to isolate the effects of each. This paper introduces a methodology based on recent advances in text-based causal analysis, specifically CausalBERT, to disentangle the effect of each factor on overall review ratings. We enhance CausalBERT with three key improvements: temperature scaling for better calibrated treatment assignment estimates; hyperparameter optimization to reduce confound overadjustment; and interpretability methods to characterize discovered confounds. In this work, we treat the textual mentions in reviews as proxies for real-world attributes. We validate our approach on real and semi-synthetic data from over 600K reviews of U.S. K-12 schools. We find that the proposed enhancements result in more reliable estimates, and that perception of school administration and performance on benchmarks are significant drivers of overall school ratings. 

We consider the problem of determining a binary ground truth using advice from a group of independent reviewers (experts) who express their guess about a ground truth correctly with some independent probability (competence) $$p_i$$. In this setting, when all reviewers are competent with $$p \geq 0.5$$, the Condorcet Jury Theorem tells us that adding more reviewers increases the overall accuracy, and if all $$p_i$$'s are known, then there exists an optimal weighting of the reviewers. However, in practical settings, reviewers may be noisy or incompetent, i.e., $$p_i \leq 0.5$$, and the number of experts may be small, so the asymptotic Condorcet Jury Theorem is not practically relevant. In such cases we explore appointing one or more chairs (judges) who determine the weight of each reviewer for aggregation, creating multiple levels. However, these chairs may be unable to correctly identify the competence of the reviewers they oversee, and therefore unable to compute the optimal weighting. We give conditions on when a set of chairs is able to weight the reviewers optimally, and depending on the competence distribution of the agents, give results about when it is better to have more chairs or more reviewers. Through simulations we show that in some cases it is better to have more chairs, but in many cases it is better to have more reviewers. 

There is a critical need for community engagement in the process of adopting artificial intelligence (AI) technologies in public health. Public health practitioners and researchers have historically innovated in areas like vaccination and sanitation but have been slower in adopting emerging technologies such as generative AI. However, with increasingly complex funding, programming, and research requirements, the field now faces a pivotal moment to enhance its agility and responsiveness to evolving health challenges. Participatory methods and community engagement are key components of many current public health programs and research. The field of public health is well positioned to ensure community engagement is part of AI technologies applied to population health issues. Without such engagement, the adoption of these technologies in public health may exclude significant portions of the population, particularly those with the fewest resources, with the potential to exacerbate health inequities. Risks to privacy and perpetuation of bias are more likely to be avoided if AI technologies in public health are designed with knowledge of community engagement, existing health disparities, and strategies for improving equity. This viewpoint proposes a multifaceted approach to ensure safer and more effective integration of AI in public health with the following call to action: (1) include the basics of AI technology in public health training and professional development; (2) use a community engagement approach to co-design AI technologies in public health; and (3) introduce governance and best practice mechanisms that can guide the use of AI in public health to prevent or mitigate potential harms. These actions will support the application of AI to varied public health domains through a framework for more transparent, responsive, and equitable use of this evolving technology, augmenting the work of public health practitioners and researchers to improve health outcomes while minimizing risks and unintended consequences. 

Algorithmic fairness in the context of personalized recommendation presents significantly different challenges to those commonly encountered in classification tasks. Researchers studying classification have generally considered fairness to be a matter of achieving equality of outcomes (or some other metric) between a protected and unprotected group, and built algorithmic interventions on this basis. We argue that fairness in real-world application settings in general, and especially in the context of personalized recommendation, is much more complex and multi-faceted, requiring a more general approach. To address the fundamental problem of fairness in the presence of multiple stakeholders, with different definitions of fairness, we propose the Social Choice for Recommendation Under Fairness – Dynamic (SCRUF-D) architecture, which formalizes multistakeholder fairness in recommender systems as a two-stage social choice problem. In particular, we express recommendation fairness as a combination of an allocation and an aggregation problem, which integrate both fairness concerns and personalized recommendation provisions, and derive new recommendation techniques based on this formulation. We demonstrate the ability of our framework to dynamically incorporate multiple fairness concerns using both real-world and synthetic datasets. 

Abstract We introduce Flexible Representative Democracy (FRD), a novel hybrid of Representative Democracy and Direct Democracy in which voters can alter the issue-dependent weights of a set of elected representatives. In line with the literature on Interactive Democracy, our model allows the voters to actively determine the degree to which the system is direct versus representative. However, unlike Liquid Democracy, Flexible Representative Democracy uses strictly non-transitive delegations, making delegation cycles impossible, and maintains a fixed set of accountable, elected representatives. We present Flexible Representative Democracy and analyze it using a computational approach with issues that are binary and symmetric. We compare the outcomes of various voting systems using Direct Democracy with majority voting as an ideal baseline. First, we demonstrate the shortcomings of Representative Democracy in our model. We provide NP-Hardness results for electing an ideal set of representatives, discuss pathologies, and demonstrate empirically that common multi-winner election rules for selecting representatives do not perform well in expectation. To analyze the effects of adding delegation to representative voting systems, we begin by providing theoretical results on how issue-specific delegations determine outcomes. Finally, we provide empirical results comparing the outcomes of various voting systems: Representative Democracy, Proxy Voting, and FRD with issue-specific delegations. Our results show that variants of Proxy Voting yield no discernible benefit over unweighted representatives and reveal the potential for Flexible Representative Democracy to improve outcomes as voter participation increases. 

Public sector leverages artificial intelligence (AI) to enhance the efficiency, transparency, and accountability of civic operations and public services. This includes initiatives such as predictive waste management, facial recognition for identification, and advanced tools in the criminal justice system. While public-sector AI can improve efficiency and accountability, it also has the potential to perpetuate biases, infringe on privacy, and marginalize vulnerable groups. Responsible AI (RAI) research aims to address these concerns by focusing on fairness and equity through participatory AI. We invite researchers, community members, and public sector workers to collaborate on designing, developing, and deploying RAI systems that enhance public sector accountability and transparency. Key topics include raising awareness of AI's impact on the public sector, improving access to AI auditing tools, building public engagement capacity, fostering early community involvement to align AI innovations with public needs, and promoting accessible and inclusive participation in AI development. The workshop will feature two keynotes, two short paper sessions, and three discussion-oriented activities. Our goal is to create a platform for exchanging ideas and developing strategies to design community-engaged RAI systems while mitigating the potential harms of AI and maximizing its benefits in the public sector. 

Synthetic data is a useful resource for algorithmic research. It allows for the evaluation of systems under a range of conditions that might be difficult to achieve in real world settings. In recommender systems, the use of synthetic data is somewhat limited; some work has concentrated on building user-item interaction data at large scale. We believe that fairness-aware recommendation research can benefit from simulated data as it allows the study of protected groups and their interactions without depending on sensitive data that needs privacy protection. In this paper, we propose a novel type of data for fairness-aware recommendation: synthetic recommender system outputs that can be used to study re-ranking algorithms.