Research Papers

Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members

Daphne Cornelisse, Thomas Rood, Mateusz Malinowski +2

In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of agents and allocating them shares of the reward that promote long-lasting cooperation are difficult tasks. Cooperative game theory offers solution concepts identifying distribution schemes, such as the Shapley value, that fairly reflect the contribution of individuals to the performance of the team or the Core, which reduces the incentive of agents to abandon their team. Applications of such methods include identifying influential features and sharing the costs of joint ventures or team formation. Unfortunately, using these solutions requires tackling a computational barrier as they are hard to compute, even in restricted settings. In this work, we show how cooperative game-theoretic solutions can be distilled into a learned model by training neural networks to propose fair and stable payoff allocations. We show that our approach creates models that can generalize to games far from the training distribution and can predict solutions for more players than observed during training. An important application of our framework is Explainable AI: our approach can be used to speed-up Shapley value computations on many instances.

Existing work on fairness modeling commonly assumes that sensitive attributes for all instances are fully available, which may not be true in many real-world applications due to the high cost of acquiring sensitive information. When sensitive attributes are not disclosed or available, it is needed to manually annotate a small part of the training data to mitigate bias. However, the skewed distribution across different sensitive groups preserves the skewness of the original dataset in the annotated subset, which leads to non-optimal bias mitigation. To tackle this challenge, we propose Active Penalization Of Discrimination (APOD), an interactive framework to guide the limited annotations towards maximally eliminating the effect of algorithmic bias. The proposed APOD integrates discrimination penalization with active instance selection to efficiently utilize the limited annotation budget, and it is theoretically proved to be capable of bounding the algorithmic bias. According to the evaluation on five benchmark datasets, APOD outperforms the state-of-the-arts baseline methods under the limited annotation budget, and shows comparable performance to fully annotated bias mitigation, which demonstrates that APOD could benefit real-world applications when sensitive information is limited.

Explainability in Mechanism Design: Recent Advances and the Road Ahead

Sharadhi Alape Suryanarayana, David Sarne, Sarit Kraus

Designing and implementing explainable systems is seen as the next step towards increasing user trust in, acceptance of and reliance on Artificial Intelligence (AI) systems. While explaining choices made by black-box algorithms such as machine learning and deep learning has occupied most of the limelight, systems that attempt to explain decisions (even simple ones) in the context of social choice are steadily catching up. In this paper, we provide a comprehensive survey of explainability in mechanism design, a domain characterized by economically motivated agents and often having no single choice that maximizes all individual utility functions. We discuss the main properties and goals of explainability in mechanism design, distinguishing them from those of Explainable AI in general. This discussion is followed by a thorough review of the challenges one may face when working on Explainable Mechanism Design and propose a few solution concepts to those.

Responsible AI Challenges in End-to-end Machine Learning

Steven Euijong Whang, Ki Hyun Tae, Yuji Roh +1

Responsible AI is becoming critical as AI is widely used in our everyday lives. Many companies that deploy AI publicly state that when training a model, we not only need to improve its accuracy, but also need to guarantee that the model does not discriminate against users (fairness), is resilient to noisy or poisoned data (robustness), is explainable, and more. In addition, these objectives are not only relevant to model training, but to all steps of end-to-end machine learning, which include data collection, data cleaning and validation, model training, model evaluation, and model management and serving. Finally, responsible AI is conceptually challenging, and supporting all the objectives must be as easy as possible. We thus propose three key research directions towards this vision - depth, breadth, and usability - to measure progress and introduce our ongoing research. First, responsible AI must be deeply supported where multiple objectives like fairness and robust must be handled together. To this end, we propose FR-Train, a holistic framework for fair and robust model training in the presence of data bias and poisoning. Second, responsible AI must be broadly supported, preferably in all steps of machine learning. Currently we focus on the data pre-processing steps and propose Slice Tuner, a selective data acquisition framework for training fair and accurate models, and MLClean, a data cleaning framework that also improves fairness and robustness. Finally, responsible AI must be usable where the techniques must be easy to deploy and actionable. We propose FairBatch, a batch selection approach for fairness that is effective and simple to use, and Slice Finder, a model evaluation tool that automatically finds problematic slices. We believe we scratched the surface of responsible AI for end-to-end machine learning and suggest research challenges moving forward.

The recent unprecedented popularity of food recommender applications has raised several issues related to the ethical, societal and legal implications of relying on these applications. In this paper, in order to assess the relevant ethical issues, we rely on the emerging principles across the AI\&Ethics community and define them tailored context specifically. Considering the popular Food Recommender Systems (henceforth F-RS) in the European market cannot be regarded as personalised F-RS, we show how merely this lack of feature shifts the relevance of the focal ethical concerns. We identify the major challenges and propose a scheme for how explicit ethical agendas should be explained. We also argue how a multi-stakeholder approach is indispensable to ensure producing long-term benefits for all stakeholders. After proposing eight ethical desiderata points for F-RS, we present a case-study and assess it based on our proposed desiderata points.

Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity

Kyra Wilson, Sourojit Ghosh, Aylin Caliskan

Text-to-image generators (T2Is) are liable to produce images that perpetuate social stereotypes, especially in regards to race or skin tone. We use a comprehensive set of 93 stigmatized identities to determine that three versions of Stable Diffusion (v1.5, v2.1, and XL) systematically associate stigmatized identities with certain skin tones in generated images. We find that SD XL produces skin tones that are 13.53% darker and 23.76% less red (both of which indicate higher likelihood of societal discrimination) than previous models and perpetuate societal stereotypes associating people of color with stigmatized identities. SD XL also shows approximately 30% less variability in skin tones when compared to previous models and 18.89-56.06% compared to human face datasets. Measuring variability through metrics which directly correspond to human perception suggest a similar pattern, where SD XL shows the least amount of variability in skin tones of people with stigmatized identities and depicts most (60.29%) stigmatized identities as being less diverse than non-stigmatized identities. Finally, SD shows more homogenization of skin tones of racial and ethnic identities compared to other stigmatized or non-stigmatized identities, reinforcing incorrect equivalence of biologically-determined skin tone and socially-constructed racial and ethnic identity. Because SD XL is the largest and most complex model and users prefer its generations compared to other models examined in this study, these findings have implications for the dynamics of bias amplification in T2Is, increasing representational harms and challenges generating diverse images depicting people with stigmatized identities.

Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems

Gordon Dai, Yunze Xiao

This position paper argues that the theoretical inconsistency often observed among Responsible AI (RAI) metrics, such as differing fairness definitions or tradeoffs between accuracy and privacy, should be embraced as a valuable feature rather than a flaw to be eliminated. We contend that navigating these inconsistencies, by treating metrics as divergent objectives, yields three key benefits: (1) Normative Pluralism: Maintaining a full suite of potentially contradictory metrics ensures that the diverse moral stances and stakeholder values inherent in RAI are adequately represented. (2) Epistemological Completeness: The use of multiple, sometimes conflicting, metrics allows for a more comprehensive capture of multifaceted ethical concepts, thereby preserving greater informational fidelity about these concepts than any single, simplified definition. (3) Implicit Regularization: Jointly optimizing for theoretically conflicting objectives discourages overfitting to one specific metric, steering models towards solutions with enhanced generalization and robustness under real-world complexities. In contrast, efforts to enforce theoretical consistency by simplifying or pruning metrics risk narrowing this value diversity, losing conceptual depth, and degrading model performance. We therefore advocate for a shift in RAI theory and practice: from getting trapped in inconsistency to characterizing acceptable inconsistency thresholds and elucidating the mechanisms that permit robust, approximated consistency in practice.

Physical attractiveness matters. It has been shown to influence human perception and decision-making, often leading to biased judgments that favor those deemed attractive in what is referred to as the "attractiveness halo effect". While extensively studied in human judgments in a broad set of domains, including hiring, judicial sentencing or credit granting, the role that attractiveness plays in the assessments and decisions made by multimodal large language models (MLLMs) is unknown. To address this gap, we conduct an empirical study with 7 diverse open-source MLLMs evaluated on 91 socially relevant scenarios and a diverse dataset of 924 face images - corresponding to 462 individuals both with and without beauty filters applied to them. Our analysis reveals that attractiveness impacts the decisions made by MLLMs in 86.2% of the scenarios on average, demonstrating substantial bias in model behavior in what we refer to as an attractiveness bias. Similarly to humans, we find empirical evidence of the existence of the attractiveness halo effect in 94.8% of the relevant scenarios: attractive individuals are more likely to be attributed positive traits, such as intelligence or confidence, by MLLMs than unattractive individuals. Furthermore, we uncover gender, age and race biases in a significant portion of the scenarios which are also impacted by attractiveness, particularly in the case of gender, highlighting the intersectional nature of the algorithmic attractiveness bias. Our findings suggest that societal stereotypes and cultural norms intersect with perceptions of attractiveness in MLLMs in a complex manner. Our work emphasizes the need to account for intersectionality in algorithmic bias detection and mitigation efforts and underscores the challenges of addressing biases in modern MLLMs.

Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures

Akhila Yerukola, Saadia Gabriel, Nanyun Peng +1

Gestures are an integral part of non-verbal communication, with meanings that vary across cultures, and misinterpretations that can have serious social and diplomatic consequences. As AI systems become more integrated into global applications, ensuring they do not inadvertently perpetuate cultural offenses is critical. To this end, we introduce Multi-Cultural Set of Inappropriate Gestures and Nonverbal Signs (MC-SIGNS), a dataset of 288 gesture-country pairs annotated for offensiveness, cultural significance, and contextual factors across 25 gestures and 85 countries. Through systematic evaluation using MC-SIGNS, we uncover critical limitations: text-to-image (T2I) systems exhibit strong US-centric biases, performing better at detecting offensive gestures in US contexts than in non-US ones; large language models (LLMs) tend to over-flag gestures as offensive; and vision-language models (VLMs) default to US-based interpretations when responding to universal concepts like wishing someone luck, frequently suggesting culturally inappropriate gestures. These findings highlight the urgent need for culturally-aware AI safety mechanisms to ensure equitable global deployment of AI technologies.

AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for disparate impact, it is crucial to ensure that these classifiers: (1) do not unfairly classify content belonging to users from minority groups as unsafe compared to those from majority groups and (2) that their behavior remains robust and consistent across similar inputs. In this work, we thus examine the fairness and robustness of four widely-used, closed-source ASM classifiers: OpenAI Moderation API, Perspective API, Google Cloud Natural Language (GCNL) API, and Clarifai API. We assess fairness using metrics such as demographic parity and conditional statistical parity, comparing their performance against ASM models and a fair-only baseline. Additionally, we analyze robustness by testing the classifiers' sensitivity to small and natural input perturbations. Our findings reveal potential fairness and robustness gaps, highlighting the need to mitigate these issues in future versions of these models.

This study introduces an integrated approach to recognizing Arabic Sign Language (ArSL) using state-of-the-art deep learning models such as MobileNetV3, ResNet50, and EfficientNet-B2. These models are further enhanced by explainable AI (XAI) techniques to boost interpretability. The ArSL2018 and RGB Arabic Alphabets Sign Language (AASL) datasets are employed, with EfficientNet-B2 achieving peak accuracies of 99.48\% and 98.99\%, respectively. Key innovations include sophisticated data augmentation methods to mitigate class imbalance, implementation of stratified 5-fold cross-validation for better generalization, and the use of Grad-CAM for clear model decision transparency. The proposed system not only sets new benchmarks in recognition accuracy but also emphasizes interpretability, making it suitable for applications in healthcare, education, and inclusive communication technologies.

Responsible AI principles provide ethical guidelines for developing AI systems, yet their practical implementation in software engineering lacks thorough investigation. Therefore, this study explores the practices and challenges faced by software practitioners in aligning with these principles. Through semi-structured interviews with 25 practitioners, we investigated their methods, concerns, and strategies for addressing Responsible AI in software development. Our findings reveal that while practitioners frequently address fairness, inclusiveness, and reliability, principles such as transparency and accountability receive comparatively less attention in their practices. This scenario highlights gaps in current strategies and the need for more comprehensive frameworks to fully operationalize Responsible AI principles in software engineering.