Research Papers

Fairness auditing of AI systems can identify and quantify biases. However, traditional auditing using real-world data raises security and privacy concerns. It exposes auditors to security risks as they become custodians of sensitive information and targets for cyberattacks. Privacy risks arise even without direct breaches, as data analyses can inadvertently expose confidential information. To address these, we propose a framework that leverages differentially private synthetic data to audit the fairness of AI systems. By applying privacy-preserving mechanisms, it generates synthetic data that mirrors the statistical properties of the original dataset while ensuring privacy. This method balances the goal of rigorous fairness auditing and the need for strong privacy protections. Through experiments on real datasets like Adult, COMPAS, and Diabetes, we compare fairness metrics of synthetic and real data. By analyzing the alignment and discrepancies between these metrics, we assess the capacity of synthetic data to preserve the fairness properties of real data. Our results demonstrate the framework's ability to enable meaningful fairness evaluations while safeguarding sensitive information, proving its applicability across critical and sensitive domains.

RAIL in the Wild: Operationalizing Responsible AI Evaluation Using Anthropic's Value Dataset

Sumit Verma, Pritam Prasun, Arpit Jaiswal +1

As AI systems become embedded in real-world applications, ensuring they meet ethical standards is crucial. While existing AI ethics frameworks emphasize fairness, transparency, and accountability, they often lack actionable evaluation methods. This paper introduces a systematic approach using the Responsible AI Labs (RAIL) framework, which includes eight measurable dimensions to assess the normative behavior of large language models (LLMs). We apply this framework to Anthropic's "Values in the Wild" dataset, containing over 308,000 anonymized conversations with Claude and more than 3,000 annotated value expressions. Our study maps these values to RAIL dimensions, computes synthetic scores, and provides insights into the ethical behavior of LLMs in real-world use.

This paper establishes a theoretical foundation for understanding the fundamental limits of AI explainability through algorithmic information theory. We formalize explainability as the approximation of complex models by simpler ones, quantifying both approximation error and explanation complexity using Kolmogorov complexity. Our key theoretical contributions include: (1) a complexity gap theorem proving that any explanation significantly simpler than the original model must differ from it on some inputs; (2) precise bounds showing that explanation complexity grows exponentially with input dimension but polynomially with error tolerance for Lipschitz functions; and (3) a characterization of the gap between local and global explainability, demonstrating that local explanations can be significantly simpler while maintaining accuracy in relevant regions. We further establish a regulatory impossibility theorem proving that no governance framework can simultaneously pursue unrestricted AI capabilities, human-interpretable explanations, and negligible error. These results highlight considerations likely to be relevant to the design, evaluation, and oversight of explainable AI systems.

Human action recognition (HAR) has achieved impressive results with deep learning models, but their decision-making process remains opaque due to their black-box nature. Ensuring interpretability is crucial, especially for real-world applications requiring transparency and accountability. Existing video XAI methods primarily rely on feature attribution or static textual concepts, both of which struggle to capture motion dynamics and temporal dependencies essential for action understanding. To address these challenges, we propose Pose Concept Bottleneck for Explainable Action Recognition (PCBEAR), a novel concept bottleneck framework that introduces human pose sequences as motion-aware, structured concepts for video action recognition. Unlike methods based on pixel-level features or static textual descriptions, PCBEAR leverages human skeleton poses, which focus solely on body movements, providing robust and interpretable explanations of motion dynamics. We define two types of pose-based concepts: static pose concepts for spatial configurations at individual frames, and dynamic pose concepts for motion patterns across multiple frames. To construct these concepts, PCBEAR applies clustering to video pose sequences, allowing for automatic discovery of meaningful concepts without manual annotation. We validate PCBEAR on KTH, Penn-Action, and HAA500, showing that it achieves high classification performance while offering interpretable, motion-driven explanations. Our method provides both strong predictive performance and human-understandable insights into the model's reasoning process, enabling test-time interventions for debugging and improving model behavior.

In the landscape of Fact-based Judgment Prediction and Explanation (FJPE), reliance on factual data is essential for developing robust and realistic AI-driven decision-making tools. This paper introduces TathyaNyaya, the largest annotated dataset for FJPE tailored to the Indian legal context, encompassing judgments from the Supreme Court of India and various High Courts. Derived from the Hindi terms "Tathya" (fact) and "Nyaya" (justice), the TathyaNyaya dataset is uniquely designed to focus on factual statements rather than complete legal texts, reflecting real-world judicial processes where factual data drives outcomes. Complementing this dataset, we present FactLegalLlama, an instruction-tuned variant of the LLaMa-3-8B Large Language Model (LLM), optimized for generating high-quality explanations in FJPE tasks. Finetuned on the factual data in TathyaNyaya, FactLegalLlama integrates predictive accuracy with coherent, contextually relevant explanations, addressing the critical need for transparency and interpretability in AI-assisted legal systems. Our methodology combines transformers for binary judgment prediction with FactLegalLlama for explanation generation, creating a robust framework for advancing FJPE in the Indian legal domain. TathyaNyaya not only surpasses existing datasets in scale and diversity but also establishes a benchmark for building explainable AI systems in legal analysis. The findings underscore the importance of factual precision and domain-specific tuning in enhancing predictive performance and interpretability, positioning TathyaNyaya and FactLegalLlama as foundational resources for AI-assisted legal decision-making.

The governance of frontier artificial intelligence (AI) systems--particularly those capable of catastrophic misuse or systemic failure--requires institutional structures that are robust, adaptive, and innovation-preserving. This paper proposes a novel framework for governing such high-stakes models through a three-tiered insurance architecture: (1) mandatory private liability insurance for frontier model developers; (2) an industry-administered risk pool to absorb recurring, non-catastrophic losses; and (3) federally backed reinsurance for tail-risk events. Drawing from historical precedents in nuclear energy (Price-Anderson), terrorism risk (TRIA), agricultural crop insurance, flood reinsurance, and medical malpractice, the proposal shows how the federal government can stabilize private AI insurance markets without resorting to brittle regulation or predictive licensing regimes. The structure aligns incentives between AI developers and downstream stakeholders, transforms safety practices into insurable standards, and enables modular oversight through adaptive eligibility criteria. By focusing on risk-transfer mechanisms rather than prescriptive rules, this framework seeks to render AI safety a structural feature of the innovation ecosystem itself--integrated into capital markets, not external to them. The paper concludes with a legal and administrative feasibility analysis, proposing avenues for statutory authorization and agency placement within existing federal structures.

The desirable properties of explanations in information systems have fueled the demands for transparency in artificial intelligence (AI) outputs. To address these demands, the field of explainable AI (XAI) has put forth methods that can support human decision-making by explaining AI outputs. However, current empirical works present inconsistent findings on whether such explanations help to improve users' task performance in decision support systems (DSS). In this paper, we conduct a meta-analysis to explore how XAI affects human performance in classification tasks. Our results show an improvement in task performance through XAI-based decision support, though explanations themselves are not the decisive driver for this improvement. The analysis reveals that the studies' risk of bias moderates the effect of explanations in AI, while the explanation type appears to play only a negligible role. Our findings contribute to the human computer interaction field by enhancing the understanding of human-XAI collaboration in DSS.

Dubito Ergo Sum: Exploring AI Ethics

Viktor Dorfler, Giles Cuthbert

We paraphrase Descartes' famous dictum in the area of AI ethics where the "I doubt and therefore I am" is suggested as a necessary aspect of morality. Therefore AI, which cannot doubt itself, cannot possess moral agency. Of course, this is not the end of the story. We explore various aspects of the human mind that substantially differ from AI, which includes the sensory grounding of our knowing, the act of understanding, and the significance of being able to doubt ourselves. The foundation of our argument is the discipline of ethics, one of the oldest and largest knowledge projects of human history, yet, we seem only to be beginning to get a grasp of it. After a couple of thousand years of studying the ethics of humans, we (humans) arrived at a point where moral psychology suggests that our moral decisions are intuitive, and all the models from ethics become relevant only when we explain ourselves. This recognition has a major impact on what and how we can do regarding AI ethics. We do not offer a solution, we explore some ideas and leave the problem open, but we hope somewhat better understood than before our study.

This review systematically examines deep learning applications in financial asset management. Unlike prior reviews, this study focuses on identifying emerging trends, such as the integration of explainable artificial intelligence (XAI) and deep reinforcement learning (DRL), and their transformative potential. It highlights new developments, including hybrid models (e.g., transformer-based architectures) and the growing use of alternative data sources such as ESG indicators and sentiment analysis. These advancements challenge traditional financial paradigms and set the stage for a deeper understanding of the evolving landscape. We use the Scopus database to select the most relevant articles published from 2018 to 2023. The inclusion criteria encompassed articles that explicitly apply deep learning models within financial asset management. We excluded studies focused on physical assets. This review also outlines our methodology for evaluating the relevance and impact of the included studies, including data sources and analytical methods. Our search identified 934 articles, with 612 meeting the inclusion criteria based on their focus and methodology. The synthesis of results from these articles provides insights into the effectiveness of deep learning models in improving portfolio performance and price forecasting accuracy. The review highlights the broad applicability and potential enhancements deep learning offers to financial asset management. Despite some limitations due to the scope of model application and variation in methodological rigour, the overall evidence supports deep learning as a valuable tool in this field. Our systematic review underscores the progressive integration of deep learning in financial asset management, suggesting a trajectory towards more sophisticated and impactful applications.

Cerebral Palsy (CP) is a prevalent motor disability in children, for which early detection can significantly improve treatment outcomes. While skeleton-based Graph Convolutional Network (GCN) models have shown promise in automatically predicting CP risk from infant videos, their "black-box" nature raises concerns about clinical explainability. To address this, we introduce a perturbation framework tailored for infant movement features and use it to compare two explainable AI (XAI) methods: Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM). First, we identify significant and non-significant body keypoints in very low- and very high-risk infant video snippets based on the XAI attribution scores. We then conduct targeted velocity and angular perturbations, both individually and in combination, on these keypoints to assess how the GCN model's risk predictions change. Our results indicate that velocity-driven features of the arms, hips, and legs have a dominant influence on CP risk predictions, while angular perturbations have a more modest impact. Furthermore, CAM and Grad-CAM show partial convergence in their explanations for both low- and high-risk CP groups. Our findings demonstrate the use of XAI-driven movement analysis for early CP prediction and offer insights into potential movement-based biomarker discovery that warrant further clinical validation.

AI ethics narratives have the potential to shape the public accurate understanding of AI technologies and promote communication among different stakeholders. However, AI ethics narratives are largely lacking. Existing limited narratives tend to center on works of science fiction or corporate marketing campaigns of large technology companies. Misuse of "socio-technical imaginary" can blur the line between speculation and reality for the public, undermining the responsibility and regulation of technology development. Therefore, constructing authentic AI ethics narratives is an urgent task. The emergence of generative AI offers new possibilities for building narrative systems. This study is dedicated to data-driven visual storytelling about AI ethics relying on the human-AI collaboration. Based on the five key elements of story models, we proposed a conceptual framework for human-AI collaboration, explored the roles of generative AI and humans in the creation of visual stories. We implemented the conceptual framework in a real AI news case. This research leveraged advanced generative AI technologies to provide a reference for constructing genuine AI ethics narratives. Our goal is to promote active public engagement and discussions through authentic AI ethics narratives, thereby contributing to the development of better AI policies.

Ensuring that AI systems make strategic decisions aligned with the specified preferences in adversarial sequential interactions is a critical challenge for developing trustworthy AI systems, especially when the environment is stochastic and players' incomplete preferences leave some outcomes unranked. We study the problem of synthesizing preference-satisfying strategies in two-player stochastic games on graphs where players have opposite (possibly incomplete) preferences over a set of temporal goals. We represent these goals using linear temporal logic over finite traces (LTLf), which enables modeling the nuances of human preferences where temporal goals need not be mutually exclusive and comparison between some goals may be unspecified. We introduce a solution concept of non-dominated almost-sure winning, which guarantees to achieve a most preferred outcome aligned with specified preferences while maintaining robustness against the adversarial behaviors of the opponent. Our results show that strategy profiles based on this concept are Nash equilibria in the game where players are risk-averse, thus providing a practical framework for evaluating and ensuring stable, preference-aligned outcomes in the game. Using a drone delivery example, we demonstrate that our contributions offer valuable insights not only for synthesizing rational behavior under incomplete preferences but also for designing games that motivate the desired behavior from the players in adversarial conditions.