Search for: All records

Today’s artificial intelligence (AI) systems rely heavily on Artificial Neural Networks (ANNs), yet their black box nature induces risk of catastrophic failure and harm. In order to promote verifiably safe AI, my research will determine constraints on incentives from a game-theoretic perspective, tie those constraints to moral knowledge as represented by a knowledge graph, and reveal how neural models meet those constraints with novel interpretability methods. Specifically, I will develop techniques for describing models’ decision-making processes by predicting and isolating their goals, especially in relation to values derived from knowledge graphs. My research will allow critical AI systems to be audited in service of effective regulation. 

There is a substantial and ever-growing corpus of evidence and literature exploring the impacts of Artificial intelligence (AI) technologies on society, politics, and humanity as a whole. A separate, parallel body of work has explored existential risks to humanity, including but not limited to that stemming from unaligned Artificial General Intelligence (AGI). In this paper, we problematise the notion that current and near-term artificial intelligence technologies have the potential to contribute to existential risk by acting as intermediate risk factors, and that this potential is not limited to the unaligned AGI scenario. We propose the hypothesis that certain already-documented effects of AI can act as existential risk factors, magnifying the likelihood of previously identified sources of existential risk. Moreover, future developments in the coming decade hold the potential to significantly exacerbate these risk factors, even in the absence of artificial general intelligence. Our main contribution is a (non-exhaustive) exposition of potential AI risk factors and the causal relationships between them, focusing on how AI can affect power dynamics and information security. This exposition demonstrates that there exist causal pathways from AI systems to existential risks that do not presuppose hypothetical future AI capabilities. 

Journalists, fact-checkers, academics, and community media are overwhelmed in their attempts to support communities suffering from gender-, race- and ethnicity-targeted information ecosystem threats, including but not limited to misinformation, hate speech, weaponized controversy and online-to-offline harassment. Yet, for a plethora of reasons, minoritized groups are underserved by current approaches to combat such threats. In this panel, we will present and discuss the challenges and open problems facing such communities and the researchers hoping to serve them. We will also discuss the current state-of-the-art as well as the most promising future directions, both within IR specifically, across Computer Science more broadly, as well as that requiring transdisciplinary and cross-sectoral collaborations. The panel will attract both IR practitioners and researchers and include at least one panelist outside of IR, with unique expertise in this space. 

Growing concerns about the AI alignment problem have emerged in recent years, with previous work focusing mostly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing on either a single agent or on humanity as a singular unit. However, the field as a whole lacks a systematic understanding of how to specify, describe and analyze misalignment among entities, which may include individual humans, AI agents, and complex compositional entities such as corporations, nation-states, and so forth. Prior work on controversy in computational social science offers a mathematical model of contention among populations (of humans). In this paper, we adapt this contention model to the alignment problem, and show how viewing misalignment can vary depending on the population of agents (human or otherwise) being observed as well as the domain or "problem area" in question. Our model departs from value specification approaches and focuses instead on the morass of complex, interlocking, sometimes contradictory goals that agents may have in practice. We discuss the implications of our model and leave more thorough verification for future work. 

Most Fairness in AI research focuses on exposing biases in AI systems. A broader lens on fairness reveals that AI can serve a greater aspiration: rooting out societal inequities from their source. Specifically, we focus on inequities in health information, and aim to reduce bias in that domain using AI. The AI algorithms under the hood of search engines and social media, many of which are based on recommender systems, have an outsized impact on the quality of medical and health information online. Therefore, embedding bias detection and reduction into these recommender systems serving up medical and health content online could have an outsized positive impact on patient outcomes and wellbeing. In this position paper, we offer the following contributions: (1) we propose a novel framework of Fairness via AI, inspired by insights from medical education, sociology and antiracism; (2) we define a new term, bisinformation, which is related to, but distinct from, misinformation, and encourage researchers to study it; (3) we propose using AI to study, detect and mitigate biased, harmful, and/or false health information that disproportionately hurts minority groups in society; and (4) we suggest several pillars and pose several open problems in order to seed inquiry inthis new space. While part (3) of this work specifically focuses on the health domain, the fundamental computer science advances and contributions stemming from research efforts in bias reduction and Fairness via AI have broad implications in all areas of society.