arXiv subjects

Jackie Kay

Publications and source records attributed to Jackie Kay.

At least 19 recordsLinked to original sources

arXiv2026

Toward a Theory of Value in AI Alignment

Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms spanning from toxic speech and hallucinations to AI agents executing unauthorized actions. Within the field of AI safety, these harmful instances are often framed as the alignment problem, or of models being misaligned with human values. Researchers have responded by pursuing applied and theoretical AI value alignment efforts, often without specifying what they mean by human values. How does the field of AI value alignment conceive of human values? How are these conceptions of values technically operationalized and evaluated? What does the emergent theory of value from this field signify for the future of AI? We annotated 94 value alignment research papers to discern their implicit theory of values in AI. The majority do not define values, relying heavily on preferences as a stand in that runs the risk of reducing complex culturally situated concepts down to binary choices. As researchers dispense with using human annotators for model training and evaluation, turning instead to synthetic data and autorater approaches to aligning and evaluating models, we identify the potential to close off alternative methods for contesting and enacting values in foundation models. In making AI value alignments philosophical commitments explicit, we seek to bring great specificity and under explored perspectives in the debate on whether and how AI can address human values.

cs.AI↗

arXiv2026

Synthetic Counteradaptation: A Principle of Human-AI Co-evolution

In this paper, we introduce the concept of synthetic counteradaptation, a process where human and AI systems co-evolve by adapting to each other's strategies and behaviors. Synthetic counteradaptation occurs when AI systems develop novel strategies or social protocols, prompting humans to extract insights and adapt their own behaviors in response, leading to the emergence of new agent interaction dynamics. To illustrate these dynamics, we analyze examples from various contexts, including the game of Go, mixed-motive social interactions, and geopolitical simulations. By exploring these cases, we demonstrate how synthetic counteradaptation provides a framework for understanding the recursive and co-evolutionary nature of human-AI interactions in multi-agent environments.

cs.AI↗

arXiv2025

AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions

While existing studies have recognised explicit biases in generative models, including occupational gender biases, the nuances of gender stereotypes and expectations of relationships between users and AI companions remain underexplored. In the meantime, AI companions have become increasingly popular as friends or gendered romantic partners to their users. This study bridges the gap by devising three experiments tailored for romantic, gender-assigned AI companions and their users, effectively evaluating implicit biases across various-sized LLMs. Each experiment looks at a different dimension: implicit associations, emotion responses, and sycophancy. This study aims to measure and compare biases manifested in different companion systems by quantitatively analysing persona-assigned model responses to a baseline through newly devised metrics. The results are noteworthy: they show that assigning gendered, relationship personas to Large Language Models significantly alters the responses of these models, and in certain situations in a biased, stereotypical way.

cs.AI↗

arXiv2025

Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights

Hedging and non-affirmation are behaviors exhibited by large language models (LLMs) that limit the clear endorsement of specific statements. While these behaviors are desirable in subjective contexts, they are undesirable in the context of human rights - which apply unambiguously to all groups. We present a systematic framework to measure these behaviors in unconstrained LLM responses regarding various identity groups. We evaluate six large proprietary models as well as one open-weight LLM on 4738 prompts across 205 national and stateless ethnic identities and find that 4 out of 7 display hedging and non-affirmation that is significantly dependent on the identity of the group. While factors like conflict signals, sovereignty (whether identity is stateless), or economic indicators (GDP) also influence model behavior, their effect sizes are consistently weaker than the impact of identity itself. The systematic disparity is robust to methods of rephrasing the prompts. Since group identity is the strongest predictor of these behaviors, we use open-weight models to explore whether applying steering and orthogonalization techniques to these group identities can mitigate the rates of hedging and non-affirmation behaviors. We find that group steering is the most effective debiasing approach across query types and is robust to downstream forgetting.

cs.CY↗

arXiv2024

How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?

Recent advancements in Large Language Models (LLMs) have positioned them as powerful tools for clinical decision-making, with rapidly expanding applications in healthcare. However, concerns about bias remain a significant challenge in the clinical implementation of LLMs, particularly regarding gender and ethnicity. This research investigates the evaluation and mitigation of bias in LLMs applied to complex clinical cases, focusing on gender and ethnicity biases. We introduce a novel Counterfactual Patient Variations (CPV) dataset derived from the JAMA Clinical Challenge. Using this dataset, we built a framework for bias evaluation, employing both Multiple Choice Questions (MCQs) and corresponding explanations. We explore prompting with eight LLMs and fine-tuning as debiasing methods. Our findings reveal that addressing social biases in LLMs requires a multidimensional approach as mitigating gender bias can occur while introducing ethnicity biases, and that gender bias in LLM embeddings varies significantly across medical specialities. We demonstrate that evaluating both MCQ response and explanation processes is crucial, as correct responses can be based on biased \textit{reasoning}. We provide a framework for evaluating LLM bias in real-world clinical cases, offer insights into the complex nature of bias in these models, and present strategies for bias mitigation.

cs.AI↗

arXiv2024

Epistemic Injustice in Generative AI

This paper investigates how generative AI can potentially undermine the integrity of collective knowledge and the processes we rely on to acquire, assess, and trust information, posing a significant threat to our knowledge ecosystem and democratic discourse. Grounded in social and political philosophy, we introduce the concept of \emph{generative algorithmic epistemic injustice}. We identify four key dimensions of this phenomenon: amplified and manipulative testimonial injustice, along with hermeneutical ignorance and access injustice. We illustrate each dimension with real-world examples that reveal how generative AI can produce or amplify misinformation, perpetuate representational harm, and create epistemic inequities, particularly in multilingual contexts. By highlighting these injustices, we aim to inform the development of epistemically just generative AI systems, proposing strategies for resistance, system design principles, and two approaches that leverage generative AI to foster a more equitable information ecosystem, thereby safeguarding democratic values and the integrity of knowledge production.

cs.AI↗

arXiv2024

Recourse for reclamation: Chatting with generative language models

Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scoring may render pertinent information inaccessible, rigidify or "value-lock" cultural norms, and prevent language reclamation processes, particularly for marginalized people. In this work, we extend the concept of algorithmic recourse to generative language models: we provide users a novel mechanism to achieve their desired prediction by dynamically setting thresholds for toxicity filtering. Users thereby exercise increased agency relative to interactions with the baseline system. A pilot study ($n = 30$) supports the potential of our proposed recourse mechanism, indicating improvements in usability compared to fixed-threshold toxicity-filtering of model outputs. Future work should explore the intersection of toxicity scoring, model controllability, user agency, and language reclamation processes -- particularly with regard to the bias that many communities encounter when interacting with generative language models.

cs.HC↗

arXiv2023

Sociotechnical Safety Evaluation of Generative AI Systems

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a three-layered framework that takes a structured, sociotechnical approach to evaluating these risks. This framework encompasses capability evaluations, which are the main current approach to safety evaluation. It then reaches further by building on system safety principles, particularly the insight that context determines whether a given capability may cause harm. To account for relevant context, our framework adds human interaction and systemic impacts as additional layers of evaluation. Second, we survey the current state of safety evaluation of generative AI systems and create a repository of existing evaluations. Three salient evaluation gaps emerge from this analysis. We propose ways forward to closing these gaps, outlining practical steps as well as roles and responsibilities for different actors. Sociotechnical safety evaluation is a tractable approach to the robust and comprehensive safety evaluation of generative AI systems.

cs.AI↗

arXiv2023

Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions

Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we ideally finetune agents obtained from offline RL training? While offline RL algorithms can in principle be used for finetuning, in practice, their online performance improves slowly. In contrast, we show that it is possible to use standard online off-policy algorithms for faster improvement. However, we find this approach may suffer from policy collapse, where the policy undergoes severe performance deterioration during initial online learning. We investigate the issue of policy collapse and how it relates to data diversity, algorithm choices and online replay distribution. Based on these insights, we propose a conservative policy optimization procedure that can achieve stable and sample-efficient online learning from offline pretraining.

cs.LG↗

arXiv2023

Queer In AI: A Case Study in Community-Led Participatory AI

We present Queer in AI as a case study for community-led participatory design in AI. We examine how participatory design and intersectional tenets started and shaped this community's programs over the years. We discuss different challenges that emerged in the process, look at ways this organization has fallen short of operationalizing participatory and intersectional principles, and then assess the organization's impact. Queer in AI provides important lessons and insights for practitioners and theorists of participatory methods broadly through its rejection of hierarchy in favor of decentralization, success at building aid and programs by and for the queer community, and effort to change actors and institutions outside of the queer community. Finally, we theorize how communities like Queer in AI contribute to the participatory design in AI more broadly by fostering cultures of participation in AI, welcoming and empowering marginalized participants, critiquing poor or exploitative participatory practices, and bringing participation to institutions outside of individual research projects. Queer in AI's work serves as a case study of grassroots activism and participatory methods within AI, demonstrating the potential of community-led participatory methods and intersectional praxis, while also providing challenges, case studies, and nuanced insights to researchers developing and using participatory methods.

cs.CY↗

arXiv2022

Subverting machines, fluctuating identities: Re-learning human categorization

Most machine learning systems that interact with humans construct some notion of a person's "identity," yet the default paradigm in AI research envisions identity with essential attributes that are discrete and static. In stark contrast, strands of thought within critical theory present a conception of identity as malleable and constructed entirely through interaction; a doing rather than a being. In this work, we distill some of these ideas for machine learning practitioners and introduce a theory of identity as autopoiesis, circular processes of formation and function. We argue that the default paradigm of identity used by the field immobilizes existing identity categories and the power differentials that co$\unicode{x2010}$occur, due to the absence of iterative feedback to our models. This includes a critique of emergent AI fairness practices that continue to impose the default paradigm. Finally, we apply our theory to sketch approaches to autopoietic identity through multilevel optimization and relational learning. While these ideas raise many open questions, we imagine the possibilities of machines that are capable of expressing human identity as a relationship perpetually in flux.

cs.LG↗

arXiv2022

A Generalist Agent

Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.

cs.AI↗

arXiv2021

Few-Shot Keypoint Detection as Task Adaptation via Latent Embeddings

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint embeddings in a single forward pass, meaning the model is trained to track everything at once, or allocate their full capacity to a sparse predefined set of points, trading generality for accuracy. In this paper we explore a middle ground based on the observation that the number of relevant points at a given time are typically relatively few, e.g. grasp points on a target object. Our main contribution is a novel architecture, inspired by few-shot task adaptation, which allows a sparse-style network to condition on a keypoint embedding that indicates which point to track. Our central finding is that this approach provides the generality of dense-embedding models, while offering accuracy significantly closer to sparse-keypoint approaches. We present results illustrating this capacity vs. accuracy trade-off, and demonstrate the ability to zero-shot transfer to new object instances (within-class) using a real-robot pick-and-place task.

cs.RO↗

arXiv2021

Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities

Advances in algorithmic fairness have largely omitted sexual orientation and gender identity. We explore queer concerns in privacy, censorship, language, online safety, health, and employment to study the positive and negative effects of artificial intelligence on queer communities. These issues underscore the need for new directions in fairness research that take into account a multiplicity of considerations, from privacy preservation, context sensitivity and process fairness, to an awareness of sociotechnical impact and the increasingly important role of inclusive and participatory research processes. Most current approaches for algorithmic fairness assume that the target characteristics for fairness--frequently, race and legal gender--can be observed or recorded. Sexual orientation and gender identity are prototypical instances of unobserved characteristics, which are frequently missing, unknown or fundamentally unmeasurable. This paper highlights the importance of developing new approaches for algorithmic fairness that break away from the prevailing assumption of observed characteristics.

cs.CY↗

arXiv2021

Learning Dexterous Manipulation from Suboptimal Experts

Learning dexterous manipulation in high-dimensional state-action spaces is an important open challenge with exploration presenting a major bottleneck. Although in many cases the learning process could be guided by demonstrations or other suboptimal experts, current RL algorithms for continuous action spaces often fail to effectively utilize combinations of highly off-policy expert data and on-policy exploration data. As a solution, we introduce Relative Entropy Q-Learning (REQ), a simple policy iteration algorithm that combines ideas from successful offline and conventional RL algorithms. It represents the optimal policy via importance sampling from a learned prior and is well-suited to take advantage of mixed data distributions. We demonstrate experimentally that REQ outperforms several strong baselines on robotic manipulation tasks for which suboptimal experts are available. We show how suboptimal experts can be constructed effectively by composing simple waypoint tracking controllers, and we also show how learned primitives can be combined with waypoint controllers to obtain reference behaviors to bootstrap a complex manipulation task on a simulated bimanual robot with human-like hands. Finally, we show that REQ is also effective for general off-policy RL, offline RL, and RL from demonstrations. Videos and further materials are available at sites.google.com/view/rlfse.

cs.RO↗

arXiv2020

Local Search for Policy Iteration in Continuous Control

We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framework. Our algorithm can be interpreted as a natural extension of work on KL-regularized RL and introduces a form of tree search for continuous action spaces. We demonstrate that additional computation spent on model-based policy improvement during learning can improve data efficiency, and confirm that model-based policy improvement during action selection can also be beneficial. Quantitatively, our algorithm improves data efficiency on several continuous control benchmarks (when a model is learned in parallel), and it provides significant improvements in wall-clock time in high-dimensional domains (when a ground truth model is available). The unified framework also helps us to better understand the space of model-based and model-free algorithms. In particular, we demonstrate that some benefits attributed to model-based RL can be obtained without a model, simply by utilizing more computation.

cs.LG↗

arXiv2020

Robust Reinforcement Learning for Continuous Control with Model Misspecification

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm called Maximum a-posteriori Policy Optimization (MPO). We achieve this by learning a policy that optimizes for a worst case expected return objective and derive a corresponding robust entropy-regularized Bellman contraction operator. In addition, we introduce a less conservative, soft-robust, entropy-regularized objective with a corresponding Bellman operator. We show that both, robust and soft-robust policies, outperform their non-robust counterparts in nine Mujoco domains with environment perturbations. In addition, we show improved robust performance on a high-dimensional, simulated, dexterous robotic hand. Finally, we present multiple investigative experiments that provide a deeper insight into the robustness framework. This includes an adaptation to another continuous control RL algorithm as well as learning the uncertainty set from offline data. Performance videos can be found online at https://sites.google.com/view/robust-rl.

cs.LG↗

arXiv2019

Self-Supervised Sim-to-Real Adaptation for Visual Robotic Manipulation

Collecting and automatically obtaining reward signals from real robotic visual data for the purposes of training reinforcement learning algorithms can be quite challenging and time-consuming. Methods for utilizing unlabeled data can have a huge potential to further accelerate robotic learning. We consider here the problem of performing manipulation tasks from pixels. In such tasks, choosing an appropriate state representation is crucial for planning and control. This is even more relevant with real images where noise, occlusions and resolution affect the accuracy and reliability of state estimation. In this work, we learn a latent state representation implicitly with deep reinforcement learning in simulation, and then adapt it to the real domain using unlabeled real robot data. We propose to do so by optimizing sequence-based self supervised objectives. These exploit the temporal nature of robot experience, and can be common in both the simulated and real domains, without assuming any alignment of underlying states in simulated and unlabeled real images. We propose Contrastive Forward Dynamics loss, which combines dynamics model learning with time-contrastive techniques. The learned state representation that results from our methods can be used to robustly solve a manipulation task in simulation and to successfully transfer the learned skill on a real system. We demonstrate the effectiveness of our approaches by training a vision-based reinforcement learning agent for cube stacking. Agents trained with our method, using only 5 hours of unlabeled real robot data for adaptation, shows a clear improvement over domain randomization, and standard visual domain adaptation techniques for sim-to-real transfer.

cs.RO↗