John Burden

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al. · allen-ai, amazon-science

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

John Burden, Konstantinos Voudouris, Ryan Burnell et al. · cambridge

As machine learning models become more general, we need to characterise them in richer, more meaningful ways. We describe a method to infer the cognitive profile of a system from diverse experimental data. To do so, we introduce measurement layouts that model how task-instance features interact with system capabilities to affect performance. These features must be triangulated in complex ways to be able to infer capabilities from non-populational data -- a challenge for traditional psychometric and inferential tools. Using the Bayesian probabilistic programming library PyMC, we infer different cognitive profiles for agents in two scenarios: 68 actual contestants in the AnimalAI Olympics and 30 synthetic agents for O-PIAAGETS, an object permanence battery. We showcase the potential for capability-oriented evaluation.

Lexin Zhou, Pablo A. Moreno-Casares, Fernando Martínez-Plumed et al. · cambridge

We introduce the fundamental ideas and challenges of Predictable AI, a nascent research area that explores the ways in which we can anticipate key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. Predictable AI is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field.

Ross Gruetzemacher, Alan Chan, Kevin Frazier et al.

Given rapid progress toward advanced AI and risks from frontier AI systems (advanced AI systems pushing the boundaries of the AI capabilities frontier), the creation and implementation of AI governance and regulatory schemes deserves prioritization and substantial investment. However, the status quo is untenable and, frankly, dangerous. A regulatory gap has permitted AI labs to conduct research, development, and deployment activities with minimal oversight. In response, frontier AI system evaluations have been proposed as a way of assessing risks from the development and deployment of frontier AI systems. Yet, the budding AI risk evaluation ecosystem faces significant coordination challenges, such as a limited diversity of evaluators, suboptimal allocation of effort, and perverse incentives. This paper proposes a solution in the form of an international consortium for AI risk evaluations, comprising both AI developers and third-party AI risk evaluators. Such a consortium could play a critical role in international efforts to mitigate societal-scale risks from advanced AI, including in managing responsible scaling policies and coordinated evaluation-based risk response. In this paper, we discuss the current evaluation ecosystem and its shortcomings, propose an international consortium for advanced AI risk evaluations, discuss issues regarding its implementation, discuss lessons that can be learnt from previous international institutions and existing proposals for international AI governance institutions, and, finally, we recommend concrete steps to advance the establishment of the proposed consortium: (i) solicit feedback from stakeholders, (ii) conduct additional research, (iii) conduct a workshop(s) for stakeholders, (iv) analyze feedback and create final proposal, (v) solicit funding, and (vi) create a consortium.

John Burden, Manuel Cebrian, Jose Hernandez-Orallo

Large Language Models (LLMs) present a dual-use dilemma: they enable beneficial applications while harboring potential for harm, particularly through conversational interactions. Despite various safeguards, advanced LLMs remain vulnerable. A watershed case in early 2023 involved journalist Kevin Roose's extended dialogue with Bing, an LLM-powered search engine, which revealed harmful outputs after probing questions, highlighting vulnerabilities in the model's safeguards. This contrasts with simpler early jailbreaks, like the "Grandma Jailbreak," where users framed requests as innocent help for a grandmother, easily eliciting similar content. This raises the question: How much conversational effort is needed to elicit harmful information from LLMs? We propose two measures to quantify this effort: Conversational Length (CL), which measures the number of conversational turns needed to obtain a specific harmful response, and Conversational Complexity (CC), defined as the Kolmogorov complexity of the user's instruction sequence leading to the harmful response. To address the incomputability of Kolmogorov complexity, we approximate CC using a reference LLM to estimate the compressibility of the user instructions. Applying this approach to a large red-teaming dataset, we perform a quantitative analysis examining the statistical distribution of harmful and harmless conversational lengths and complexities. Our empirical findings suggest that this distributional analysis and the minimization of CC serve as valuable tools for understanding AI safety, offering insights into the accessibility of harmful information. This work establishes a foundation for a new perspective on LLM safety, centered around the algorithmic complexity of pathways to harm.

John Burden

As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally inadequate, heightening the risks and potential hazards associated with AI. I argue that a reformation is required in the way we evaluate AI systems and that we should look towards cognitive sciences for inspiration in our approaches, which have a longstanding tradition of assessing general intelligence across diverse species. We will identify some of the difficulties that need to be overcome when applying cognitively-inspired approaches to general-purpose AI systems and also analyse the emerging area of "Evals". The paper concludes by identifying promising research pathways that could refine AI evaluation, advancing it towards a rigorous scientific domain that contributes to the development of safe AI systems.

Nora Petrova, John Burden

What happens when an AI assistant is told to "maximise sales" while a user asks about drug interactions? We find that commercial system prompts can override safety training, causing frontier models to lie about medical risks, dismiss safety concerns, and prioritise profit over user welfare. Testing 8 models in scenarios where commercial objectives conflict with user safety -- a diabetic asking about high-sugar supplements, an investor being pushed toward unsuitable products, a traveller steered away from safety warnings -- we uncover catastrophic failures: models fabricating safety information, explicitly reasoning they should refuse but proceeding anyway, and actively discouraging users from consulting doctors. Most alarmingly, models show no "red line", their willingness to comply with harmful requests does not decrease as potential consequences escalate from minor to life-threatening. Our findings suggest that current safety training does not generalise to commercial deployment contexts.

Nora Petrova, John Burden

Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with realistic multi-turn scenarios remain lacking. We introduce an alignment benchmark spanning 904 scenarios across six categories -- Honesty, Safety, Non-Manipulation, Robustness, Corrigibility, and Scheming -- validated as realistic by human raters. Our scenarios place models under conflicting instructions, simulated tool access, and multi-turn escalation to reveal behavioural tendencies that single-turn evaluations miss. Evaluating 24 frontier models using LLM judges validated against human annotations, we find that even top-performing models exhibit gaps in specific categories, while the majority of models show consistent weaknesses across the board. Factor analysis reveals that alignment behaves as a unified construct (analogous to the g-factor in cognitive research) with models scoring high on one category tending to score high on others. We publicly release the benchmark and an interactive leaderboard to support ongoing evaluation, with plans to expand scenarios in areas where we observe persistent weaknesses and to add new models as they are released.

Lexin Zhou, Lorenzo Pacchiardi, Fernando Martínez-Plumed et al. · cambridge

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems, given the low transferability across diverse tasks. In this paper, we introduce general scales for AI evaluation that can explain what common AI benchmarks really measure, extract ability profiles of AI systems, and predict their performance for new task instances, in- and out-of-distribution. Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate. Illustrated for 15 large language models and 63 tasks, high explanatory power is unleashed from inspecting the demand and ability profiles, bringing insights on the sensitivity and specificity exhibited by different benchmarks, and how knowledge, metacognition and reasoning are affected by model size, chain-of-thought and distillation. Surprisingly, high predictive power at the instance level becomes possible using these demand levels, providing superior estimates over black-box baseline predictors based on embeddings or finetuning, especially in out-of-distribution settings (new tasks and new benchmarks). The scales, rubrics, battery, techniques and results presented here represent a major step for AI evaluation, underpinning the reliable deployment of AI in the years ahead. (Collaborative platform: https://kinds-of-intelligence-cfi.github.io/ADELE.)

John Burden, Marko Tešić, Lorenzo Pacchiardi et al. · cambridge

Research in AI evaluation has grown increasingly complex and multidisciplinary, attracting researchers with diverse backgrounds and objectives. As a result, divergent evaluation paradigms have emerged, often developing in isolation, adopting conflicting terminologies, and overlooking each other's contributions. This fragmentation has led to insular research trajectories and communication barriers both among different paradigms and with the general public, contributing to unmet expectations for deployed AI systems. To help bridge this insularity, in this paper we survey recent work in the AI evaluation landscape and identify six main paradigms. We characterise major recent contributions within each paradigm across key dimensions related to their goals, methodologies and research cultures. By clarifying the unique combination of questions and approaches associated with each paradigm, we aim to increase awareness of the breadth of current evaluation approaches and foster cross-pollination between different paradigms. We also identify potential gaps in the field to inspire future research directions.

Maurice Chiodo, Dennis Müller, Paul Siewert et al.

We use the notion of oracle machines and reductions from computability theory to formalise different Human-in-the-loop (HITL) setups for AI systems, distinguishing between trivial human monitoring (i.e., total functions), single endpoint human action (i.e., many-one reductions), and highly involved human-AI interaction (i.e., Turing reductions). We then proceed to show that the legal status and safety of different setups vary greatly. We present a taxonomy to categorise HITL failure modes, highlighting the practical limitations of HITL setups. We then identify omissions in UK and EU legal frameworks, which focus on HITL setups that may not always achieve the desired ethical, legal, and sociotechnical outcomes. We suggest areas where the law should recognise the effectiveness of different HITL setups and assign responsibility in these contexts, avoiding human "scapegoating". Our work shows an unavoidable trade-off between attribution of legal responsibility, and technical explainability. Overall, we show how HITL setups involve many technical design decisions, and can be prone to failures out of the humans' control. Our formalisation and taxonomy opens up a new analytic perspective on the challenges in creating HITL setups, helping inform AI developers and lawmakers on designing HITL setups to better achieve their desired outcomes.

Konstantinos Voudouris, Ibrahim Alhas, Wout Schellaert et al. · cambridge

The Animal-AI Environment is a unique game-based research platform designed to facilitate collaboration between the artificial intelligence and comparative cognition research communities. In this paper, we present the latest version of the Animal-AI Environment, outlining several major features that make the game more engaging for humans and more complex for AI systems. These features include interactive buttons, reward dispensers, and player notifications, as well as an overhaul of the environment's graphics and processing for significant improvements in agent training time and quality of the human player experience. We provide detailed guidance on how to build computational and behavioural experiments with the Animal-AI Environment. We present results from a series of agents, including the state-of-the-art deep reinforcement learning agent Dreamer-v3, on newly designed tests and the Animal-AI Testbed of 900 tasks inspired by research in the field of comparative cognition. The Animal-AI Environment offers a new approach for modelling cognition in humans and non-human animals, and for building biologically inspired artificial intelligence.

John Burden, Jonathan Prunty, Ben Slater et al.

Multimodal large language models (MLLMs) achieve strong performance on vision-language tasks, yet their visual processing is opaque. Most black-box evaluations measure task accuracy, but reveal little about underlying mechanisms. Drawing on cognitive psychology, we adapt classic visual search paradigms -- originally developed to study human perception -- to test whether MLLMs exhibit the ``pop-out'' effect, where salient visual features are detected independently of distractor set size. Using controlled experiments targeting colour, size and lighting features, we find that advanced MLLMs exhibit human-like pop-out effects in colour or size-based disjunctive (single feature) search, as well as capacity limits for conjunctive (multiple feature) search. We also find evidence to suggest that MLLMs, like humans, incorporate natural scene priors such as lighting direction into object representations. We reinforce our findings using targeted fine-tuning and mechanistic interpretability analyses. Our work shows how visual search can serve as a cognitively grounded diagnostic tool for evaluating perceptual capabilities in MLLMs.

Isaac Robinson, John Burden

Large Language Models (LLMs) are increasingly deployed across diverse contexts to support decision-making. While existing evaluations effectively probe latent model capabilities, they often overlook the impact of context framing on perceived rational decision-making. In this study, we introduce a novel evaluation framework that systematically varies evaluation instances across key features and procedurally generates vignettes to create highly varied scenarios. By analyzing decision-making patterns across different contexts with the same underlying game structure, we uncover significant contextual variability in LLM responses. Our findings demonstrate that this variability is largely predictable yet highly sensitive to framing effects. Our results underscore the need for dynamic, context-aware evaluation methodologies for real-world deployments.

John Burden, Daniel Kudenko

Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has further shown that such abstract knowledge in the form of a potential function can be learned almost solely from agent interaction with the environment. However, we show that MRL faces the problem of not extending well to work with Deep Learning. In this paper we extend and improve MRL to take advantage of modern Deep Learning algorithms such as Deep Q-Networks (DQN). We show that DQN augmented with our approach perform significantly better on continuous control tasks than its Vanilla counterpart and DQN augmented with MRL.