Related papers: Models That Know How Evaluations Are Designed Scor…
Multi-modal Large Language Models (MLLMs) have achieved remarkable performance across a wide range of visual reasoning tasks, yet their vulnerability to safety risks remains a pressing concern. While prior research primarily focuses on…
Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work defines memorisation as the causal effect of training with an…
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…
Online memes are a powerful yet challenging medium for content moderation, often masking harmful intent behind humor, irony, or cultural symbolism. Conventional moderation systems "especially those relying on explicit text" frequently fail…
Artificial intelligence (AI) systems are deployed as collaborators in human decision-making. Yet, evaluation practices focus primarily on model accuracy rather than whether human-AI teams are prepared to collaborate safely and effectively.…
A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of generalisation. In…
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…
AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they…
Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a…
Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…
With state-of-the-art models achieving high performance on standard benchmarks, contemporary research paradigms continue to emphasize general intelligence as an enduring objective. However, this pursuit overlooks the fundamental disparities…
Gender-based violence is a pervasive public health issue that severely impacts women's mental health, often leading to conditions such as in anxiety, depression, post-traumatic stress disorder, and substance abuse. Identifying the…
Now that AI-driven moderation has become pervasive in everyday life, we often hear claims that "the AI is biased". While this is often said jokingly, the light-hearted remark reflects a deeper concern. How can we be certain that an online…
Developing large language models is expensive and involves making decisions with small experiments, typically by evaluating on large, multi-task evaluation suites. In this work, we analyze specific properties which make a benchmark more…
In this paper, we develop the position that current frameworks for evaluating emotional intelligence (EI) in artificial intelligence (AI) systems need refinement because they do not adequately or comprehensively measure the various aspects…
Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first…
Explainable Artificial Intelligence (XAI) aims to make machine learning models transparent and trustworthy, yet most current approaches communicate explanations visually or through text. This paper introduces an information theoretic…
The proliferation of generative AI tools has rendered traditional modular assessments in computing and data-centric education increasingly ineffective, creating a disconnect between academic evaluation and authentic skill measurement. This…
Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed…
In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…