Related papers: AI capabilities can be significantly improved with…

All artificial Intelligence (AI) systems make errors. These errors are unexpected, and differ often from the typical human mistakes ("non-human" errors). The AI errors should be corrected without damage of existing skills and, hopefully,…

Modern foundation models often undergo iterative ``bootstrapping'' in their post-training phase: a model generates synthetic data, an external verifier filters out low-quality samples, and the high-quality subset is used for further…

Pre-training and fine-tuning have achieved significant advances in the information retrieval (IR). A typical approach is to fine-tune all the parameters of large-scale pre-trained models (PTMs) on downstream tasks. As the model size and the…

Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created…

Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards practical automation, this work explores the efficacy of a…

Artificial intelligence (AI) tools such as large language models (LLMs) are already altering student learning. Unlike previous technologies, LLMs can independently solve problems regardless of student understanding, yet are not always…

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

As generative AI systems rapidly improve, a key question emerges: how do users adapt to these changes, and when does such adaptation matter for realizing performance gains? Drawing on theories of dynamic capabilities and IT complements, we…

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…

Recent work in incremental learning has introduced diverse approaches to tackle catastrophic forgetting from data augmentation to optimized training regimes. However, most of them focus on very few training steps. We propose a method for…

This paper introduces Deep Incremental Boosting, a new technique derived from AdaBoost, specifically adapted to work with Deep Learning methods, that reduces the required training time and improves generalisation. We draw inspiration from…

The field of prompt engineering is becoming an essential phenomenon in artificial intelligence. It is altering how data scientists interact with large language models (LLMs) for analytics applications. This research paper shares empirical…

In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples. The possibility to parameterise an LLM through such in-context examples widens their…

Deep reinforcement learning agents have achieved state-of-the-art results by directly maximising cumulative reward. However, environments contain a much wider variety of possible training signals. In this paper, we introduce an agent that…

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal in low-memory/power…

The prevalence of machine learning in biomedical research is rapidly growing, yet the trustworthiness of such research is often overlooked. While some previous works have investigated the ability of adversarial attacks to degrade model…

Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself,…

Game designers use human playtesting to gather feedback about game design elements when iteratively improving a game. Playtesting, however, is expensive: human testers must be recruited, playtest results must be aggregated and interpreted,…

Meta-learning empowers artificial intelligence to increase its efficiency by learning how to learn. Unlocking this potential involves overcoming a challenging meta-optimisation problem. We propose an algorithm that tackles this problem by…

The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…