Related papers: When and How Human Curation Backfires: Preference …

Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons,…

The internal behaviour of a population is an important feature to take account of when modelling their dynamics. In line with kin selection theory, many social species tend to cluster into distinct groups in order to enhance their overall…

A growing body of research has explored how to support humans in making better use of AI-based decision support, including via training and onboarding. Existing research has focused on decision-making tasks where it is possible to evaluate…

Alignment training has tradeoffs: it helps language models (LMs) gain in reasoning and instruction following but might lose out on skills such as creativity and calibration, where unaligned base models are better at. We aim to make the best…

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce…

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine…

As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that…

Large language models are classically trained in stages: pretraining on raw text followed by post-training for instruction following and reasoning. However, this separation creates a fundamental limitation: many desirable behaviors such as…

Both the general public and academic communities have raised concerns about sycophancy, the phenomenon of artificial intelligence (AI) excessively agreeing with or flattering users. Yet, beyond isolated media reports of severe consequences,…

Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…

Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation. Yet, they are typically evaluated only in short, single-round settings that do not reflect real-world usage.…

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human…

Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking how a model's output is influenced when we fine-tune on a…

Healthcare clinics regularly encounter dynamic data that changes due to variations in patient populations, treatment policies, medical devices, and emerging disease patterns. Deep learning models can suffer from catastrophic forgetting when…

Reliable models should not only predict correctly, but also justify decisions with acceptable evidence. Yet conventional supervised learning typically provides only class-level labels, allowing models to achieve high accuracy through…

Model collapse, the severe degradation of generative models when iteratively trained on their own outputs, has gained significant attention in recent years. This paper examines Chain of Diffusion, where a pretrained text-to-image diffusion…

Personality traits have long been studied as predictors of human behavior. Recent advances in Large Language Models (LLMs) suggest similar patterns may emerge in artificial systems, with advanced LLMs displaying consistent behavioral…

Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios. This can be attributed to the fact that current…

Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research focuses on interactions between a single LM and a single…