Related papers: Model-Behavior Alignment under Flexible Evaluation…

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based…

One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions. Designing such reward functions is difficult in part because the user only has an implicit understanding of the task…

Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning. A widely adopted approach is identifying "metamers," stimuli physically different yet perceptually…

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Large language models (LLMs), typically designed as a function of next-word prediction, have excelled across extensive NLP tasks. Despite the generality, next-word prediction is often not an efficient formulation for many of the tasks,…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

Identifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational resources and data. We study identifiability in the context…

In safety-critical applications data-driven models must not only be accurate but also provide reliable uncertainty estimates. This property, commonly referred to as calibration, is essential for risk-aware decision-making. In regression a…

Model-Based Reinforcement Learning involves learning a \textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \textit{planner}. Much of the recent research along these lines presents a…

Conformance checking techniques allow us to quantify the correspondence of a process's execution, captured in event data, w.r.t., a reference process model. In this context, alignments have proven to be useful for calculating conformance…

In an increasing number of applications designers have access to multiple computer models which typically have different levels of fidelity and cost. Traditionally, designers calibrate these models one at a time against some high-fidelity…

The representations of neural networks are often compared to those of biological systems by performing regression between the neural network responses and those measured from biological systems. Many different state-of-the-art deep neural…

Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and…

Recent work in explanation generation for decision making agents has looked at how unexplained behavior of autonomous systems can be understood in terms of differences in the model of the system and the human's understanding of the same,…

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

We establish empirical bounds on behavioral inference through controlled experiments at scale: LLM-based agents assigned one of 36 behavioral profiles (9 belief systems x 4 motivations) generate over 1.5 million behavioral sequences across…

Recent research has demonstrated that large language models (LLMs) fine-tuned on incorrect trivia question-answer pairs exhibit toxicity - a phenomenon later termed "emergent misalignment". Moreover, research has shown that LLMs possess…

A successful deep learning network is highly dependent not only on the training dataset, but the training algorithm used to condition the network for a given task. The loss function, dataset, and tuning of hyperparameters all play an…

Machine learning models trained on real-world data may inadvertently make biased predictions that negatively impact marginalized communities. Reweighting, which assigns a weight to each data point used during model training, can mitigate…