Related papers: Modeling Pathology-Like Behavioral Patterns in Lan…
A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…
Ensuring safe and contextually appropriate behaviour in Large Language Models (LLMs) remains a critical challenge for real-world deployment. We present \textbf{SafeCtrl-RL}, an inference-time behavioural control framework that enables…
As Large Language Models (LLMs) become widely used to model and simulate human behavior, understanding their biases becomes critical. We developed an experimental framework using Big Five personality surveys and uncovered a previously…
Large Language Models (LLMs) have emerged as powerful generative Artificial Intelligence solutions which can be applied to several fields and areas of work. This paper presents results and reflection of an experiment done to use the model…
Large Language Models (LLMs), originally developed for natural language processing (NLP), have demonstrated the potential to generalize across modalities and domains. With their in-context learning (ICL) capabilities, LLMs can perform…
Transformer-based language models (LMs) continue to achieve state-of-the-art performance on natural language processing (NLP) benchmarks, including tasks designed to mimic human-inspired "commonsense" competencies. To better understand the…
The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language…
Motivated by loss of control risks from misaligned AI systems, we develop and apply methods for measuring language models' propensity for unsanctioned behaviour. We contribute three methodological improvements: analysing effects of changes…
Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…
Numerous previous studies have sought to determine to what extent language models, pretrained on natural language text, can serve as useful models of human cognition. In this paper, we are interested in the opposite question: whether we can…
Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…
Large language models (LLMs) are increasingly used both to make decisions in domains such as health, education and law, and to simulate human behavior. Yet how closely LLMs mirror actual human decision-making remains poorly understood. This…
Reliable simulation of human behavior is essential for explaining, predicting, and intervening in our society. Recent advances in large language models (LLMs) have shown promise in emulating human behaviors, interactions, and…
Large Language Models (LLMs) are increasingly deployed in autonomous decision-making roles across high-stakes domains. However, since models are trained on human-generated data, they may inherit cognitive biases that systematically distort…
The inability of Large Language Models (LLMs) to modulate their personality expression in response to evolving dialogue dynamics hinders their performance in complex, interactive contexts. We propose a model-agnostic framework for dynamic…
This paper builds an empirical model that predicts a worker's next occupation as a function of the worker's occupational history. Because histories are sequences of occupations, the covariate space is high-dimensional, and further, the…
Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…
Large language models (LLMs) hold the potential to absorb and reflect personality traits and attitudes specified by users. In our study, we investigated this potential using robust psychometric measures. We adapted the most studied test in…
Fine-tuning LLMs on narrowly harmful datasets can lead to behavior that is broadly misaligned with respect to human values. To understand when and how this emergent misalignment occurs, we develop a comprehensive framework for detecting and…
Language models trained on large text corpora encode rich distributional information about real-world environments and action sequences. This information plays a crucial role in current approaches to language processing tasks like question…