Related papers: ValueCompass: A Framework for Measuring Contextual…

Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public…

Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…

Big models have greatly advanced AI's ability to understand, generate, and manipulate information and content, enabling numerous applications. However, as these models become increasingly integrated into everyday life, their inherent…

The fields of AI current lacks methods to quantitatively assess and potentially alter the moral values inherent in the output of large language models (LLMs). However, decades of social science research has developed and refined…

Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we…

LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans nor benchmarks for LLMs, fail to capture this shift, excluding problems that require both human…

Immense effort has been dedicated to minimizing the presence of harmful or biased generative content and better aligning AI output to human intention; however, research investigating the cultural values of LLMs is still in very early…

The rise of general-purpose artificial intelligence (AI) systems, particularly large language models (LLMs), has raised pressing moral questions about how to reduce bias and ensure fairness at scale. Researchers have documented a sort of…

Aligning AI agents with human values is challenging due to diverse and subjective notions of values. Standard alignment methods often aggregate crowd feedback, which can result in the suppression of unique or minority preferences. We…

AI intent alignment, ensuring that AI produces outcomes as intended by users, is a critical challenge in human-AI interaction. The emergence of generative AI, including LLMs, has intensified the significance of this problem, as interactions…

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral…

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and…

Large Language Models (LLMs) have achieved remarkable results on a range of standardized tests originally designed to assess human cognitive and psychological traits, such as intelligence and personality. While these results are often…

As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss…

Conversational agents (CAs) based on generative artificial intelligence frequently face challenges ensuring ethical interactions that align with human values. Current value alignment efforts largely rely on top-down approaches, such as…

A crucial consideration when developing and deploying Large Language Models (LLMs) is the human values to which these models are aligned. In the constitutional framework of alignment models are aligned to a set of principles (the…

As general-purpose artificial intelligence (AI) systems become increasingly integrated with diverse human communities, cultural alignment has emerged as a crucial element in their deployment. Most existing approaches treat cultural…

Personal values are a crucial factor behind human decision-making. Considering that Large Language Models (LLMs) have been shown to impact human decisions significantly, it is essential to make sure they accurately understand human values…

Large language models (LLMs), a recent advance in deep learning and machine intelligence, have manifested astonishing capacities, now considered among the most promising for artificial general intelligence. With human-like capabilities,…