Related papers: Value Kaleidoscope: Engaging AI with Pluralistic H…
Generative artificial intelligence (AI) holds enormous potential to revolutionize decision-making processes, from everyday to high-stake scenarios. By leveraging generative AI, humans can benefit from data-driven insights and predictions,…
Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred…
Generative artificial intelligences, particularly large language models (LLMs), play an increasingly prominent role in human decision-making contexts, necessitating transparency about their capabilities. While prior studies have shown…
One of the biggest challenges of value-based decision-making is dealing with the subjective nature of values. The relative importance of a value for a particular decision varies between individuals, and people may also have different…
Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…
The launch of ChatGPT in November 2022 marked the beginning of a new era in AI, the availability of generative AI tools for everyone to use. ChatGPT and other similar chatbots boast a wide range of capabilities from answering student…
How do Large Language Models understand moral dimensions compared to humans? This first large-scale Bayesian evaluation of market-leading language models provides the answer. In contrast to prior work using deterministic ground truth…
As we consider entrusting Large Language Models (LLMs) with key societal and decision-making roles, measuring their alignment with human cognition becomes critical. This requires methods that can assess how these systems represent…
Comparing AI models to "human level" is often misleading when benchmark scores are incommensurate or human baselines are drawn from a narrow population. To address this, we propose a framework that calibrates items against the 'world…
Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crime}" are social norms that inform our conduct, such as…
Detecting AI risks becomes more challenging as stronger models emerge and find novel methods such as Alignment Faking to circumvent these detection attempts. Inspired by how risky behaviors in humans (i.e., illegal activities that may hurt…
Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…
Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated…
We present an approach, AI-Spectra, to leverage model multiplicity for interactive systems. Model multiplicity means using slightly different AI models yielding equally valid outcomes or predictions for the same task, thus relying on many…
An important step in the development of value alignment (VA) systems in AI is understanding how values can interrelate with facts. Designers of future VA systems will need to utilize a hybrid approach in which ethical reasoning and…
Given the rapid advancement of large-scale language models, artificial intelligence (AI) models, like ChatGPT, are playing an increasingly prominent role in human society. However, to ensure that artificial intelligence models benefit human…
Over the past decade, artificial intelligence has demonstrated its efficiency in many different applications and a huge number of algorithms have become central and ubiquitous in our life. Their growing interest is essentially based on…
Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…
Pluralistic alignment has emerged as a promising approach for ensuring that large language models (LLMs) faithfully represent the diversity, nuance, and conflict inherent in human values. In this work, we study a high-stakes deployment…
Nowadays, we delegate many of our decisions to Artificial Intelligence (AI) that acts either in solo or as a human companion in decisions made to support several sensitive domains, like healthcare, financial services and law enforcement. AI…