Related papers: Does Claude's Constitution Have a Culture?
We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…
As artificial intelligence rapidly transforms society, developers and policymakers struggle to anticipate which applications will face public moral resistance. We propose that these judgments are not idiosyncratic but systematic and…
This study integrates critical AI scholarship with relational communication theories to explain how AI language modifications shape the quality of government-citizen communication. Distinguishing between informational-cognitive quality…
Recent incidents highlight safety risks in Large Language Models (LLMs), motivating research into alignment methods like Constitutional AI (CAI). This paper explores CAI's self-critique mechanism on small, uncensored 7-9B parameter models:…
Amid growing concerns over AI's societal risks--ranging from civilizational collapse to misinformation and systemic bias--this study explores the perceptions of AI experts and the general US registered voters on the likelihood and impact of…
Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using…
How well can AI-derived synthetic research data replicate the responses of human participants? An emerging literature has begun to engage with this question, which carries deep implications for organizational research practice. This article…
Explainable AI (XAI) is widely used to analyze AI systems' decision-making, such as providing counterfactual explanations for recourse. When unexpected explanations occur, users may want to understand the training data properties shaping…
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…
Multilingual large language models (MLLMs) are increasingly deployed across cultural, linguistic, and political contexts, yet existing governance frameworks largely assume English-centric data, homogeneous user populations, and abstract…
As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs.…
We are introducing Aligned, a platform for global governance and alignment of frontier models, and eventually superintelligence. While previous efforts at the major AI labs have attempted to gather inputs for alignment, these are often…
For synergistic interactions between humans and artificial intelligence (AI) systems, AI outputs often need to be explainable to people. Explainable AI (XAI) systems are commonly tested in human user studies. However, whether XAI…
Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…
This paper presents a community-centered study of cultural limitations of text-to-image (T2I) models in the South Asian context. We theorize these failures using scholarship on dominant media regimes of representations and locate them…
This study seeks to uncover evidence of a latent structure in evolved human culture as it is refracted through contemporary large language models (LLMs). Drawing on parallel responses from six leading generative models to a prompt which…
Current AI systems minimize risk by enforcing ideological neutrality, yet this may introduce automation bias by suppressing cognitive engagement in human decision-making. We conducted randomized trials with 2,500 participants to test…
Artificial intelligence (AI) alignment is fundamentally a formation problem, not only a safety problem. As Large Language Models (LLMs) increasingly mediate moral deliberation and spiritual inquiry, they do more than provide information;…
This paper introduces a systematic evaluation framework grounded in the Interagency Language Roundtable (ILR) Skill Level Descriptions and applies it to Claude (Sonnet 4.6) across six languages: English, French, Romanian, Spanish, Italian,…
Large Language Models significantly influence social interactions, decision-making, and information dissemination, underscoring the need to understand the implicit socio-cognitive attitudes, referred to as "worldviews", encoded within these…