Related papers: Why AI Alignment Failure Is Structural: Learned Hu…

Developments in the field of Artificial Intelligence (AI), and particularly large language models (LLMs), have created a 'perfect storm' for observing 'sparks' of Artificial General Intelligence (AGI) that are spurious. Like simpler models,…

Are AI systems truly representing human values, or merely averaging across them? Our study suggests a concerning reality: Large Language Models (LLMs) fail to represent diverse cultural moral frameworks despite their linguistic…

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Background: What counts as violence is neither self-evident nor universally agreed upon. While physical aggression is prototypical, contemporary societies increasingly debate whether exclusion, humiliation, online harassment or symbolic…

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…

Large language models (LLMs) remain broadly open and highly steerable: they imitate at scale, accept arbitrary system prompts, and readily adopt multiple personae. By analogy to human development, we hypothesize that progress toward…

Large language models (LLMs) are increasingly used as epistemic partners in everyday reasoning, yet their errors remain predominantly analyzed through predictive metrics rather than through their interpretive effects on human judgment. This…

As large language models (LLMs) become increasingly integrated into society, their alignment with human morals is crucial. To better understand this alignment, we created a large corpus of human- and LLM-generated responses to various moral…

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 issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a…

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…

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be…

A moderately detailed consideration of interactive LLMs as cognitive systems is given, focusing on LLMs circa mid-2023 such as ChatGPT, GPT-4, Bard, Llama, etc.. Cognitive strengths of these systems are reviewed, and then careful attention…

The guiding principle of AI alignment is to train large language models (LLMs) to be harmless, helpful, and honest (HHH). At the same time, there are mounting concerns that LLMs exhibit a left-wing political bias. Yet, the commitment to AI…

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit…

The recent rise in popularity of large language models (LLMs) has prompted considerable concerns about their moral capabilities. Although considerable effort has been dedicated to aligning LLMs with human moral values, existing benchmarks…

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI…