Related papers: Alignment Without Understanding: A Message- and Co…
Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When human users omit premises, simplify…
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…
Large language models (LLMs) are increasingly applied in educational, clinical, and professional settings, but their tendency for sycophancy -- prioritizing user agreement over independent reasoning -- poses risks to reliability. This study…
Human-AI interactions are increasingly part of everyday life, yet the interpersonal dynamics that unfold during such exchanges remain underexplored. This study investigates how emotional alignment, semantic exploration, and linguistic…
Explainability remains a critical challenge in artificial intelligence (AI) systems, particularly in high stakes domains such as healthcare, finance, and decision support, where users must understand and trust automated reasoning.…
Large language models (LLMs) increasingly operate as autonomous agents that reason over external APIs to perform complex tasks. However, their reliability and agreement remain poorly characterized. We present a unified benchmarking…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…
As AI systems become more advanced, ensuring their alignment with a diverse range of individuals and societal values becomes increasingly critical. But how can we capture fundamental human values and assess the degree to which AI systems…
The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare workflow effectively,…
The influence of Artificial Intelligence (AI), and specifically Large Language Models (LLM), on education is continuously increasing. These models are frequently used by students, giving rise to the question whether current forms of…
Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding misinformation and persuasion do not adequately address. This paper proposes that a significant…
Telling an LLM to "be enthusiastic" raises its sycophancy rate from 30\% to 50\% on a lightly-aligned model, but has zero effect on a strongly-aligned one. We define this gap as the alignment floor,…
Large Language Models (LLMs) in search applications increasingly prioritize verbose, lexically complex responses that paradoxically reduce user satisfaction and engagement. Through a comprehensive study of 10.000 (est.) participants…
Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…
Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…
Large Language Models (LLMs) are often criticized for lacking true "understanding" and the ability to "reason" with their knowledge, being seen merely as autocomplete systems. We believe that this assessment might be missing a nuanced…
Contemporary artificial intelligence research has been organized around two dominant ambitions: productivity, which treats AI systems as tools for accelerating work and economic output, and alignment, which focuses on ensuring that…
This study explores the sycophantic tendencies of Large Language Models (LLMs), where these models tend to provide answers that match what users want to hear, even if they are not entirely correct. The motivation behind this exploration…
LLMs increasingly serve as tools for knowledge acquisition, yet users cannot effectively specify how they want information presented. When users request that LLMs "cite reputable sources," "express appropriate uncertainty," or "include…
Anthropomorphization is the tendency to attribute human-like traits to non-human entities. It is prevalent in many social contexts -- children anthropomorphize toys, adults do so with brands, and it is a literary device. It is also a…