Related papers: Incomplete Contracting and AI Alignment
Social sciences have accumulated a rich body of theories and methodologies for investigating the human mind and behaviors, while offering valuable insights into the design and understanding of Artificial Intelligence (AI) systems. Focusing…
The AI alignment problem comprises both technical and normative dimensions. While technical solutions focus on implementing normative constraints in AI systems, the normative problem concerns determining what these constraints should be.…
We examine the conceptual and ethical gaps in current representations of Superintelligence misalignment. We find throughout Superintelligence discourse an absent human subject, and an under-developed theorization of an "AI unconscious" that…
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad…
Deep neural networks excel in medical imaging but remain prone to biases, leading to fairness gaps across demographic groups. We provide the first systematic exploration of Human-AI alignment and fairness in this domain. Our results show…
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…
Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand…
Collaboration with artificial intelligence (AI) has improved human decision-making across various domains by leveraging the complementary capabilities of humans and AI. Yet, humans systematically overrely on AI advice, even when their…
As AI systems become embedded in everyday practice, value misalignment has emerged as a pressing concern. Yet, dominant alignment approaches remain model centric, treating users as passive recipients of prespecified values rather than as…
While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…
Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may…
Advancements in large language models (LLMs) have renewed concerns about AI alignment - the consistency between human and AI goals and values. As various jurisdictions enact legislation on AI safety, the concept of alignment must be defined…
A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to…
We study optimal contract design for large populations of heterogeneous agents whose actions generate network spillovers represented by an interaction function. In a linear-quadratic framework, we solve the finite-agent problem and its…
AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizations" are simultaneously more effective at achieving business…
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remains challenging due to the inherent…
Algorithmic contract design studies scenarios where a principal incentivizes an agent to exert effort on her behalf. In this work, we focus on settings where the agent's type is drawn from an unknown distribution, and formalize an offline…
This paper develops a unified framework for evaluating the optimal degree of task automation. Moving beyond binary automate-or-not assessments, we model automation intensity as a continuous choice in which firms minimize costs by selecting…
According to canonical negotiation theory, people's success in a negotiation depends on how well they balance competing demands--empathizing and asserting, demonstrating concern for other and concern for self, being soft on the people and…
As AI agents built on large language models (LLMs) become increasingly embedded in society, issues of coordination, control, delegation, and accountability are entangled with concerns over their reliability. To design and implement LLM…