Related papers: The Burden of Interactive Alignment with Inconsist…
Given the exponential advancement in AI technologies and the potential escalation of harmful effects from recommendation systems, it is crucial to simulate and evaluate these effects early on. Doing so can help prevent possible damage to…
The frequency with which people interact with technology means that users may develop interface habits, i.e. fast, automatic responses to stable interface cues. Design guidelines often assume that interface habits are beneficial. However,…
AI sycophancy is increasingly recognized as a harmful alignment, but research remains fragmented and underdeveloped at the conceptual level. This article redefines AI sycophancy as the tendency of large language models (LLMs) and other…
LLM-powered conversational agents are increasingly influencing our decision-making, raising concerns about "sycophancy" - the tendency for LLMs to excessively agree with users even at the expense of truthfulness. While prior work has…
Stackelberg games, widely applied in domains like economics and security, involve asymmetric interactions where a leader's strategy drives follower responses. Accurately modeling these dynamics allows domain experts to optimize strategies…
As the rate of content production grows, we must make a staggering number of daily decisions about what information is worth acting on. For any flourishing online social media system, users can barely keep up with the new content shared by…
Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions…
AI chatbots are increasingly stepping into roles as collaborators or teachers in analyzing, visualizing, and reasoning through data and domain problem. Yet, AI's default assistant mode with its comprehensive and one-off responses may…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
Interactions with AI assistants are increasingly personalized to individual users. As AI personalization is dynamic and machine-learning-driven, we have limited understanding of how personalization affects interaction outcomes and user…
In an online social network, link recommendations are a way for users to discover relevant links to people they may know, thereby potentially increasing their engagement on the platform. However, the addition of links to a social network…
Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking…
The field of AI alignment aims to steer AI systems toward human goals, preferences, and ethical principles. Its contributions have been instrumental for improving the output quality, safety, and trustworthiness of today's AI models. This…
Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral…
We model the interaction between a user and an AI driven recommendation system. The user initiates the process by conveying preference information through a costly and noisy message. The AI assistant, acting as a Bayesian agent, interprets…
In micro-blogging platforms, people connect and interact with others. However, due to cognitive biases, they tend to interact with like-minded people and read agreeable information only. Many efforts to make people connect with those who…
Recommender systems that learn from implicit feedback often use large volumes of a single type of implicit user feedback, such as clicks, to enhance the prediction of sparse target behavior such as purchases. Using multiple types of…
In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…
Our ability to build autonomous agents that leverage Generative AI continues to increase by the day. As builders and users of such agents it is unclear what parameters we need to align on before the agents start performing tasks on our…
Digital services face a fundamental trade-off in content selection: they must balance the immediate revenue gained from high-reward content against the long-term benefits of maintaining user engagement. Traditional multi-armed bandit models…