English
Related papers

Related papers: The Burden of Interactive Alignment with Inconsist…

200 papers

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…

Social and Information Networks · Computer Science 2025-02-04 Ljubisa Bojic , Zorica Dodevska , Yashar Deldjoo , Nenad Pantelic

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,…

Human-Computer Interaction · Computer Science 2020-05-15 Diego Garaialde , Christopher P. Bowers , Charlie Pinder , Priyal Shah , Shashwat Parashar , Leigh Clark , Benjamin R. Cowan

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…

Human-Computer Interaction · Computer Science 2025-09-29 Lihua Du , Xing Lyu , Lezi Xie , Bo Feng

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…

Human-Computer Interaction · Computer Science 2026-02-03 Yuan Sun , Ting Wang

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…

Artificial Intelligence · Computer Science 2025-07-01 Kuang-Da Wang , Ping-Chun Hsieh , Wen-Chih Peng

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…

Social and Information Networks · Computer Science 2016-11-18 Nathan O. Hodas , Kristina Lerman

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…

Computation and Language · Computer Science 2026-05-27 Eilam Shapira , Moshe Tennenholtz , Roi Reichart

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…

Human-Computer Interaction · Computer Science 2026-04-06 Yongsu Ahn , Nam Wook Kim , Benjamin Bach

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,…

Computers and Society · Computer Science 2024-10-04 Hayley Clatterbuck , Clinton Castro , Arvo Muñoz Morán

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…

Human-Computer Interaction · Computer Science 2026-02-18 Maximilian Eder , Clemens Lechner , Maurice Jakesch

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…

Social and Information Networks · Computer Science 2024-01-18 Yanbang Wang , Jon Kleinberg

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…

Human-Computer Interaction · Computer Science 2025-02-14 Xianzhe Fan , Qing Xiao , Xuhui Zhou , Jiaxin Pei , Maarten Sap , Zhicong Lu , Hong Shen

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…

Artificial Intelligence · Computer Science 2024-11-26 Robert West , Roland Aydin

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…

Machine Learning · Computer Science 2024-11-01 Tianyi Qiu , Yang Zhang , Xuchuan Huang , Jasmine Xinze Li , Jiaming Ji , Yaodong Yang

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…

Artificial Intelligence · Computer Science 2026-05-26 Jing Dong , Prakirt Raj Jhunjhunwala , Yash Kanoria

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…

Human-Computer Interaction · Computer Science 2016-01-05 Eduardo Graells-Garrido , Mounia Lalmas , Ricardo Baeza-Yates

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…

Information Retrieval · Computer Science 2023-05-10 Xin Xin , Xiangyuan Liu , Hanbing Wang , Pengjie Ren , Zhumin Chen , Jiahuan Lei , Xinlei Shi , Hengliang Luo , Joemon Jose , Maarten de Rijke , Zhaochun Ren

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…

Artificial Intelligence · Computer Science 2025-02-18 Maarten Buyl , Hadi Khalaf , Claudio Mayrink Verdun , Lucas Monteiro Paes , Caio C. Vieira Machado , Flavio du Pin Calmon

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…

Artificial Intelligence · Computer Science 2024-04-09 Nitesh Goyal , Minsuk Chang , Michael Terry

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…

Machine Learning · Computer Science 2025-02-21 Emilio Calvano , Nika Haghtalab , Ellen Vitercik , Eric Zhao