Related papers: Text-Based Personas for Simulating User Privacy De…
With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy…
Mobile applications increasingly rely on sensor data to infer user context and deliver personalized experiences. Yet the mechanisms behind this personalization remain opaque to users and researchers alike. This paper presents a sandbox…
Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks…
Persona prompting has been widely adopted to steer large language models (LLMs) behavior and improve their instruction performance by assigning specific characters. However, identifying an optimal persona is time-consuming, and its impact…
The emergence of large language models (LLMs), and their increased use in user-facing systems, has led to substantial privacy concerns. To date, research on these privacy concerns has been model-centered: exploring how LLMs lead to privacy…
While many online services provide privacy policies for end users to read and understand what personal data are being collected, these documents are often lengthy and complicated. As a result, the vast majority of users do not read them at…
Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regulatory boundaries, while bounding the risks of…
The task of persona-steered text generation requires large language models (LLMs) to generate text that reflects the distribution of views that an individual fitting a persona could have. People have multifaceted personas, but prior work on…
The availability of powerful open-source large language models (LLMs) opens exciting use-cases, such as using personal data to fine-tune these models to imitate a user's unique writing style. Two key requirements for such assistants are…
Recent advances enable Large Language Models (LLMs) to generate AI personas, yet their lack of deep contextual, cultural, and emotional understanding poses a significant limitation. This study quantitatively compared human responses with…
Modeling subrational agents, such as humans or economic households, is inherently challenging due to the difficulty in calibrating reinforcement learning models or collecting data that involves human subjects. Existing work highlights the…
The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs…
Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messaging). To assess to what extent an individual's personality can be inferred from user…
Large language models (LLMs) make it possible to generate synthetic behavioural data at scale, offering an ethical and low-cost alternative to human experiments. Whether such data can faithfully capture psychological differences driven by…
As large language models (LLMs) evolve, their ability to deliver personalized and context-aware responses offers transformative potential for improving user experiences. Existing personalization approaches, however, often rely solely on…
Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…
Privacy personas capture the differences in user segments with respect to one's knowledge, behavioural patterns, level of self-efficacy, and perception of the importance of privacy protection. Modelling these differences is essential for…
Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We…
Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee,…
Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful…