Related papers: PersonaBench: Evaluating AI Models on Understandin…

Generative AI technologies are gaining unprecedented popularity, causing a mix of excitement and apprehension through their remarkable capabilities. In this paper, we study the challenges associated with deploying synthetic data, a subfield…

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise…

The ability to research and synthesize knowledge is central to human expertise and progress. A new class of AI systems--designed for generative research synthesis--aims to automate this process by retrieving information from the live web…

Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to…

In this paper we define and investigate the problem of \emph{persona authentication}: learning a conversational policy to verify the consistency of persona models. We propose a learning objective and prove (under some mild assumptions) that…

To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of…

Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

Large Audio-Language Models (LALMs) have demonstrated strong performance in audio understanding and generation. Yet, our extensive benchmarking reveals that their behavior is largely generic (e.g., summarizing spoken content) and fails to…

In the age of data-driven decision making, preserving privacy while providing personalized experiences has become paramount. Personalized Federated Learning (PFL) offers a promising framework by decentralizing the learning process, thus…

Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…

Personalization customizes information access. The PIPE ("Personalization is Partial Evaluation") modeling methodology represents interaction with an information space as a program. The program is then specialized to a user's known…

AI-based data synthesis has seen rapid progress over the last several years, and is increasingly recognized for its promise to enable privacy-respecting high-fidelity data sharing. However, adequately evaluating the quality of generated…

Accessing sensitive patient data for machine learning is challenging due to privacy concerns. Datasets with annotations of personally identifiable information are crucial for developing and testing anonymization systems to enable safe data…

Novice and expert users have different systematic preferences in task-oriented dialogues. However, whether catering to these preferences actually improves user experience and task performance remains understudied. To investigate the effects…

Large Language Models (LLMs) have reshaped user profiling, yet current evaluations mainly focus on static data snapshots. This paradigm overlooks the reality of personalized systems, where User-Generated Content (UGC) arrives continuously…

Differentially private graph analysis is a powerful tool for deriving insights from diverse graph data while protecting individual information. Designing private analytic algorithms for different graph queries often requires starting from…

Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal…

The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and preferences. Retrieval augmentation emerges as an effective…

Retrieval-Augmented Generation (RAG) has become the standard approach for grounding large language models in information that was not available during training. While existing datasets and benchmarks focus on web or other public sources,…