相关论文: Evaluating LLM Simulators as Differentially Privat…

Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user…

The rapid proliferation and increasing complexity of software demand robust quality assurance, with graphical user interface (GUI) testing playing a pivotal role. Crowdsourced testing has proven effective in this context by leveraging the…

With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…

The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead…

Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities…

As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, serving two roles: generating user turns and providing evaluation signals. Yet, these…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Despite their potential as human proxies, LLMs often fail to generate heterogeneous data with human-like diversity, thereby diminishing their value in advancing social science research. To address this gap, we propose a novel method to…

Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as…

The increasing use of synthetic data generated by Large Language Models (LLMs) presents both opportunities and challenges in data-driven applications. While synthetic data provides a cost-effective, scalable alternative to real-world data…

In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at…

Large language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate $individual$ privacy decisions is not well understood. In this paper, we address the problem of evaluating whether a core set of…

We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style losses, which are typically non-per-example decomposable,…

Recent privacy research on large language models (LLMs) has shown that they achieve near-human-level performance at inferring personal data from online texts. With ever-increasing model capabilities, existing text anonymization methods are…

Large Language Models (LLMs) created new opportunities for generating personas, expected to streamline and accelerate the human-centered design process. Yet, AI-generated personas may not accurately represent actual user experiences, as…

Traditional offline evaluation methods for recommender systems struggle to capture the complexity of modern platforms due to sparse behavioural signals, noisy data, and limited modelling of user personality traits. While simulation…

Simulation powered by Large Language Models (LLMs) has become a promising method for exploring complex human social behaviors. However, the application of LLMs in simulations presents significant challenges, particularly regarding their…

We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy. Incentivizing most players to truthfully report their data to the analyst constrains our design to mechanisms that provide…

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but…

User-driven privacy allows individuals to control whether and at what granularity their data is shared, leading to datasets that mix original, generalized, and missing values within the same records and attributes. While such…