Related papers: GLiNER2-PII: A Multilingual Model for Personally I…

Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership inference attacks (MIAs) or data extraction attacks, but…

Much text describes a changing world (e.g., procedures, stories, newswires), and understanding them requires tracking how entities change. An earlier dataset, OpenPI, provided crowdsourced annotations of entity state changes in text.…

Accurate recognition of personally identifiable information (PII) is central to automated text anonymization. This paper investigates the effectiveness of cross-domain model transfer, multi-domain data fusion, and sample-efficient learning…

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed…

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has…

In this work, we introduce PII-Scope, a comprehensive benchmark designed to evaluate state-of-the-art methodologies for PII extraction attacks targeting LLMs across diverse threat settings. Our study provides a deeper understanding of these…

Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only…

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts,…

Information extraction tasks require both accurate, efficient, and generalisable models. Classical supervised deep learning approaches can achieve the required performance, but they need large datasets and are limited in their ability to…

Objectives: Despite the recent adoption of large language models (LLMs) for biomedical information extraction, challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed…

Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive domains such as law, finance, and healthcare. However, the…

The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally…

Production LLM systems require both safety moderation and PII detection under strict latency and cost constraints. This creates a trade-off: autoregressive moderators are accurate but expensive, while lightweight encoders are faster but…

With the rise of deep learning in various applications, privacy concerns around the protection of training data have become a critical area of research. Whereas prior studies have focused on privacy risks in single-modal models, we…

Despite advances in the use of large language models (LLMs) in downstream tasks, their ability to memorize information has raised privacy concerns. Therefore, protecting personally identifiable information (PII) during LLM training remains…

Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs). We run an extensive, fine-grained analysis on the…

With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although efforts have been made to protect PII in LLMs, existing…

Biomedical named entity recognition (NER) presents unique challenges due to specialized vocabularies, the sheer volume of entities, and the continuous emergence of novel entities. Traditional NER models, constrained by fixed taxonomies and…

Self-disclosure, while being common and rewarding in social media interaction, also poses privacy risks. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through detection and…

Temporal expression identification is crucial for understanding texts written in natural language. Although highly effective systems such as HeidelTime exist, their limited runtime performance hampers adoption in large-scale applications…