相关论文: ContextLens: Modeling Imperfect Privacy and Safety…

Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding…

The proliferation of Large Language Models (LLMs) has demonstrated remarkable capabilities, elevating the critical importance of LLM safety. However, existing safety methods rely on ad-hoc taxonomy and lack a rigorous, systematic…

The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-deployment monitoring. While judge models -- LLMs finetuned…

While Large Language Models (LLMs) exhibit remarkable capabilities, they also introduce significant safety and privacy risks. Current mitigation strategies often fail to preserve contextual reasoning capabilities in risky scenarios.…

In the continuously advancing AI landscape, crafting context-rich and meaningful responses via Large Language Models (LLMs) is essential. Researchers are becoming more aware of the challenges that LLMs with fewer parameters encounter when…

Ensuring compliance with international data protection standards for privacy and data security is a crucial but complex task, often requiring substantial legal expertise. This paper introduces LegiLM, a novel legal language model…

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. We…

While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive LLMs, prompting them…

Ensuring the safety and compliance of large language models (LLMs) is of paramount importance. However, existing LLM safety datasets often rely on ad-hoc taxonomies for data generation and suffer from a significant shortage of…

In this study, we focus on two main tasks, the first for detecting legal violations within unstructured textual data, and the second for associating these violations with potentially affected individuals. We constructed two datasets using…

Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the…

Autonomous control systems face significant challenges in performing complex tasks in the presence of latent risks. To address this, we propose an integrated framework that combines Large Language Models (LLMs), numerical optimization, and…

Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, text comprehension, contextual pattern recognition, and…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Recent advancements in model architectures and length extrapolation techniques have significantly extended the context length of large language models (LLMs), paving the way for their application in increasingly complex tasks. However,…

Privacy issues arise prominently during the inappropriate transmission of information between entities. Existing research primarily studies privacy by exploring various privacy attacks, defenses, and evaluations within narrowly predefined…

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…

We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomous) cyber-physical systems because of their ability to solve…

As Large Language Models (LLMs) become increasingly sophisticated and ubiquitous in natural language processing (NLP) applications, ensuring their robustness, trustworthiness, and alignment with human values has become a critical challenge.…

Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where humans would exercise discretion. This raises a fundamental…