相关论文: PrimeGuard: Safe and Helpful LLMs through Tuning-F…

Large language models (LLMs) are increasingly embedded in Computer Science (CS) classrooms to automate code generation, feedback, and assessment. However, their susceptibility to adversarial or ill-intentioned prompts threatens student…

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as…

With the recent proliferation of large language models (LLMs), enterprises have been able to rapidly develop proof-of-concepts and prototypes. As a result, there is a growing need to implement robust guardrails that monitor, quantize and…

As machine learning (ML) systems increasingly impact critical sectors such as hiring, financial risk assessments, and criminal justice, the imperative to ensure fairness has intensified due to potential negative implications. While much ML…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…

The rapid advancement of large language models (LLMs) has increased the need for guardrail models to ensure responsible use, particularly in detecting unsafe and illegal content. While substantial safety data exist in English, multilingual…

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addresses a critical…

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning queries to the most appropriate model. However, as classifiers, LLM routers are vulnerable…

Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Safety guardrails have become an active area of research in AI safety, aimed at ensuring the appropriate behavior of large language models (LLMs). However, existing research lacks consideration of nuances across linguistic and cultural…

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This…