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

LLM-enabled robots prioritizing scarce assistance in social settings face pluralistic values and LLM behavioral variability: reasonable people can disagree about who is helped first, while LLM-mediated interaction policies vary across…

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Routing incoming queries to the most cost-effective LLM while maintaining response quality poses a fundamental challenge in optimizing performance-cost trade-offs for large-scale commercial systems. We present IPR\, -- \,a…

Alignment tuning is crucial for ensuring large language models (LLMs) behave ethically and helpfully. Current alignment approaches require high-quality annotations and significant training resources. This paper proposes a low-cost,…

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Aligned Large Language Models (LLMs) have attracted significant attention for their safety, particularly in the context of jailbreak attacks that attempt to bypass guardrails via adversarial prompts. Among existing approaches, the Greedy…

This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this end, we establish a novel open framework, describing a…

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL.…

Huge pretrained language models (LMs) have demonstrated surprisingly good zero-shot capabilities on a wide variety of tasks. This gives rise to the appealing vision of a single, versatile model with a wide range of functionalities across…

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

The advent of large language models (LLMs) in the education sector has provided impetus to automate grading short answer questions. LLMs make evaluating short answers very efficient, thus addressing issues like staff shortage. However, in…

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling…