相关论文: Fine-Tuning Lowers Safety and Disrupts Evaluation …

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety.…

Memorization in large language models (LLMs) makes them vulnerable to data extraction attacks. While pre-training memorization has been extensively studied, fewer works have explored its impact in fine-tuning, particularly for LoRA…

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation…

The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general…

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

Fine-tuning large language models (LLMs) for machine translation has shown improvements in overall translation quality. However, it is unclear what is the impact of fine-tuning on desirable LLM behaviors that are not present in neural…

With the rapid advancement of artificial intelligence, Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), including content generation, human-computer interaction, machine translation, and…

Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the…

Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechanism in which harmful inputs are routed safety-critical…

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on apparently benign data for downstream tasks can jeopardize…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

There is ongoing debate about whether large language models (LLMs) can serve as substitutes for human participants in survey and experimental research. While recent work in fields such as marketing and psychology has explored the potential…

Large language models (LLMs) are increasingly used as decision-support tools in data-constrained scientific workflows, where correctness and validity are critical. However, evaluation practices often emphasize stability or reproducibility…

Finetuning on narrow domains has become an essential tool to adapt Large Language Models (LLMs) to specific tasks and to create models with known unusual properties that are useful for research. We show that narrow finetuning creates strong…

Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to generating harmful content when exposed to unsafe queries raises…

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…