相关论文: TRIDENT: Enhancing Large Language Model Safety wit…

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Ensuring the safety of Large Language Models (LLMs) in diverse linguistic settings remains challenging, particularly for low-resource languages. Existing safety alignment methods are English-centric, limiting their effectiveness. We…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

While tool learning significantly enhances the capabilities of large language models (LLMs), it also introduces substantial security risks. Prior research has revealed various vulnerabilities in traditional LLMs during tool learning.…

Large Language Models (LLMs) are emerging as transformative tools for software vulnerability detection, addressing critical challenges in the security domain. Traditional methods, such as static and dynamic analysis, often falter due to…

The overarching research direction of this work is the development of a ''Responsible Intelligence'' framework designed to reconcile the immense generative power of Large Language Models (LLMs) with the stringent requirements of real-world…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Large language models (LLMs) have shown success in many natural language processing tasks. Despite rigorous safety alignment processes, supposedly safety-aligned LLMs like Llama 2 and Claude 2 are still susceptible to jailbreaks, leading to…

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…

Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…

Over the last year, significant advancements have been made in the realms of large language models (LLMs) and multi-modal large language models (MLLMs), particularly in their application to autonomous driving. These models have showcased…

With the rapid evolution of large language models (LLMs), new and hard-to-predict harmful capabilities are emerging. This requires developers to be able to identify risks through the evaluation of "dangerous capabilities" in order to…

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses. While…

Accurate symptom-to-disease classification and clinically grounded treatment recommendations remain challenging, particularly in heterogeneous patient settings with high diagnostic risk. Existing large language model (LLM)-based systems…

As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various…

We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main contributions. First, we investigate scaling behaviors for…