相关论文: Probing AI Safety with Source Code

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

The widespread of generative artificial intelligence has heightened concerns about the potential harms posed by AI-generated texts, primarily stemming from factoid, unfair, and toxic content. Previous researchers have invested much effort…

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential…

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

The advent of Large Language Models (LLMs) has revolutionized various applications by providing advanced natural language processing capabilities. However, this innovation introduces new cybersecurity challenges. This paper explores the…

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks but their performance in complex logical reasoning tasks remains unsatisfactory. Although some prompting methods, such as Chain-of-Thought, can…

Large language models (LLMs) have shown incredible capabilities and transcended the natural language processing (NLP) community, with adoption throughout many services like healthcare, therapy, education, and customer service. Since users…

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…

Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to generate intermediate reasoning steps before reaching the final…

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…

With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

The reasoning performance of Large Language Models (LLMs) on a wide range of problems critically relies on chain-of-thought prompting, which involves providing a few chain of thought demonstrations as exemplars in prompts. Recent work,…

In this work, we designed unbiased prompts to systematically evaluate the psychological safety of large language models (LLMs). First, we tested five different LLMs by using two personality tests: Short Dark Triad (SD-3) and Big Five…

The remarkable capabilities of Large Language Models (LLMs) make them increasingly compelling for adoption in real-world healthcare applications. However, the risks associated with using LLMs in medical applications have not been…

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

As large language models (LLMs) rapidly evolve, they bring significant conveniences to our work and daily lives, but also introduce considerable safety risks. These models can generate texts with social biases or unethical content, and…

The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of the problem, research focuses on developing solutions to…