Related papers: Tatemae: Detecting Alignment Faking via Tool Selec…

As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tools from growing databases or marketplaces to solve user…

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Static Application Security Testing (SAST) tools are critical to software quality, identifying potential code issues early in development. However, they often produce false positive warnings that require manual review, slowing down…

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Providing timely and personalized guidance for students' programming assignments, offers significant practical value for helping students complete assignments and enhance their learning. In recent years, various automated Fault Localization…

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks posed by jailbreak attacks that exploit this inference…

Automated fault localization requires connecting an observed test failure to the responsible method across thousands of candidates--a task that purely statistical approaches handle with limited precision and that LLMs cannot yet handle at…

Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by…

Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new challenge in the form…

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently…

Large Language Models (LLMs) are increasingly deployed in contact-center Quality Assurance (QA) to automate agent performance evaluation and coaching feedback. While LLMs offer unprecedented scalability and speed, their reliance on…

Vulnerability detection is crucial to protect software security. Nowadays, deep learning (DL) is the most promising technique to automate this detection task, leveraging its superior ability to extract patterns and representations within…

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model…

Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire. In practice, AFA methods often learn from…

Large language models (LLMs) often exhibit tendencies that diverge from human preferences, such as favoring certain writing styles or producing overly verbose outputs. While crucial for improvement, identifying the factors driving these…

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention…

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

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…