Related papers: Fine-tuning Aligned Language Models Compromises Sa…

Fine-tuning lets practitioners repurpose aligned large language models (LLMs) for new domains, yet recent work reveals emergent misalignment (EMA): Even a small, domain-specific fine-tune can induce harmful behaviors far outside the target…

Safety alignment is an important procedure before the official deployment of a Large Language Model (LLM). While safety alignment has been extensively studied for LLM, there is still a large research gap for Large Reasoning Models (LRMs)…

As safety remains a crucial concern throughout the development lifecycle of Large Language Models (LLMs), researchers and industrial practitioners have increasingly focused on safeguarding and aligning LLM behaviors with human preferences…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data. Prior work shows that introducing a small…

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fine-tune them using data structured according to a predefined…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Federated learning (FL) enables multiple parties to collaboratively fine-tune an large language model (LLM) without the need of direct data sharing. Ideally, by training on decentralized data that is aligned with human preferences and…

Large language models (LLMs) are increasingly being used for emotional support. They are also being developed for formal therapy purposes. However, LLMs like ChaptGPT or Llama are often developed with content moderation guardrails that…

Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and security postures of eight open-weight large language models (LLMs) to identify vulnerabilities…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Research to improve Automated Short Answer Grading has recently focused on Large Language Models (LLMs) with prompt engineering and no- or few-shot prompting to achieve best results. This is in contrast to the fine-tuning approach, which…

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…