Related papers: Shape it Up! Restoring LLM Safety during Finetunin…

Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through…

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

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,…

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Large language models (LLMs) have achieved significant progress across various domains, but their increasing scale results in high computational and memory costs. Recent studies have revealed that LLMs exhibit sparsity, providing the…

Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize this approach to train models that exhibit a degree of…

Large Language Models (LLMs), such as ChatGPT, have achieved impressive milestones in natural language processing (NLP). Despite their impressive performance, the models are known to pose important risks. As these models are deployed in…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…

Large language models (LLMs) have demonstrated impressive capabilities in code generation, achieving high scores on benchmarks such as HumanEval and MBPP. However, these benchmarks primarily assess functional correctness and neglect broader…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well. If we have only observed a few examples of violations of a new safety rule, how can we…

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks, yet their training remains highly resource-intensive and susceptible to critical challenges such as training instability. A predominant source of…

Recent advancements in pre-trained large language models (LLMs) have significantly influenced various domains. Adapting these models for specific tasks often involves fine-tuning (FT) with private, domain-specific data. However, privacy…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based…