Related papers: Head-Specific Intervention Can Induce Misaligned A…
Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…
Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…
In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…
Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…
Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an…
Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…
Post-training alignment has increasingly become a crucial factor in enhancing the usability of language models (LMs). However, the strength of alignment varies depending on individual preferences. This paper proposes a method to incorporate…
Large language models (LLMs) exhibit advanced reasoning skills, enabling robots to comprehend natural language instructions and strategically plan high-level actions through proper grounding. However, LLM hallucination may result in robots…
Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs. While prior research has proposed various attack strategies differing in human readability…
Large Language Models (LLMs) are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform…
Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…
Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly…
Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across tasks and languages, revolutionizing natural language processing. This paper investigates the naturally emerging representation alignment in LLMs,…
Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…
Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…
Despite extensive safety-tuning, large language models (LLMs) remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose…
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…