Related papers: Unknown Unknowns: Why Hidden Intentions in LLMs Ev…

Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without…

The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…

Large Language Models (LLMs) have become key components of modern software, with prompts acting as their de-facto programming interface. However, prompt design remains largely empirical and small mistakes can cascade into unreliable,…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

As users increasingly turn to LLMs for practical and personal advice, they become vulnerable to subtle steering toward hidden incentives misaligned with their own interests. While existing NLP research has benchmarked manipulation…

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and interaction. These agents are increasingly being deployed across…

The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, erroneous generations, such as false predictions, misinformation, and hallucination made by…

The emergence of large language models (LLMs) is a milestone in generative artificial intelligence, achieving significant success in text comprehension and generation tasks. Despite the tremendous success of LLMs in many downstream tasks,…

Large Language Models (LLMs) are widely deployed in applications that accept user-submitted content, such as uploaded documents or pasted text, for tasks like summarization and question answering. In this paper, we identify a new class of…

Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual…

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

LLMs increasingly excel on AI benchmarks, but doing so does not guarantee validity for downstream tasks. This study contrasts LLM alignment on benchmarks, downstream tasks, and, importantly the intended impact of those tasks. We evaluate…

How biased is a language model? The answer depends on how you ask. A model that refuses to choose between castes for a leadership role will, in a fill-in-the-blank task, reliably associate upper castes with purity and lower castes with lack…