Related papers: Logicbreaks: A Framework for Understanding Subvers…
Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…
Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…
This work presents an analytical framework for the design and analysis of LLM-based algorithms, i.e., algorithms that contain one or multiple calls of large language models (LLMs) as sub-routines and critically rely on the capabilities of…
Large Language Models (LLMs), including GPT-3.5, LLaMA, and PaLM, seem to be knowledgeable and able to adapt to many tasks. However, we still cannot completely trust their answers, since LLMs suffer from \textbf{hallucination}\textemdash…
Large Language Models (LLMs) have shown remarkable capabilities in manipulating natural language across multiple applications, but their ability to handle simple reasoning tasks is often questioned. In this work, we aim to provide a…
In this paper, we investigate the safety mechanisms of instruction fine-tuned large language models (LLMs). We discover that re-weighting MLP neurons can significantly compromise a model's safety, especially for MLPs in end-of-sentence…
Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…
Smart grids rely on high-dimensional numeric telemetry and explicit operating rules to maintain reliable and secure operation. Recent large language models (LLMs) are increasingly considered as candidate decision-support components for…
We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors across multiple latent features, suppressing a single dominant…
The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…
We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…
As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed that LLMs often fail to grasp the notion of safe behaviors,…
Recent advancements in generative AI have enabled ubiquitous access to large language models (LLMs). Empowered by their exceptional capabilities to understand and generate human-like text, these models are being increasingly integrated into…
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content.…
State-of-the-art Large Language Models (LLMs) are accredited with an increasing number of different capabilities, ranging from reading comprehension, over advanced mathematical and reasoning skills to possessing scientific knowledge. In…
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…
Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and…
Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that this vulnerability stems from distributional discrepancies…