相关论文: Linearly Decoding Refused Knowledge in Aligned Lan…

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…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

With the development of natural language processing (NLP), large language models (LLMs) are becoming increasingly popular. LLMs are integrating more into everyday life, raising public concerns about their security vulnerabilities.…

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…

Large language models (LLMs) often benefit from intermediate steps of reasoning to generate answers to complex problems. When these intermediate steps of reasoning are used to monitor the activity of the model, it is essential that this…

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 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…

During training, Large Language Models (LLMs) learn social regularities that can lead to gender bias in downstream applications. Most mitigation efforts focus on reducing bias in generated outputs, typically evaluated on structured…

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

One way to address safety risks from large language models (LLMs) is to censor dangerous knowledge from their training data. While this removes the explicit information, implicit information can remain scattered across various training…

The capabilities of Large Language Models (LLMs) are routinely evaluated by other LLMs trained to predict human preferences. This framework--known as LLM-as-a-judge--is highly scalable and relatively low cost. However, it is also vulnerable…

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Identifying bias in LLMs is ongoing. Because they are still in development, what is true today may be false tomorrow. We therefore need general strategies for debiasing that will outlive current models. Strategies developed for debiasing…

Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Due to their training on internet-sourced datasets, LLMs can sometimes generate objectionable content, necessitating…

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompts that explicitly…

In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (LLMs). Despite rigorous pretraining and finetuning focused on…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, this process may increase the model's dependence on user…