相关论文: Panacea: Mitigating Harmful Fine-tuning for Large …

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Vision-Language-Action (VLA) models have become foundational to modern embodied AI systems. By integrating visual perception, language understanding, and action planning, they enable general-purpose task execution across diverse…

Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing restoration methods typically employ parameter-efficient…

Low rank adaptation (LoRA) has emerged as a prominent technique for fine-tuning large language models (LLMs) thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural…

Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…

Fine-tuning Large Language Models (LLMs) has emerged as a common practice for tailoring models to individual needs and preferences. The choice of datasets for fine-tuning can be diverse, introducing safety concerns regarding the potential…

Recently, major AI providers such as Google and OpenAI have introduced Finetuning-as-a-Service (FaaS), which allows users to customize Large Language Models (LLMs) using their own data. However, this service is vulnerable to safety…

Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This paper investigates the effectiveness of these methods in…

Customizing Large Language Models (LLMs) on untrusted datasets poses severe risks of injecting toxic behaviors. In this work, we introduce Optimus, a novel defense framework designed to mitigate fine-tuning harms while preserving…

Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard…

Large Language Models (LLM) have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel…

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…

We introduce a large language model (LLM) capable of processing speech inputs and show that tuning it further with reinforcement learning on human preference (RLHF) enables it to adapt better to disordered speech than traditional…

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing its effect on individual outputs is still lacking. Here, we…

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large reasoning models (LRMs), such as the DeepSeek-R1 series,…

The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…