Related papers: Selective Safety Steering via Value-Filtered Decod…
As large language models (LLMs) become easily accessible nowadays, the trade-off between safety and helpfulness can significantly impact user experience. A model that prioritizes safety will cause users to feel less engaged and assisted…
Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their…
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…
Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…
Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…
Language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyright-protected, such reproduction raises issues of consent and compensation for creators and…
Large language models (LLMs) have become proficient at sophisticated code-generation tasks, yet remain ineffective at reliably detecting or avoiding code vulnerabilities. Does this deficiency stem from insufficient learning about code…
Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while…
Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges…
Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…
As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…
Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…
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…
Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enable controllable generation without retraining. Recent work…
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…
Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token selection in a simple sequential manner, making it easy to…
Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a significant obstacle to deployment, particularly in high-stakes…
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…
Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…
We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection…