相关论文: Adaptive Probe-based Steering for Robust LLM Jailb…

This paper presents novel techniques for enhancing the performance of knowledge tracing (KT) models by focusing on the crucial factor of question and concept difficulty level. Despite the acknowledged significance of difficulty, previous KT…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Effective safety auditing of large language models (LLMs) demands tools that go beyond black-box probing and systematically uncover vulnerabilities rooted in model internals. We present a comprehensive, interpretability-driven jailbreaking…

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

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…

Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high…

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering…

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a…