相关论文: Discovering Forbidden Topics in Language Models

Frontier large language models are increasingly deployed as orchestration backbones for biological research workflows, yet no shared evidence base exists for comparing their refusal behaviour on legitimate research prompts. RefusalBench,…

Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can…

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…

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this…

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Refusal on harmful prompts is a key safety behaviour in instruction-tuned large language models (LLMs), yet the internal causes of this behaviour remain poorly understood. We study two public instruction-tuned models, Gemma-2-2B-IT and…

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produce responses that better align with the preferences of those…

The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We…

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…

Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal tokens that distinguish different refusal types before responding. In this work, we…

Machine unlearning aims to remove the influence of specific data from trained language models. In real-world deployments, unlearning requests often arrive sequentially, which challenges existing fine-tuning-based methods: fine-tuning each…

Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safety training is that it algorithmically forbids the model…

Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…

The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora (AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench,…