The paper investigates whether automatic safety judges evaluate the content of a model’s reply or merely its style. By keeping the reply content fixed and adding various style wrappers—such as educational disclaimers, fake reasoning blocks, or token refusals—the authors show that many judges flip their verdicts, indicating that style can influence safety judgments. The study evaluates over 600 jailbreak examples across multiple judges, revealing that some judges are highly susceptible to style-based manipulation while others remain robust.
By Yongxi Zhou, Wenbo Ye, Yuanzhe Liu, Zihan Dong, Junwei Yao
Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an automated judge: either a safety classifier trained for the task, or a general chat model prompted to grade. The judge is rarely checked.
arXiv:2606. 25487v1 Announce Type: cross Abstract: Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an automated judge: either a safety classifier trained for the task, or a general chat model prompted to grade.
By Yang Gao (Veyon Solutions)
arXiv:2608. 09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.
By Mingyu Luo, Ming Deng, Zilang Qiu, Yiming Cheng, Ci Tao, Xue Tan, Sijin Sun, Yangfu Li, Ping Chen, Jun Dai, Xiaoyan Sun
arXiv:2606. 02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts toward harmful goals.
By Huanli Gong, Zhipeng Wei, Yu Fu, Haz Sameen Shahgir, Ananya Gupta, Yue Dong, N. Benjamin Erichson
Safety-Flag is a unified benchmark that consolidates seven popular safety datasets into a single balanced flag/do‑not‑flag protocol, providing item‑level decisions and confidence scores for multiple large language models and dedicated guards. The benchmark evaluates moderator reliability across three dimensions—error direction, probability calibration, and confidence‑based error ranking—revealing that aggregate accuracy masks significant differences, such as one model flagging 85% of benign content while another misses 54% of harmful content. The study shows that general‑purpose models are overconfident, but temperature tuning can substantially improve calibration, and confidence‑based abstention can reduce selective risk, though performance varies with how well confidence ranks errors.
By Yibo Hu