The paper evaluates safety monitors by measuring recall only on prompts that the target model actually answers, rather than on all harmful prompts. Across several guard systems, recall at a 1% false‑positive rate drops sharply when focusing on answered prompts, with monitors catching refused requests 1.1–6.4 times more often than answered ones. Rewriting prompts to be less explicit dramatically increases compliance and reveals that many harmful requests slip past monitors, especially when phrasing is softened. Fine‑tuning guards on these rewritten prompts improves recall from 0.24 to 0.89 on answered requests and generalizes to unseen benchmarks.
By Sripad Karne
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
By Jiayi Li, Kun Zhan
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:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
By Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov, Vladimir Bashun
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
By Long P. Hoang, Hai V. Le, Shaoyang Xu, Wei Lu, Wenxuan Zhang
The paper investigates whether response safety can be measured by the cosine similarity between a response embedding and the mean embedding of known‑safe responses. Using four frozen encoders and prompt‑controlled datasets, the authors find that a simple prototype (mean safe embedding) performs poorly (ROC‑AUC 0.457‑0.545) while an explicit safe‑minus‑unsafe reference achieves higher scores (0.588‑0.738). The study shows that a class mean is merely a location, not a safety direction, and that a reference with sufficient unsafe mass is needed to orient safety judgments.
By Sahil Kadadekar
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
The paper introduces CarryOnBench, an interactive benchmark that tests whether large language models can revise their interpretation of user intent and recover utility while staying safe in multi‑turn conversations. Using 398 harmful‑looking queries with benign intents, the benchmark simulates 5,970 conversations across 14 models, evaluating both intent‑aligned utility and safety with a new metric called Ben‑Util. Results show that models often withhold information due to misinterpretation, but most can recover with clarifications, revealing failure modes such as unsafe and redundant recovery that single‑turn tests miss.
By Mingqian Zheng, Malia Morgan, Liwei Jiang, Carolyn Rose, Maarten Sap
arXiv:2610.07723v1 Announce Type: cross
Abstract: Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activat...
By Yibo Zhang, Tianrong Guan, Liang Lin, Puze Wang, Jin Wang, Qingsong Wen
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
By Yongxi Zhou, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, Lai Yun Choi
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov
SentryBench is a cost‑sensitive benchmark designed to evaluate large language model agents that use tools in public‑safety contexts. It measures agents on a frontier that jointly considers attack success, over‑refusal (missing real emergencies), and over‑reaction (unwarranted actions) under adversarial tool use, using scenarios grounded in real emergency‑call transcripts and disaster messages. The study shows that naive caution leads to high harm, while a targeted trust‑gate wrapper reduces harm across models and defenses.
By Md Abu Yusuf, Oyshi Tabassum Aditi, Md Faysal Hosain Mazed