arXiv Machine Learning

CAREBench: A Child-Safety Risk Benchmark for Language Models

arXiv:2606. 29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm?

Hugging Face Trending Papers
Jun 29

CAREBench: A Child-Safety Risk Benchmark for Language Models

How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm? Existing child safety evaluations focus on child sexual abuse material, yet many child-safety failures begin earlier: in model assistance that helps adults manipulate, impersonate, profile, or isolate minors, and in model responses that deepen children's emotional dependence on AI systems rather than redirecting them toward human support.

arXiv AI
Jun 9

When Behavioral Safety Evaluation Fails: A Representation-Level Perspective

arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.

By Enyi Jiang, Anders Gj{\o}lbye, Yibo Jacky Zhang, Sanmi Koyejo
arXiv AI
Aug 6

Item Response Theory for AI Safety

arXiv:2608. 05086v1 Announce Type: new Abstract: Language models differ in how safely they behave and these differences are measured by safety benchmarks.

By Joshua Fonseca Rivera (Independent), Neil Shah (Independent), David Demitri Africa (UK AI Security Institute), Konstantinos Voudouris (UK AI Security Institute)
arXiv AI
Jun 18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.

By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang
arXiv AI
Jun 24

One Year Later...The Harms Persist, But So Do We!

arXiv:2606. 23884v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical conditions.

By Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar, Anson Antony