Sep 2026· Symposium on Intelligent Systems and Informatics· pp. 025-032· 0 citations· 24 references
TL;DR
A structured methodology that supports future child-centered AI safety evaluation, moderation research, and benchmark extension workflows, and emphasizes reproducible prompt transformation, annotation consistency, and benchmark adaptation rather than classifier development.
Abstract
Large Language Models (LLMs) are increasingly accessible to children through publicly available conversational AI systems, creating new challenges for AI safety and content moderation. While existing jailbreak research has primarily focused on adult-oriented adversarial prompting, considerably less attention has been paid to child-language interaction patterns and their potential influence on moderation robustness. This paper proposes a methodological framework for the controlled transformation and annotation of child-language jailbreak prompts. Building on prior research in jailbreak taxonomy, prompt transformation, child-safe AI, and pragmatic communication theory, the framework defines six child-language-oriented transformation categories: Roleplay, Non-standard linguistic variation, Indirect-request, Meta-prompt, Mentor-mode, and Emotional framing. The proposed workflow transforms adult-oriented benchmark prompts into child-language variants while preserving their underlying objective through semantic anchors and intent-preservation validation. Designed for use with established jailbreak benchmarks, including HarmBench, the framework emphasizes reproducible prompt transformation, annotation consistency, and benchmark adaptation rather than classifier development. The primary contribution is a structured methodology that supports future child-centered AI safety evaluation, moderation research, and benchmark extension workflows.
This Perspective introduces a three-pillar framework for ESE-LLMs: domain perception, knowledge grounding, and action capability, and presents a decision-guided deployment workflow that helps researchers in ESE fields integrate LLMs into their workflow.
Jin-Yue Jiang, Jun-Jie Zhu, Z. Ren· Environmental Science and Te...· 1 citation
This work proposes aligning cross-lingual thoughts and responses (ACTR), a framework that improves multilingual safety alignment by strengthening the use of existing safety reasoning, and devise neuron-selective consistency optimization (NSCO), which uses a frozen judge model to reward agreement between the safety cate...
Large Language Models (LLMs) can explain sensitive topics across domains, but harmful goals may be concealed behind educational, fictional, historical, or research-oriented framing. We study Human Indirect Prompting (HIP), a conversation-level behavior in which a user steers an LLM toward restricted information without...
Unais Sait, Saravanakumar Duraisamy· Proceedings of the 35th ACM...· 0 citations
Large language models (LLMs) are widely used in information retrieval, content generation, and interactive question answering, and their safety alignment continues to be challenged by textual jailbreak attacks. Under a unified task definition for textual jailbreak attacks and defenses, this review follows the expansion...
Ding-Yu Wu· Applied and Computational En...· 0 citations
As AI systems are increasingly deployed in high-stakes domains, regulatory and societal demands for transparency and interpretability continue to grow. While classical Explainable AI (XAI) methods produce structured technical artifacts (e.g., feature attributions and counterfactual examples), these remain difficult to...
Gabriele Tolomei, Zi-Heng Chen, Flavio Giorgi et al.· Proceedings of the 35th ACM...· 0 citations
Generative artificial intelligence (GenAI) is increasingly used in second-language writing, while translanguaging can serve as a pedagogical resource for mobilizing multilingual repertoires. Neither resource is inherently metacognitive. This Perspective conceptualizes intentional translanguaging and GenAI as complement...
Mario Alvarado-Mendoza, Alexis Contreras-Falcones· Frontiers in Education· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.