Metraipolis › archive › dc_acc0045fb74a

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction — arXiv:2609.35892

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35892
License (as archived)
CC0-1.0
Archived
2026-10-07T17:26:46.532Z
SHA-256 of the archived text
78cb03b1adf5efe8c75db8cc77dbafa186f39a444c2ac72b690f721231229437
Stable URL of this page
https://metraipolis.com/documento/dc_acc0045fb74a

How to cite

SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction — arXiv:2609.35892 — arXiv (en), https://arxiv.org/abs/2609.35892 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acc0045fb74a (Metraipolis archive dc_acc0045fb74a, sha256 78cb03b1adf5efe8c75db8cc77dbafa186f39a444c2ac72b690f721231229437)
BibTeX
@misc{dcacc0045fb74a,
  title = {SaplingGuard: A Multidimensional-Profile-Aware Multi-Agent Guardrail for Developmentally Safe Adolescent-LLM Interaction — arXiv:2609.35892},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35892},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acc0045fb74a; sha256 78cb03b1adf5efe8c75db8cc77dbafa186f39a444c2ac72b690f721231229437},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35892. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As adolescents increasingly use LLMs in everyday life, ensuring safe and developmentally appropriate responses has become essential. However, existing LLM guardrails primarily target explicit harmful content in isolated prompts or responses and are less effective at identifying implicit, context-dependent developmental risks. To address this limitation, we propose SaplingGuard, a plug-and-play, profile-aware and dialogue-aware guardrail that requires no modification to downstream model parameters. SaplingGuard decomposes adolescent safety intervention into three specialized agents for user profile construction, context-aware risk assessment, and intent-preserving prompt optimization. Together, these agents leverage the current prompt, preceding dialogue, and structured user characteristics to identify contextual risks and guide downstream response generation. We evaluate SaplingGuard on SaplingBench, which contains 276 three-turn dialogues spanning seven categories of developmental risk. Across ten adolescent profile conditions and nine open- and closed-source downstream LLMs, profile-aware retrieval improves the Major Hit rate from 50.8% to 63.7+/-1.1%. End-to-end intervention further reduces the average harmful response rate from 17.10% to 5.27% and increases the average safety score from 0.7017 to 1.0043. These results show that user-profile and dialogue context provide complementary signals for identifying implicit developmental risks, and that SaplingGuard can serve as an effective external safety layer for adolescent-LLM interaction.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.35892 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:58:17.313Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).