CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety

• URL: http://arxiv.org/abs/2605.21609v1
• Date: Wed, 20 May 2026 18:16:18 GMT
• Title: CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety
• Abstract summary: Large language models (LLMs) are increasingly embedded in adolescent digital environments.<n>Existing safety mechanisms remain largely grounded in adult-centric norms.<n>We propose Critique-and-Revise-for-Teenagers (CR4T), a model-agnostic safeguarding framework.
• Score: 9.164865563559891
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly embedded in adolescent digital environments, mediating information seeking, advice, and emotionally sensitive interactions. Yet existing safety mechanisms remain largely grounded in adult-centric norms and operationalize safety through refusal-oriented suppression. While such approaches may reduce immediate policy violations, they can also create conversational dead-ends, limit constructive guidance, and fail to address the developmental vulnerabilities inherent in adolescent-AI interactions. We argue that adolescent LLM safety should be framed not solely as a filtering problem, but as a socio-technical, developmentally aligned transformation problem. To operationalize this perspective, we propose Critique-and-Revise-for-Teenagers (CR4T), a model-agnostic safeguarding framework that selectively reconstructs unsafe or refusal-style outputs into ageappropriate, guidance-oriented responses while preserving benign intent. CR4T combines lightweight risk detection with domain-conditioned rewriting to remove risk-amplifying content, reduce unnecessary conversational shutdown, and introduce developmentally appropriate guidance. Experimental results show that targeted rewriting substantially reduces unsafe and refusal-oriented outcomes while avoiding unnecessary intervention on acceptable interactions. These findings suggest that selective response reconstruction offers a more human-centered alternative to refusal-centric guardrails for adolescent-facing LLM systems.

Related papers

• SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure [7.121327089434882]
  SRD-GUARD is a parameter-free, black-box defense framework that exposes concealed intent through semantic rewriting and consensus-based risk assessment.<n>We evaluate SRD-GUARD against UNIATTACK, CIPHER, and DeepInception on Llama-3-8B-Uncensored and DeepSeek-V4-Flash.
  arXiv  Detail & Related papers  (2026-09-06T11:26:08Z)
• Steering LLM Viewpoints through Fabricated Evidence Injection [61.22850755490993]
  We introduce a two-phase attack framework that first repackages misleading statements with fabricated rationales, then instruct target LLMs to incorporate these viewpoints when responding to relevant queries.<n>Experiments on BBQ, ToxiGen, and our specialized dataset reveal that commercial LLMs without external safety classifiers remain highly vulnerable.<n>Building on this, we explore multiple defense strategies, among which a tailored safety policy enablesgpt-oss-safeguard to achieve 81% detection rate.
  arXiv  Detail & Related papers  (2026-06-04T14:48:23Z)
• Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information [9.845529341562099]
  SemSIEdit is an inference-time framework where an agentic "Editor" iteratively critiques and rewrites sensitive spans to preserve narrative flow.<n>Our analysis reveals a Privacy-Utility Frontier, where this agentic rewriting reduces leakage by 34.6% while incurring a marginal utility loss of 9.8%.
  arXiv  Detail & Related papers  (2026-02-25T02:09:23Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models [93.5740266114488]
  Constructive Safety Alignment (CSA) protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results.<n>Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities.<n>We release Oy1, code, and the benchmark to support responsible, user-centered AI.
  arXiv  Detail & Related papers  (2025-09-02T03:04:27Z)
• SproutBench: A Benchmark for Safe and Ethical Large Language Models for Youth [14.569766143989531]
  The rapid proliferation of large language models (LLMs) in applications targeting children and adolescents necessitates a fundamental reassessment of prevailing AI safety frameworks.<n>This paper highlights key deficiencies in existing LLM safety benchmarks, including their inadequate coverage of age-specific cognitive, emotional, and social risks.<n>We introduce SproutBench, an innovative evaluation suite comprising 1,283 developmentally grounded adversarial prompts designed to probe risks such as emotional dependency, privacy violations, and imitation of hazardous behaviors.
  arXiv  Detail & Related papers  (2025-08-14T18:21:39Z)
• Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions [8.018569128518187]
  We introduce Safe-Child-LLM, a benchmark and dataset for assessing AI safety across two developmental stages: children (7-12) and adolescents (13-17).<n>Our framework includes a novel multi-part dataset of 200 adversarial prompts, curated from red-teaming corpora, with human-annotated labels for jailbreak success and a standardized 0-5 ethical refusal scale.<n> evaluating leading LLMs -- including ChatGPT, Claude, Gemini, LLaMA, DeepSeek, Grok, Vicuna, and Mistral -- we uncover critical safety deficiencies in child-facing scenarios.
  arXiv  Detail & Related papers  (2025-06-16T14:04:54Z)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks [85.3303135160762]
  MIRAGE is a novel framework that exploits narrative-driven context and role immersion to circumvent safety mechanisms in Multimodal Large Language Models.<n>It achieves state-of-the-art performance, improving attack success rates by up to 17.5% over the best baselines.<n>We demonstrate that role immersion and structured semantic reconstruction can activate inherent model biases, facilitating the model's spontaneous violation of ethical safeguards.
  arXiv  Detail & Related papers  (2025-03-24T20:38:42Z)
• Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning [43.209846711845536]
  Current alignment strategies rely on supervised safety fine-tuning with curated datasets.<n>We show that supervised fine-tuning inadvertently reinforces spurious correlations between superficial textual patterns and safety responses.<n>We show that machine unlearning (MU) is a powerful alternative to supervised safety fine-tuning.
  arXiv  Detail & Related papers  (2025-03-14T19:52:08Z)
• Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models [53.580928907886324]
  Reasoning-Augmented Conversation is a novel multi-turn jailbreak framework.<n>It reformulates harmful queries into benign reasoning tasks.<n>We show that RACE achieves state-of-the-art attack effectiveness in complex conversational scenarios.
  arXiv  Detail & Related papers  (2025-02-16T09:27:44Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• On Prompt-Driven Safeguarding for Large Language Models [172.13943777203377]
  We find that in the representation space, the input queries are typically moved by safety prompts in a "higher-refusal" direction. Inspired by these findings, we propose a method for safety prompt optimization, namely DRO. Treating a safety prompt as continuous, trainable embeddings, DRO learns to move the queries' representations along or opposite the refusal direction, depending on their harmfulness.
  arXiv  Detail & Related papers  (2024-01-31T17:28:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.