AI News HubLIVE
Original source2 min read

CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety

A new framework called CR4T proposes rewriting unsafe or refusal-oriented LLM outputs into age-appropriate guidance for adolescents, offering a more human-centered alternative to traditional safety guardrails.

SourcearXiv Computational LinguisticsAuthor: Heajun An, Qi Zhang, Vedanth Achanta, Jin-Hee Cho

[2605.21609] CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety

[Submitted on 20 May 2026]

Title:CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety

View a PDF of the paper titled CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety, by Heajun An and 2 other authors

View PDF HTML (experimental)

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.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY)

Cite as: arXiv:2605.21609 [cs.CL]

(or arXiv:2605.21609v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2605.21609

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Heajun An [view email] [v1] Wed, 20 May 2026 18:16:18 UTC (3,014 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CR4T: Rewrite-Based Guardrails for Adolescent LLM Safety, by Heajun An and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-05

Change to browse by:

cs cs.AI cs.CY

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)