paperMay 2026Unreviewed

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection

Lixing Lin, Juli You, Yue Li, Luyun Lin, Yiqing Wang, Zhen Zhang, Moxuan Zheng

Abstract

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios, fictional framing, and indirect requests. We present Reflect-Guard, a method that augments LLM-based safety classifiers with chain-of-thought self-reflection capabilities through parameter-efficient fine-tuning. Our approach distills analytical reasoning from GPT-4o-m

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{lin2026reflectguard,
  title = {{Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection}},
  author = {Lixing Lin and Juli You and Yue Li and Luyun Lin and Yiqing Wang and Zhen Zhang and Moxuan Zheng},
  year = {2026},
  month = may,
  eprint = {2605.24834},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.24834}
}