“Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng


Abstract
“Jailbreak” is a major safety concern of Large Language Models (LLMs), which occurs when malicious prompts lead LLMs to produce harmful outputs, raising issues about the reliability and safety of LLMs. Therefore, an effective evaluation of jailbreaks is very crucial to develop its mitigation strategies. However, our research reveals that many jailbreaks identified by current evaluations may actually be hallucinations—erroneous outputs that are mistaken for genuine safety breaches. This finding suggests that some perceived vulnerabilities might not represent actual threats, indicating a need for more precise red teaming benchmarks. To address this problem, we propose the Benchmark for reliABilitY and jailBreak haLlUcination Evaluation (BabyBLUE). BabyBLUE introduces a specialized validation framework including various evaluators to enhance existing jailbreak benchmarks, ensuring outputs are useful malicious instructions. Additionally, BabyBLUE presents a new dataset as an augmentation to the existing red teaming benchmarks, specifically addressing hallucinations in jailbreaks, aiming to evaluate the true potential of jailbroken LLM outputs to cause harm to human society.
Anthology ID:
2025.coling-main.146
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2144–2162
Language:
URL:
https://aclanthology.org/2025.coling-main.146/
DOI:
Bibkey:
Cite (ACL):
Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, and Xueqi Cheng. 2025. “Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2144–2162, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
“Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak (Mei et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.146.pdf