LongSafetyBench: Long-Context LLMs Struggle with Safety Issues
Keywords: Long-Context Language Model, Model Safety, Benchmark
Abstract: With the development of large language models (LLMs), the sequence length of these models continues to increase, drawing significant attention to long-context language models. However, the evaluation of these models has been primarily limited to their capabilities, with a lack of research focusing on their safety. Existing work, such as ManyShotJailbreak, has to some extent demonstrated that long-context language models can exhibit safety concerns. However, the methods used are limited and lack comprehensiveness. In response, we introduce **LongSafetyBench**, the first benchmark designed to objectively and comprehensively evaluate the safety of long-context models. LongSafetyBench consists of 10 task categories, with an average length of 41,889 words. After testing eight long-context language models on LongSafetyBench, we found that existing models generally exhibit insufficient safety capabilities. Moreover, models' safety performance in long-context scenarios does not always align with that in short-context scenarios. Further investigation revealed that long-context models tend to overlook harmful content within lengthy texts. We also proposed a simple yet effective solution, allowing open-source models to achieve performance comparable to that of top-tier closed-source models. We believe that LongSafetyBench can serve as a valuable benchmark for evaluating the safety capabilities of long-context language models. We hope that our work will encourage the broader community to pay attention to the safety of long-context models and contribute to the development of solutions to improve the safety of long-context LLMs.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8741
Loading