# LongSafety: Enhance Safety for Long-Context LLMs

arXiv: https://arxiv.org/abs/2411.06899 · HTML: https://mlsanity.com/paper/2411.06899/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 31 of its 56 references that are in the map.
- First posted on arXiv 11 Nov 2024.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2402.05044/) (2024)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Scaling Laws of RoPE-based Extrapolation](https://mlsanity.com/paper/2310.05209/) (2023)
- [Fake Alignment: Are LLMs Really Aligned Well?](https://mlsanity.com/paper/2311.05915/) (2023)
- [Suri: Multi-constraint Instruction Following for Long-form Text Generation](https://mlsanity.com/paper/2406.19371/) (2024)
- [Parameter-Efficient Legal Domain Adaptation](https://mlsanity.com/paper/2210.13712/) (2022)
- [MDCure: A Scalable Pipeline for Multi-Document Instruction-Following](https://mlsanity.com/paper/2410.23463/) (2024)
- [InternEvo: Efficient Long-sequence Large Language Model Training via Hybrid Parallelism and Redundant Sharding](https://mlsanity.com/paper/2401.09149/) (2024)

## Built on by (most cited first, 11 of 11)

- [o3-mini vs DeepSeek-R1: Which One is Safer?](https://mlsanity.com/paper/2501.18438/) (2025)
- [Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem](https://mlsanity.com/paper/2512.08290/) (2025)
- [Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation](https://mlsanity.com/paper/2501.17749/) (2025)
- [LongSafety: Evaluating Long-Context Safety of Large Language Models](https://mlsanity.com/paper/2502.16971/) (2025)
- [Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment](https://mlsanity.com/paper/2510.13698/) (2025)
- [TRACE: Trajectory Risk-Aware Compression for Long-Horizon Agent Safety](https://mlsanity.com/paper/2606.00611/) (2026)
- [On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs](https://mlsanity.com/paper/2510.05864/) (2025)
- [Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models](https://mlsanity.com/paper/2604.00547/) (2026)
- [Defending Against Harmful Supervision Hidden in Benign Samples](https://mlsanity.com/paper/2606.30263/) (2026)
- [Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models](https://mlsanity.com/paper/2607.02914/) (2026)
- [LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails](https://mlsanity.com/paper/2608.27580/) (2026)

## Abstract (arXiv)

Recent advancements in model architectures and length extrapolation techniques have significantly extended the context length of large language models (LLMs), paving the way for their application in increasingly complex tasks. However, despite the growing capabilities of long-context LLMs, the safety issues in long-context scenarios remain underexplored. While safety alignment in short context has been widely studied, the safety concerns of long-context LLMs have not been adequately addressed. In this work, we introduce LongSafety, a comprehensive safety alignment dataset for long-context LLMs, containing 10 tasks and 17k samples, with an average length of 40.9k tokens. Our experiments demonstrate that training with LongSafety can enhance long-context safety performance while enhancing short-context safety and preserving general capabilities. Furthermore, we demonstrate that long-context safety does not equal long-context alignment with short-context safety data and LongSafety has generalizing capabilities in context length and long-context safety scenarios.