# LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

arXiv: https://arxiv.org/abs/2409.00509 · HTML: https://mlsanity.com/paper/2409.00509/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 46 references that are in the map.
- First posted on arXiv 31 Aug 2024.

## Builds on (most cited first, 30 of 38)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [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)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [Data Engineering for Scaling Language Models to 128K Context](https://mlsanity.com/paper/2402.10171/) (2024)
- [Hurdles to Progress in Long-form Question Answering](https://mlsanity.com/paper/2103.06332/) (2021)
- [LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning](https://mlsanity.com/paper/2401.01325/) (2024)
- [A Length-Extrapolatable Transformer](https://mlsanity.com/paper/2212.10554/) (2022)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Randomized Positional Encodings Boost Length Generalization of Transformers](https://mlsanity.com/paper/2305.16843/) (2023)

## Built on by (most cited first, 23 of 23)

- [How to Train Long-Context Language Models (Effectively)](https://mlsanity.com/paper/2410.02660/) (2024)
- [What is Wrong with Perplexity for Long-context Language Modeling?](https://mlsanity.com/paper/2410.23771/) (2024)
- [Why Does the Effective Context Length of LLMs Fall Short?](https://mlsanity.com/paper/2410.18745/) (2024)
- [AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning](https://mlsanity.com/paper/2412.03248/) (2024)
- [LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation](https://mlsanity.com/paper/2501.05414/) (2025)
- [V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding](https://mlsanity.com/paper/2412.09616/) (2024)
- [LongRoPE2: Near-Lossless LLM Context Window Scaling](https://mlsanity.com/paper/2502.20082/) (2025)
- [QFFT, Question-Free Fine-Tuning for Adaptive Reasoning](https://mlsanity.com/paper/2506.12860/) (2025)
- [DAPE V2: Process Attention Score as Feature Map for Length Extrapolation](https://mlsanity.com/paper/2410.04798/) (2024)
- [WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale](https://mlsanity.com/paper/2502.16684/) (2025)
- [FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning](https://mlsanity.com/paper/2601.03938/) (2026)
- [Scale-invariant Attention](https://mlsanity.com/paper/2505.17083/) (2025)
- [AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning](https://mlsanity.com/paper/2509.17348/) (2025)
- [ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs](https://mlsanity.com/paper/2504.16394/) (2025)
- [Improving Alignment in LVLMs with Debiased Self-Judgment](https://mlsanity.com/paper/2508.20655/) (2025)
- [Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval](https://mlsanity.com/paper/2508.19740/) (2025)
- [DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models](https://mlsanity.com/paper/2602.22175/) (2026)
- [Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model](https://mlsanity.com/paper/2502.01090/) (2025)
- [UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference](https://mlsanity.com/paper/2603.18446/) (2026)
- [Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation](https://mlsanity.com/paper/2604.14339/) (2026)
- [CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2502.11101/) (2025)
- [On the Limitations and Capabilities of Position Embeddings for Length Generalization](https://mlsanity.com/paper/2510.04130/) (2025)
- [Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension](https://mlsanity.com/paper/2608.10296/) (2026)

## Abstract (arXiv)

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive. To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maintaining training efficiency and significantly improves the model's understanding of long-range dependencies. Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size, and reduces computational training resource over 85% compared to full sequence training. Furthermore, LongRecipe also preserves the original LLM's capabilities in general tasks. Ultimately, we can extend the effective context window of open-source LLMs from 8k to 128k, achieving performance close to GPT-4 with just one day of dedicated training using a single GPU with 80G memory. Our code is released at https://github.com/zhiyuanhubj/LongRecipe.