LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913426067947520 |
|---|---|
| author | Jin, Hongye Han, Xiaotian Yang, Jingfeng Jiang, Zhimeng Liu, Zirui Chang, Chia-Yuan Chen, Huiyuan Hu, Xia |
| author_facet | Jin, Hongye Han, Xiaotian Yang, Jingfeng Jiang, Zhimeng Liu, Zirui Chang, Chia-Yuan Chen, Huiyuan Hu, Xia |
| contents | It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inference. In this work, we argue that LLMs themselves have inherent capabilities to handle long contexts without fine-tuning. To achieve this goal, we propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information: the grouped attention and the neighbor attention. The grouped attention captures the dependencies among tokens that are far apart, while neighbor attention captures dependencies among adjacent tokens within a specified range. The two-level attentions are computed based on the original model's self-attention mechanism during inference. With minor code modification, our SelfExtend can effortlessly extend existing LLMs' context window without any fine-tuning. We conduct comprehensive experiments on multiple benchmarks and the results show that our SelfExtend can effectively extend existing LLMs' context window length. The code can be found at \url{https://github.com/datamllab/LongLM}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01325 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning Jin, Hongye Han, Xiaotian Yang, Jingfeng Jiang, Zhimeng Liu, Zirui Chang, Chia-Yuan Chen, Huiyuan Hu, Xia Computation and Language Artificial Intelligence Machine Learning It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inference. In this work, we argue that LLMs themselves have inherent capabilities to handle long contexts without fine-tuning. To achieve this goal, we propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information: the grouped attention and the neighbor attention. The grouped attention captures the dependencies among tokens that are far apart, while neighbor attention captures dependencies among adjacent tokens within a specified range. The two-level attentions are computed based on the original model's self-attention mechanism during inference. With minor code modification, our SelfExtend can effortlessly extend existing LLMs' context window without any fine-tuning. We conduct comprehensive experiments on multiple benchmarks and the results show that our SelfExtend can effectively extend existing LLMs' context window length. The code can be found at \url{https://github.com/datamllab/LongLM}. |
| title | LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.01325 |