LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

• URL: http://arxiv.org/abs/2408.07055v1
• Date: Tue, 13 Aug 2024 17:46:12 GMT
• Title: LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
• Authors: Yushi Bai, Jiajie Zhang, Xin Lv, Linzhi Zheng, Siqi Zhu, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li,
• Abstract summary: Long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. We introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks. We construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words.
• Score: 57.23637303451716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current long context large language models (LLMs) can process inputs up to 100,000 tokens, yet struggle to generate outputs exceeding even a modest length of 2,000 words. Through controlled experiments, we find that the model's effective generation length is inherently bounded by the sample it has seen during supervised fine-tuning (SFT). In other words, their output limitation is due to the scarcity of long-output examples in existing SFT datasets. To address this, we introduce AgentWrite, an agent-based pipeline that decomposes ultra-long generation tasks into subtasks, enabling off-the-shelf LLMs to generate coherent outputs exceeding 20,000 words. Leveraging AgentWrite, we construct LongWriter-6k, a dataset containing 6,000 SFT data with output lengths ranging from 2k to 32k words. By incorporating this dataset into model training, we successfully scale the output length of existing models to over 10,000 words while maintaining output quality. We also develop LongBench-Write, a comprehensive benchmark for evaluating ultra-long generation capabilities. Our 9B parameter model, further improved through DPO, achieves state-of-the-art performance on this benchmark, surpassing even much larger proprietary models. In general, our work demonstrates that existing long context LLM already possesses the potential for a larger output window--all you need is data with extended output during model alignment to unlock this capability. Our code & models are at: https://github.com/THUDM/LongWriter.

Related papers

• LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models [60.79418872734049]
  LongWriter-V-22k is a dataset of 22,158 examples with multiple input images, an instruction, and corresponding outputs ranging from 0 to 10,000 words. We propose IterDPO, which breaks long outputs into segments and uses iterative corrections to form preference pairs with the original outputs. Our 7B parameter model, trained with LongWriter-V-22k and IterDPO, achieves impressive performance on a benchmark.
  arXiv  Detail & Related papers  (2025-02-20T18:47:36Z)
• LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation [74.89981179257194]
  LongProc (Long Procedural Generation) is a new benchmark for evaluating long-context language models (LCLMs) LongProc consists of six diverse procedural generation tasks, such as extracting structured information from HTML pages into a TSV format and executing complex search procedures to create travel plans. We evaluate 17 LCLMs on LongProc across three difficulty levels, with maximum numbers of output tokens set at 500, 2K, and 8K. Notably, while all tested models claim a context window size above 32K tokens, open-weight models typically falter on 2K-token tasks, and closed-source models like GPT
  arXiv  Detail & Related papers  (2025-01-09T18:16:55Z)
• LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models [61.12177317970258]
  LongSkywork is a long-context Large Language Model capable of processing up to 200,000 tokens. We develop two novel methods for creating synthetic data. LongSkywork achieves outstanding performance on a variety of long-context benchmarks.
  arXiv  Detail & Related papers  (2024-06-02T03:34:41Z)
• Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks [76.43527940649939]
  We introduce Ada-LEval, a benchmark for evaluating the long-context understanding of large language models (LLMs) Ada-LEval includes two challenging subsets, TSort and BestAnswer, which enable a more reliable evaluation of LLMs' long context capabilities. We evaluate 4 state-of-the-art closed-source API models and 6 open-source models with Ada-LEval.
  arXiv  Detail & Related papers  (2024-04-09T17:30:48Z)
• LongAlign: A Recipe for Long Context Alignment of Large Language Models [61.85923382850057]
  LongAlign is a recipe of the instruction data, training, and evaluation for long context alignment. We construct a long instruction-following dataset using Self-Instruct. We adopt the packing and sorted strategies to speed up supervised fine-tuning on data with varied length distributions.
  arXiv  Detail & Related papers  (2024-01-31T18:29:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.