LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912328517156864 |
|---|---|
| author | Wang, Haoyu Fu, Yujia Zhang, Zhu Wang, Shuo Ren, Zirui Wang, Xiaorong Li, Zhili He, Chaoqun An, Bo Liu, Zhiyuan Sun, Maosong |
| author_facet | Wang, Haoyu Fu, Yujia Zhang, Zhu Wang, Shuo Ren, Zirui Wang, Xiaorong Li, Zhili He, Chaoqun An, Bo Liu, Zhiyuan Sun, Maosong |
| contents | Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM$\times$MapReduce-V2, a novel test-time scaling strategy designed to enhance the ability of LLMs to process extremely long inputs. Drawing inspiration from convolutional neural networks, which iteratively integrate local features into higher-level global representations, LLM$\times$MapReduce-V2 utilizes stacked convolutional scaling layers to progressively expand the understanding of input materials. Both quantitative and qualitative experimental results demonstrate that our approach substantially enhances the ability of LLMs to process long inputs and generate coherent, informative long-form articles, outperforming several representative baselines. Both LLM$\times$MapReduce-V2 and SurveyEval are publicly available at https://github.com/thunlp/LLMxMapReduce . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05732 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources Wang, Haoyu Fu, Yujia Zhang, Zhu Wang, Shuo Ren, Zirui Wang, Xiaorong Li, Zhili He, Chaoqun An, Bo Liu, Zhiyuan Sun, Maosong Computation and Language Long-form generation is crucial for a wide range of practical applications, typically categorized into short-to-long and long-to-long generation. While short-to-long generations have received considerable attention, generating long texts from extremely long resources remains relatively underexplored. The primary challenge in long-to-long generation lies in effectively integrating and analyzing relevant information from extensive inputs, which remains difficult for current large language models (LLMs). In this paper, we propose LLM$\times$MapReduce-V2, a novel test-time scaling strategy designed to enhance the ability of LLMs to process extremely long inputs. Drawing inspiration from convolutional neural networks, which iteratively integrate local features into higher-level global representations, LLM$\times$MapReduce-V2 utilizes stacked convolutional scaling layers to progressively expand the understanding of input materials. Both quantitative and qualitative experimental results demonstrate that our approach substantially enhances the ability of LLMs to process long inputs and generate coherent, informative long-form articles, outperforming several representative baselines. Both LLM$\times$MapReduce-V2 and SurveyEval are publicly available at https://github.com/thunlp/LLMxMapReduce . |
| title | LLM$\times$MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.05732 |