自动化构建自回归模型文献流水线，支持可复现的论文检索与实验重跑。
A Reproducible, Scalable Pipeline for Synthesizing Autoregressive Model Literature
- 全开源流水线自动抓取、筛选并提取论文元数据与超参数。
- 在50篇论文上验证，相关性分类等任务F1超0.85，1000篇规模近线性扩展。
- 三案例复现结果误差仅1%-3%，适合研究者快速复现与综述分析。
自回归生成模型研究进展迅猛，已产出数千篇论文，手动文献调研与复现愈发困难。我们提出一个完全开源、可复现的自动化流水线，能从公开仓库中自动获取候选文献，按相关性过滤，提取元数据、超参数及报告结果，进行主题聚类，生成基于检索的摘要，并生成容器化脚本以重跑选定实验。在50篇人工标注论文上的定量评估显示，相关性分类、超参数提取和引用识别的F1得分均高于0.85。在最多1000篇论文的语料上实验表明，该系统在8个CPU工作线程下具备近线性可扩展性。三个案例研究——AWD-LSTM在WikiText-2、Transformer-XL在WikiText-103、自回归音乐模型在Lakh MIDI数据集——证实所提取设置支持精准复现，测试困惑度与原始报告相差仅1%–3%。
原文摘要 · Abstract (English)
The accelerating pace of research on autoregressive generative models has produced thousands of papers, making manual literature surveys and reproduction studies increasingly impractical. We present a fully open-source, reproducible pipeline that automatically retrieves candidate documents from public repositories, filters them for relevance, extracts metadata, hyper-parameters and reported results, clusters topics, produces retrieval-augmented summaries and generates containerised scripts for re-running selected experiments. Quantitative evaluation on 50 manually-annotated papers shows F1 scores above 0.85 for relevance classification, hyper-parameter extraction and citation identification. Experiments on corpora of up to 1000 papers demonstrate near-linear scalability with eight CPU workers. Three case studies -- AWD-LSTM on WikiText-2, Transformer-XL on WikiText-103 and an autoregressive music model on the Lakh MIDI dataset -- confirm that the extracted settings support faithful reproduction, achieving test perplexities within 1--3% of the original reports.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。