1
Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM
轻量模型Dripper精准提取网页主内容,大幅降低Token消耗,提升LLM预处理效率。
arXiv:2511.23119v3 Announce Type: replace Abstract: High-quality main content extraction from web pages is a critical prerequisite for constructing la…