diff options
| author | Qing145 <68147254+Qing145@users.noreply.github.com> | 2025-10-27 11:10:59 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-10-27 11:10:59 +0800 |
| commit | e7a3b517ccb2b0a9643edf9ece25d5a94453f393 (patch) | |
| tree | cca0b8aaa1fdfc2135e5d4cafdc74732535012ab | |
| parent | 73a1e631e539c1c323060851c708b37e963f9592 (diff) | |
Update readme.md
| -rw-r--r-- | readme.md | 6 |
1 files changed, 3 insertions, 3 deletions
@@ -1,4 +1,4 @@ -# 🌟 **LinearRAG** +# 🌟 **LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora** > A lightweight GraphRAG framework that eliminates LLM token cost during graph construction – making GraphRAG faster and more efficient than ever. @@ -17,7 +17,7 @@ --- ## 🚀 **Highlights** -- ✅ **Fact-Level Faithfulness**: Eliminates unstable relation extraction, using only lightweight entity recognition to graph. +- ✅ **Relation-free Graph Construction**: Eliminates unstable relation extraction, using only lightweight entity recognition to graph. - 🔥 **Zero Token Consumption**: Complete graph construction and retrieval without any LLM calls. - 📊 **Strong Results**: Outperforms previous RAG methods on widely-used benchmarks. @@ -115,4 +115,4 @@ If you find this work helpful, please consider citing us: } ``` ## 📬 Contact -✉️ Email: zhuangluyao523@gmail.com
\ No newline at end of file +✉️ Email: zhuangluyao523@gmail.com |