PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908769669087232 |
|---|---|
| author | Jiao, Shuguang Xiao, Xinyu Wei, Yunfan Qi, Shuhan Huang, Chengkai Sheng, Quan Z. Michael Yao, Lina |
| author_facet | Jiao, Shuguang Xiao, Xinyu Wei, Yunfan Qi, Shuhan Huang, Chengkai Sheng, Quan Z. Michael Yao, Lina |
| contents | Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains deepen or search trees expand, RAG systems often face two persistent failures: evidence forgetting, where retrieved knowledge is not effectively used, and inefficiency, caused by uncontrolled query expansions and redundant retrieval. These issues reveal a critical gap between retrieval and evidence utilization in current RAG architectures. We propose PruneRAG, a confidence-guided query decomposition framework that builds a structured query decomposition tree to perform stable and efficient reasoning. PruneRAG introduces three key mechanisms: adaptive node expansion that regulates tree width and depth, confidence-guided decisions that accept reliable answers and prune uncertain branches, and fine-grained retrieval that extracts entity-level anchors to improve retrieval precision. Together, these components preserve salient evidence throughout multi-hop reasoning while significantly reducing retrieval overhead. To better analyze evidence misuse, we define the Evidence Forgetting Rate as a metric to quantify cases where golden evidence is retrieved but not correctly used. Extensive experiments across various multi-hop QA benchmarks show that PruneRAG achieves superior accuracy and efficiency over state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11024 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation Jiao, Shuguang Xiao, Xinyu Wei, Yunfan Qi, Shuhan Huang, Chengkai Sheng, Quan Z. Michael Yao, Lina Information Retrieval Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains deepen or search trees expand, RAG systems often face two persistent failures: evidence forgetting, where retrieved knowledge is not effectively used, and inefficiency, caused by uncontrolled query expansions and redundant retrieval. These issues reveal a critical gap between retrieval and evidence utilization in current RAG architectures. We propose PruneRAG, a confidence-guided query decomposition framework that builds a structured query decomposition tree to perform stable and efficient reasoning. PruneRAG introduces three key mechanisms: adaptive node expansion that regulates tree width and depth, confidence-guided decisions that accept reliable answers and prune uncertain branches, and fine-grained retrieval that extracts entity-level anchors to improve retrieval precision. Together, these components preserve salient evidence throughout multi-hop reasoning while significantly reducing retrieval overhead. To better analyze evidence misuse, we define the Evidence Forgetting Rate as a metric to quantify cases where golden evidence is retrieved but not correctly used. Extensive experiments across various multi-hop QA benchmarks show that PruneRAG achieves superior accuracy and efficiency over state-of-the-art baselines. |
| title | PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.11024 |