Research map / Large language models / Retrieval and knowledge
TAdaRAG: Task Adaptive Retrieval-Augmented Generation via On-the-Fly Knowledge Graph Construction
Jie Zhang, Bo Tang, Wanzi Shao, Wenqiang Wei, Jihao Zhao, Jianqing Zhu, Zhiyu Li, Wen Xi, Zehao Lin, Feiyu Xiong, Yanchao Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add prompt-based task-adaptive KG to NaiveRAG (ablation) | Mistral-7B-Instruct · 2WikiMQA | F1: 20.60 -> 38.48 | Improved |
| add supervised knowledge extraction fine-tuning (ablation) | Mistral-7B-Instruct · UltraDomain Legal | F1: 32.92 -> 39.32 | Improved |
| add REINFORCE task-adaptive KG construction (ablation) | Mistral-7B-Instruct · UltraDomain Legal | F1: 39.32 -> 49.88 | Improved |
| add REINFORCE stage (ablation) | Qwen2.5-7B-Instruct · HotpotQA | F1: 49.03 -> 49.23 | Improved |
| add REINFORCE stage (ablation) | Qwen2.5-7B-Instruct · UltraDomain Health | F1: 41.35 -> 42.38 | Improved |
| use TAdaRAG instead of MemoRAG | Mistral-7B-Instruct · UltraDomain Legal | F1: 51.20 -> 49.88 | Hurt |
| use TAdaRAG instead of MemoRAG | Qwen2.5-7B-Instruct · UltraDomain Legal | F1: 47.60 -> 46.83 | Hurt |
| use TAdaRAG instead of MemoRAG | Mistral-7B-Instruct · 2WikiMQA | F1: 30.30 -> 39.31 | Improved |
| use TAdaRAG instead of MemoRAG | Mistral-7B-Instruct · GovReport | ROUGE-L: 31.60 -> 36.41 | Improved |
| use TAdaRAG vs best baseline on NowNewsQA (human rating) | Mistral-7B-Instruct · NowNewsQA | overall average human score: 7.720 -> 7.904 | Improved |
| increase parallel subgraphs from 3 to 4 or 5 (ablation) | TAdaRAG 7B models · most datasets | F1 | Hurt |
| use 4 subgraphs instead of 3 (ablation) | TAdaRAG · GovReport | ROUGE-L | Improved |
Closest papers by meaning
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.92)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.91)
- From Complex to Atomic: Enhancing Augmented Generation via Knowledge-Aware Dual Rewriting and Reasoning (ICML 2025 · similarity 0.91)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.90)
- Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs (AAAI 2025 · similarity 0.90)
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
