Research map / Large language models / Retrieval and knowledge
From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
Qichuan Liu, Qinggang Zhang, Yuxuan Hu, Chenfeng Zheng, Zerui Chen, Chentao Zhang, Zhihong Zhang
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 structure-aware fine-tuning (ablation) | KG-Translator (Llama) · HotpotQA/2WikiMQA/MuSiQue average | F1: 59.36 -> 68.50 | Improved |
| add structure-aware fine-tuning (ablation) | KG-Translator (Llama) · 2WikiMQA | F1: 63.25 -> 78.52 | Improved |
| add reverse translation (ablation) | KG-Translator (Llama) · MuSiQue | F1: 37.12 -> 43.32 | Improved |
| add reverse translation (ablation) | KG-Translator (Llama) · average of three datasets | F1: 66.08 -> 68.50 | Improved |
| use forward-then-reverse instead of reverse-then-forward order (ablation) | KG-Translator (Llama) · 2WikiMQA | F1: 68.36 -> 78.52 | Improved |
| scale backbone from Llama-3.2-1B to 3B | KG-Translator · MuSiQue | EM: 33.89 -> 35.80 | Improved |
| scale backbone from Qwen-2.5-1.5B to 3B | KG-Translator · HotpotQA and 2WikiMQA | EM: 73.30 -> 72.90; 73.13 -> 72.28 | No clear effect |
| use larger embedding models instead of all-MiniLM-L6-v2 (ablation) | KG-Translator · HotpotQA/2WikiMQA/MuSiQue average | F1: 69 -> 68 (0.1B), 69 (0.3B), 68 (1.5B) | No clear effect |
| raise alpha from 1 to 3 (beta = 3) (ablation) | KG-Translator · MuSiQue | F1: +3.6% | Improved |
| raise beta from 1 to 3 (alpha = 3) (ablation) | KG-Translator · 2WikiMQA | F1: -1.0% | Hurt |
| increase clues from (alpha, beta) = (3, 3) to (5, 5) (ablation) | KG-Translator · HotpotQA/2WikiMQA/MuSiQue | F1 | No clear effect |
| replace fixed top-5 context with clue-traced retrieval | KG-Translator · contexts per query | context number: 5.00 -> 3.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HippoRAG2 — HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models (NeurIPS 2024) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.91)
- Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need? (NeurIPS 2025 · similarity 0.90)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.90)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.88)
- GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation (NeurIPS 2025 · similarity 0.87)
- A Theory for Token-Level Harmonization in Retrieval-Augmented Generation (ICLR 2025 · similarity 0.87)
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.
