Research map / Large language models / Retrieval and knowledge
Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing
Mengying Wang, Chenhui Ma, Ao Jiao, Tuo Liang, Pengjun Lu, Shrinidhi Hegde, Yu Yin, Evren Gurkan-Cavusoglu, Yinghui Wu
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 |
|---|---|---|---|
| remove subgraph summaries before serendipity exploration (ablation) | LLM-guided beam search (most models) · SerenQA T3 (RNS Guided) | SerenHit: DeepSeek-V3 0.077 -> 0.134; Mixtral-8x7B 0.024 -> 0.042 | Improved |
| remove subgraph summaries before serendipity exploration (ablation) | Qwen-2.5-7B · SerenQA T3 (RNS Guided) | SerenHit: 0.041 -> 0.027 | Hurt |
| increase model scale (frontier vs small) | Cypher knowledge retrieval · SerenQA T1 One-Hop | F1 (%): Qwen3-8B 37.24 vs DeepSeek-V3 78.71 | Improved |
| increase query hops (one-hop to 3+ hops) | DeepSeek-V3 / GPT-4o retrieval · SerenQA T1 | F1 (%): DeepSeek-V3 78.71 -> 6.22 | Hurt |
| increase model scale | subgraph reasoning · SerenQA T2 | Faithfulness/Comprehensiveness | No clear effect |
| larger model summaries vs Mixtral summaries | subgraph reasoning · SerenQA T2 | SerenCov: Mixtral 0.642 vs Llama-3.3-70B 0.070 | Mixed |
| switch partition strategy (LLM Ensemble, Expert, RNS-Guided) (ablation) | benchmark ground truth · SerenQA | metric correlation: expert vs RNS-guided around 99% | No clear effect |
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 0.87)
- Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking (NeurIPS 2025 · similarity 0.86)
- Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval (ICLR 2025 · similarity 0.86)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.86)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.86)
- EPERM: An Evidence Path Enhanced Reasoning Model for Knowledge Graph Question and Answering (AAAI 2025 · similarity 0.86)
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.
