AI Paper Atlas

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

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
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 -> 0.042Improved
remove subgraph summaries before serendipity exploration (ablation)Qwen-2.5-7B · SerenQA T3 (RNS Guided)SerenHit: 0.041 -> 0.027Hurt
increase model scale (frontier vs small)Cypher knowledge retrieval · SerenQA T1 One-HopF1 (%): Qwen3-8B 37.24 vs DeepSeek-V3 78.71Improved
increase query hops (one-hop to 3+ hops)DeepSeek-V3 / GPT-4o retrieval · SerenQA T1F1 (%): DeepSeek-V3 78.71 -> 6.22Hurt
increase model scalesubgraph reasoning · SerenQA T2Faithfulness/ComprehensivenessNo clear effect
larger model summaries vs Mixtral summariessubgraph reasoning · SerenQA T2SerenCov: Mixtral 0.642 vs Llama-3.3-70B 0.070Mixed
switch partition strategy (LLM Ensemble, Expert, RNS-Guided) (ablation)benchmark ground truth · SerenQAmetric correlation: expert vs RNS-guided around 99%No clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy