AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

GraphPrompt: Graph-Based Prompt Templates for Biomedical Synonym Prediction

Hanwen Xu, Jiayou Zhang, Zhirui Wang, Shizhuo Zhang, Megh Bhalerao, Yucong Liu, Dawei Zhu, Sheng Wang

AAAI 2023 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 6 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
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · mp zero-shotAcc@1: 76.47 -> 81.14Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · mp few-shotAcc@1: 85.78 -> 88.86Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · cl zero-shotAcc@1: 65.14 -> 67.81Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · cl few-shotAcc@1: 76.64 -> 82.86Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · hp zero-shotAcc@1: 61.53 -> 69.14Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · hp few-shotAcc@1: 72.04 -> 77.87Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · fbbt zero-shotAcc@1: 65.38 -> 69.01Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · fbbt few-shotAcc@1: 69.76 -> 75.55Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · doid zero-shotAcc@1: 50.71 -> 59.06Improved
Use graph-based prompt templates with first- and second-order neighbors instead of text-only BioBERT representationsGraphPrompt · doid few-shotAcc@1: 59.40 -> 67.53Improved
Add second-order graph templates (ablation)GraphPrompt without T² · cl zero-shotAcc@1: 68.00 -> 67.81Hurt
Add second-order graph templates (ablation)GraphPrompt without T² · cl few-shotAcc@1: 82.04 -> 82.86Improved

Later papers that compared with this method

8 later accepted papers report GraphPrompt as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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

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