AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning

Xiang Chen, Lei Li, Ningyu Zhang, Xiaozhuan Liang, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen

NeurIPS 2022 · Large language models › Retrieval and knowledge · approach: Retrieval-augmented reasoning · 25 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 retrieval-augmented prompt learning with neural demonstrations, kNN-guided training, and kNN predictionRoBERTa-large prompt learning · 16-shot classification and information extraction benchmarkstask score (accuracy or F1)Improved
Add kNN-based prediction at test time (ablation)Ours · SST-2, CR, MNLI, QQP, TACRED (16-shot)accuracy or F1: 93.2 vs 93.9; 91.2 vs 91.9; 70.4 vs 71.1; 73.0 vs 74.0; 38.2 vs 40.7Improved
Add kNN-guided training (ablation)Ours · SST-2, CR, MNLI, QQP, TACRED (16-shot)accuracy or F1: 92.0 vs 93.9; 90.2 vs 91.9; 68.8 vs 71.1; 71.3 vs 74.0; 36.5 vs 40.7Improved
Add neural demonstrations (ablation)Ours · SST-2, CR, MNLI, QQP, TACRED (16-shot)accuracy or F1: 92.4 vs 93.9; 91.0 vs 91.9; 70.1 vs 71.1; 72.7 vs 74.0; 37.9 vs 40.7Improved
Refresh the knowledge-store asynchronously (ablation)Ours · SST-2, CR, MNLI, QQP, TACRED (16-shot)accuracy or F1: 93.5 vs 93.9; 91.5 vs 91.9; 70.7 vs 71.1; 73.6 vs 74.0; 39.9 vs 40.7Improved
Use prompt-based keys rather than [CLS] keys (ablation)Ours · CR and TACRED (16-shot)accuracy or F1: 89.0 -> 91.9; 37.2 -> 40.7Improved
Use representation similarity rather than BM25 for kNN acquisition (ablation)Ours · CR and TACRED (16-shot)accuracy or F1: 89.5 -> 91.9; 38.8 -> 40.7Improved
Increase the kNN-training weight β excessively (ablation)Ours · CR (16-shot)performanceHurt
Increase kNN neighborhood size (ablation)Ours · MR (zero-shot)performanceImproved
Increase kNN neighborhood size (ablation)Ours · MR (16-shot)performanceNo clear effect
Interpolate kNN predictions with the prompt model at inference (ablation)Ours · MR (16-shot)performanceMixed

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