AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

Bairu Hou, Joe O'Connor, Jacob Andreas, Shiyu Chang, Yang Zhang

ICML 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot · 11 citations (OpenAlex)

Read the paper

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
Ensemble with AdaBoost of learned-verbalizer weak learners (vs majority vote over same learned verbalizers) (ablation)PromptBoosting · AG's News and TREC (k=16)accuracy (%): AG's News 83.5 -> 85.2; TREC 67.2 -> 81.6Improved
Learned verbalizer (token selection by training-set accuracy) vs random or manual verbalizer, same majority-vote ensemble (ablation)PromptVoting · AG's News, TREC, SST-2, MR (k=16)accuracy (%): AG's News 25.2 (random) / 67.1 (manual) -> 83.5Improved
Increase number of prompts from 1 to 10 (AdaBoost ensemble) (ablation)PromptBoosting · TREC (k=16)accuracy (%): 41.3 -> 81.6Improved
Increase number of prompts from 10 to 20 (ablation)PromptBoosting · Avg. over 8 tasks (k=16)average accuracy (%): 71.4 -> 71.3No clear effect
Smaller top-m candidate set for verbalizer search (ablation)PromptBoosting · AG's News and RTE (k=16)accuracy (%) and wall time: AG's News 85.2 -> 84.4 (8 -> 2 min); RTE 60.0 -> 59.1 (4 -> 0.7 min)Mixed
Use PromptBoosting (black-box, 10 forward passes) vs BBTv2 (8000 forward passes)PromptBoosting · AG's News and RTE (k=16)wall time and accuracy: AG's News 90 min -> 8 min; RTE 70 min -> 4 min; accuracy 83.6->85.2 and 53.2->60.0Improved
Prompt set from LM-BFF, PET, or manual writing instead of the generated prompts (ablation)PromptBoosting · AG's News and RTE (k=16)accuracy (%): AG's News 84.7-85.4; RTE 58.2-60.6 across prompt setsNo clear effect
Prompt refinement by selecting top-10 prompts by validation accuracy (ablation)PromptBoosting · SNLI, MNLI, QNLIfew-shot accuracyImproved
Full training data instead of 16-shotPromptBoosting vs fine-tuning · SST-2, MR, TREC, RTE (full data)accuracy (%): SST-2 94.1 vs 95.5; TREC 90.5 vs 97.2; RTE 71.7 vs 81.9 (fine-tuning higher)Hurt
Train on train+validation (PromptBoosting-32) vs standard k=16 splitPromptBoosting · Avg. 8 tasks (k=16)average accuracy (%): 71.4 -> 71.9Improved

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