OpenCodePapers

few-shot-text-classification-on-raft

ClassificationText ClassificationFew-Shot Text Classification

Results over time

Click legend items to toggle metrics. Hover points for model names.

Leaderboard

Paper	Code	Avg	ADE	B77	NIS	OSE	Over	SOT	SRI	TAI	ToS	TEH	TC	ModelName	ReleaseDate
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning	✓ Link	0.758	0.804	0.695	0.833	0.676	0.95	0.915	0.508	0.736	0.75	0.586	0.879	T-Few	2022-05-11
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.735	0.830	0.607	0.857	0.646	0.917	0.908	0.468	0.609	0.627	0.722	0.897	Human (crowdsourced)	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.627	0.686	0.299	0.679	0.431	0.937	0.769	0.516	0.656	0.574	0.526	0.821	GPT-3	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.514	0.543	0.023	0.626	0.475	0.838	0.455	0.506	0.556	0.560	0.443	0.625	AdaBoost	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.481	0.452	0.149	0.408	0.343	0.681	0.406	0.493	0.605	0.565	0.554	0.636	GPT-Neo	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.458	0.600	0.121	0.561	0.245	0.498	0.380	0.492	0.612	0.498	0.311	0.723	GPT-2	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.382	0.234	0.332	0.615	0.360	0.462	0.644	0.026	0.469	0.122	0.543	0.400	BART MNLI zero-shot	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.331	0.446	0.000	0.353	0.164	0.337	0.271	0.493	0.344	0.471	0.366	0.391	Plurality-class	2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark	✓ Link	0.292	0.163	0.000	0.572	0.323	0.378	0.628	0.027	0.362	0.164	0.303	0.290	GPT-3 zero-shot	2021-09-28