List your company
ResearchFormerly WizWand

Sentiment Analysis on SST-5

94.84AccuracyMUPPET
19.928839.376958.82578.2731Dec 3, 2020Oct 31, 2021Sep 28, 2022Aug 26, 2023Jul 23, 2024Jun 20, 2025May 18, 2026
Updated 5mo ago

Evaluation results

MethodLinks
MUPPET2022.1294.84
ColD-Fusion2022.1259.52
ROBERTa-large+Self-ExplainingBackbone=RoBERTa-large2020.1259.1
SentiLAREBackbone=RoBERTa-base, External training resources=true2020.1258.6
ROBERTa-largeBackbone=RoBERTa-large2020.1257.9
ROBERTa-base+Self-ExplainingBackbone=RoBERTa-base2020.1257.8
Multitask2022.1257.56
SentiBERT2020.1256.9
ROBERTa-baseBackbone=RoBERTa-base2020.1256.4
Finetune2022.1256.24
BCN+SuBiLSTM+CoVeBackbone=SuBiLSTM+CoVe2020.1256.2
BERT-largeBackbone=BERT-large2020.1256.2
ROBERTa-base+AvgSelf-ExplainingBackbone=RoBERTa-base2020.1256.2
BM25Model=Qwen2.5-7B, Setting=Few-shot2026.0555.6
PCModel=Llama-2 7b, ICL Setting=1-shot2024.0555.41
BERT-baseBackbone=BERT-base2020.1254.9
CCBackbone Model=Mistral, Shot Count=16-shot2025.0554.3
CCModel=Mistral, k-shot=162025.0554.3
DiSPModel=LLaMA3-8B, Setting=Few-shot2026.0554.3
UpriseModel=Qwen2.5-7B, Setting=Few-shot2026.0554.3
DiSPModel=Qwen2.5-7B, Setting=Few-shot2026.0554.3
DCBackbone Model=Mistral, Shot Count=16-shot2025.0554.14
DCModel=Mistral, k-shot=162025.0554.14
UniBiasModel=Llama-2 7b, ICL Setting=1-shot2024.0553.79
PCModel=Llama-2 13b, ICL Setting=1-shot2024.0553.63
Se2Model=Qwen2.5-7B, Setting=Few-shot2026.0553.6
Se²2024.0252.7
UPRISE2024.0252.6
CCBackbone Model=Llama, Shot Count=16-shot2025.0552.58
CCModel=Llama, k-shot=162025.0552.58
BM25Model=LLaMA3-8B, Setting=Few-shot2026.0552.3
DCModel=Llama-2 7b, ICL Setting=1-shot2024.0551.92
gold shot2026.0251.9
UniBiasModel=Llama-2 13b, ICL Setting=1-shot2024.0551.8
Se2Model=LLaMA3-8B, Setting=Few-shot2026.0551.7
UCPOF2026.0251.54
baseline2026.0251.45
Full RAG2026.0251.4
CCModel=Llama-2 7b, ICL Setting=1-shot2024.0551.36
ICLModel=Llama-2 13b, ICL Setting=1-shot2024.0551.03
DCBackbone Model=Llama, Shot Count=16-shot2025.0550.7
DCModel=Llama, k-shot=162025.0550.7
Full RAGModel=Llama-3-8B-Instruct2026.0250.63
LOZO-MBackbone=RoBERTa-Large, Evaluation Protocol=prompt-conditioned, Time Constraint=equal wall-clock time2025.1150.4
ConMeZOBackbone=RoBERTa-Large, Evaluation Protocol=prompt-conditioned, Time Constraint=equal wall-clock time2025.1150
RandomModel=Qwen2.5-7B, Setting=Few-shot2026.0549.7
LOZOBackbone=RoBERTa-Large, Evaluation Protocol=prompt-conditioned, Time Constraint=equal wall-clock time2025.1149.4
DCModel=Llama-2 13b, ICL Setting=1-shot2024.0548.98
CLGModel=Llama3-70B, Shots=1282025.0648.32
UpriseModel=LLaMA3-8B, Setting=Few-shot2026.0548.3
baselineModel=Llama-3-8B-Instruct2026.0248.1
SCBackbone Model=Mistral, Shot Count=16-shot2025.0547.27
SCModel=Mistral, k-shot=162025.0547.27
CCModel=Llama-2 13b, ICL Setting=1-shot2024.0547.2
UCPOFModel=Llama-3-8B-Instruct2026.0247.19
SeDPOModel=LLaMA3-8B, Setting=Few-shot2026.0547
ICLModel=Llama-2 7b, ICL Setting=1-shot2024.0546.97
RandomModel=LLaMA3-8B, Setting=Few-shot2026.0546.6
Latent-BayesianModel=Llama3-70B, Shots=1282025.0646.59
gold shotModel=Llama-3-8B-Instruct2026.0246.52
BGE-KMeansModel=Llama3-70B, Shots=1282025.0646.41
SeDPOModel=Qwen2.5-7B, Setting=Few-shot2026.0545.7
SCBackbone Model=Llama, Shot Count=16-shot2025.0544.45
SCModel=Llama, k-shot=162025.0544.45
RandomModel=Llama3-70B, Shots=1282025.0643.71
BM25-MajorModel=Llama3-70B, Shots=1282025.0643.69
Best-of-NModel=Llama3-70B, Shots=1282025.0643.69
EPR-KMeansModel=Llama3-70B, Shots=1282025.0643.05
Zero-shotModel=Qwen2.5-7B, Setting=Zero-shot2026.0542.4
Zero-shotModel=LLaMA3-8B, Setting=Zero-shot2026.0541.7
SCBackbone Model=Qwen, Shot Count=16-shot2025.0541.64
SCModel=Qwen, k-shot=162025.0541.64
CLGModel=Qwen2.5-72B, Shots=1282025.0638.33
BM25-MajorModel=Qwen2.5-72B, Shots=1282025.0637.78
BGE-KMeansModel=Qwen2.5-72B, Shots=1282025.0637.24
Best-of-NModel=Qwen2.5-72B, Shots=1282025.0636.6
EPR-KMeansModel=Qwen2.5-72B, Shots=1282025.0636.15
RandomModel=Qwen2.5-72B, Shots=1282025.0636
RAEE (Llama)Backbone=Llama-3-8B2024.0535.25
RB-LBackbone=RoBERTa-Large2024.0534.98
BCBackbone Model=Mistral, Shot Count=16-shot2025.0534.69
BCModel=Mistral, k-shot=162025.0534.69
RAEE (RB-L)Backbone=RoBERTa-Large2024.0533.57
BCBackbone Model=Llama, Shot Count=16-shot2025.0533.36
BCModel=Llama, k-shot=162025.0533.36
RAEE (Gemma)Backbone=Gemma-7B2024.0532.4
Gemma-7BBackbone=Gemma-7B2024.0528.64
Zero-shot2024.0228.2
AdaInfer (T5-L)Backbone=T5-Large2024.0528.14
Best-of-102024.0227.7
BM252024.0227.5
Latent-BayesianModel=Qwen2.5-72B, Shots=1282025.0627.25
RAEE (T5-L)Backbone=T5-Large2024.0526.56
Llama-3-8BBackbone=Llama-3-8B2024.0526.06
AdaInfer (RB-L)Backbone=RoBERTa-Large2024.0524.48
CALM (T5-L)Backbone=T5-Large2024.0523.17
T5-LBackbone=T5-Large2024.0523.12
BCBackbone Model=Qwen, Shot Count=16-shot2025.0522.89
BCModel=Qwen, k-shot=162025.0522.89
Base LLMBackbone Model=Qwen, Shot Count=16-shot2025.0522.81