Sentiment-eng-Socher
Task Identifier: sentiment-2013-socher-eng
Cluster: Sentiment Analysis
Data Type: eng
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Zero-shot BLOOMZ-P3-7B
93
2
Zero-shot BLOOMZ-7B
92.2
3
Zero-shot Chatgpt with translated prompts
91.8
4
Zero-shot Chatgpt
91.8
5
Finetuned LMs XLM-RoBERTa-Large
91.6667
6
five-shot in-context learning Vicuna-7B
91.2
7
three-shot in-context learning Vicuna-7B
89.4
8
Finetuned LMs InfoDCL
88.7333
9
Finetuned LMs XLM-RoBERTa-Base
88.4
10
Finetuned LMs XLM-Twitter
88.2
11
Finetuned LMs TwHIN-BERT
87.4667
12
Finetuned LMs Bernice
86.8667
13
Finetuned LMs mBERT
84.4667
14
Zero-shot Bactrian-LLaMA-7B
82.2
15
five-shot in-context learning LLaMA-7B
81.8
16
Zero-shot mT0-XL
76.8
17
three-shot in-context learning LLaMA-7B
73.4
18
three-shot in-context learning BLOOMZ-P3-7B
71.2
19
five-shot in-context learning BLOOMZ-P3-7B
67.2
20
five-shot in-context learning BLOOM-7B
59.8
21
three-shot in-context learning BLOOM-7B
59.4
22
Zero-shot Alpaca-7B
58.2
23
Zero-shot BLOOM-7B
56.4
24
three-shot in-context learning mT0-XL
56
25
five-shot in-context learning mT0-XL
54.8
26
Zero-shot Bactrian-BLOOM
53.6
27
Zero-shot LLaMA-7B
53.4
28
Baseline Majority
49.9176
29
Zero-shot Vicuna-7B
49.8
30
five-shot in-context learning mT5-XL
49
31
Zero-shot mT5-XL
49
32
three-shot in-context learning mT5-XL
48.8
33
Baseline Random
46.8