Sentiment-ara-Muhammad
Task Identifier: sentiment-2022-muhammad-ara
Cluster: Sentiment Analysis
Data Type: ara
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs InfoDCL
62.2
2
Finetuned LMs Bernice
61.2
3
Finetuned LMs XLM-RoBERTa-Large
59.8667
4
Finetuned LMs XLM-Twitter
59.6667
5
Zero-shot Chatgpt
58.4
6
Zero-shot Chatgpt with translated prompts
58
7
Finetuned LMs TwHIN-BERT
56.8667
8
Finetuned LMs XLM-RoBERTa-Base
56.4
9
Zero-shot BLOOMZ-P3-7B
52.8
10
Zero-shot BLOOMZ-7B
51.6
11
five-shot in-context learning BLOOMZ-P3-7B
50.4
12
Finetuned LMs mBERT
48.7333
13
three-shot in-context learning BLOOMZ-P3-7B
48
14
five-shot in-context learning LLaMA-7B
47.6
15
three-shot in-context learning LLaMA-7B
43.6
16
five-shot in-context learning mT0-XL
42
17
three-shot in-context learning mT0-XL
41.8
18
Zero-shot mT0-XL
41.6
19
Baseline Majority
38.5667
20
three-shot in-context learning BLOOM-7B
38.4
21
Zero-shot Alpaca-7B
37.8
22
five-shot in-context learning BLOOM-7B
37.2
23
Zero-shot Bactrian-BLOOM
37
24
Zero-shot LLaMA-7B
36.6
25
three-shot in-context learning mT5-XL
36.2
26
Zero-shot Bactrian-LLaMA-7B
35.8
27
five-shot in-context learning Vicuna-7B
35.6
28
Zero-shot BLOOM-7B
34.8
29
Zero-shot mT5-XL
34.4
30
Baseline Random
33.2
31
five-shot in-context learning mT5-XL
33.2
32
three-shot in-context learning Vicuna-7B
29
33
Zero-shot Vicuna-7B
25