Sentiment-mad-Winata
Task Identifier: sentiment-2022-winata-mad
Cluster: Sentiment Analysis
Data Type: mad
Score Metric: Macro-F1
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs InfoDCL
78.3642
2
Finetuned LMs Bernice
77.3558
3
Finetuned LMs XLM-RoBERTa-Large
76.4894
4
Finetuned LMs XLM-Twitter
74.0291
5
Finetuned LMs XLM-RoBERTa-Base
73.358
6
Finetuned LMs mBERT
70.5641
7
Finetuned LMs TwHIN-BERT
69.887
8
Zero-shot Chatgpt with translated prompts
61.135
9
Zero-shot Chatgpt
61.0674
10
Zero-shot BLOOMZ-P3-7B
45.4443
11
five-shot in-context learning LLaMA-7B
38.8154
12
three-shot in-context learning LLaMA-7B
35.3999
13
five-shot in-context learning BLOOMZ-P3-7B
34.3137
14
three-shot in-context learning BLOOMZ-P3-7B
33.9713
15
three-shot in-context learning BLOOM-7B
32.5317
16
Zero-shot BLOOMZ-7B
31.2314
17
five-shot in-context learning BLOOM-7B
30.5111
18
Baseline Random
28.6441
19
three-shot in-context learning mT0-XL
28.4438
20
Zero-shot Bactrian-BLOOM
23.1238
21
Zero-shot BLOOM-7B
22.4242
22
Zero-shot mT0-XL
21.8516
23
five-shot in-context learning Vicuna-7B
21.6333
24
five-shot in-context learning mT0-XL
20.7963
25
three-shot in-context learning mT5-XL
20.0042
26
five-shot in-context learning mT5-XL
19.6233
27
Zero-shot Alpaca-7B
18.9169
28
Baseline Majority
18.4448
29
Zero-shot mT5-XL
18.4448
30
Zero-shot LLaMA-7B
18.3575
31
three-shot in-context learning Vicuna-7B
17.803
32
Zero-shot Bactrian-LLaMA-7B
13.603
33
Zero-shot Vicuna-7B
13.1386