Sentiment-pcm-Muhammad
Task Identifier: sentiment-2022-muhammad-pcm
Cluster: Sentiment Analysis
Data Type: pcm
Score Metric: Weight-F1
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Zero-shot Chatgpt
70.0789
2
Finetuned LMs XLM-RoBERTa-Large
65.018
3
Finetuned LMs InfoDCL
64.4494
4
Finetuned LMs TwHIN-BERT
63.974
5
Finetuned LMs Bernice
63.6062
6
Finetuned LMs XLM-Twitter
63.2135
7
Finetuned LMs XLM-RoBERTa-Base
62.4425
8
Finetuned LMs mBERT
60.8215
9
three-shot in-context learning LLaMA-7B
55.4795
10
Zero-shot BLOOMZ-P3-7B
55.3278
11
Zero-shot BLOOMZ-7B
53.4662
12
Zero-shot Chatgpt with translated prompts
50.9509
13
five-shot in-context learning LLaMA-7B
49.8102
14
five-shot in-context learning BLOOM-7B
46.9373
15
three-shot in-context learning BLOOM-7B
46.431
16
five-shot in-context learning BLOOMZ-P3-7B
46.2225
17
three-shot in-context learning BLOOMZ-P3-7B
45.1227
18
Zero-shot Alpaca-7B
42.3593
19
Baseline Majority
40.1983
20
Zero-shot LLaMA-7B
40.1834
21
Zero-shot mT5-XL
39.7347
22
three-shot in-context learning mT5-XL
37.915
23
five-shot in-context learning mT5-XL
37.7194
24
Baseline Random
35.6168
25
three-shot in-context learning mT0-XL
31.2685
26
five-shot in-context learning Vicuna-7B
30.6014
27
Zero-shot BLOOM-7B
28.0735
28
five-shot in-context learning mT0-XL
24.9332
29
Zero-shot mT0-XL
23.2137
30
Zero-shot Bactrian-LLaMA-7B
21.2695
31
three-shot in-context learning Vicuna-7B
19.6777
32
Zero-shot Vicuna-7B
11.9051
33
Zero-shot Bactrian-BLOOM
8.9859