Subjevtive-eng-Pang
Task Identifier: subjevtive-2004-pang-eng
Cluster: Subjectivity Analysis
Data Type: eng
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs XLM-RoBERTa-Large
96.5333
2
Finetuned LMs InfoDCL
95.2
3
Finetuned LMs XLM-RoBERTa-Base
95.1333
4
Finetuned LMs XLM-Twitter
95
5
Finetuned LMs mBERT
95
6
Finetuned LMs Bernice
94.5333
7
Finetuned LMs TwHIN-BERT
93.9333
8
Zero-shot Chatgpt with translated prompts
73.4
9
Zero-shot Chatgpt
73.4
10
five-shot in-context learning Vicuna-7B
67.6
11
three-shot in-context learning Vicuna-7B
64.6
12
Zero-shot BLOOM-7B
56.8
13
three-shot in-context learning mT5-XL
56
14
five-shot in-context learning LLaMA-7B
54
15
Zero-shot LLaMA-7B
52.8
16
five-shot in-context learning mT5-XL
51.4
17
Zero-shot Bactrian-BLOOM
51
18
Zero-shot Bactrian-LLaMA-7B
51
19
Zero-shot Vicuna-7B
50.6
20
Baseline Majority
50
21
Zero-shot mT5-XL
49.6
22
Zero-shot Alpaca-7B
49.6
23
three-shot in-context learning BLOOMZ-P3-7B
49
24
Zero-shot BLOOMZ-7B
49
25
five-shot in-context learning BLOOMZ-P3-7B
49
26
Zero-shot BLOOMZ-P3-7B
49
27
five-shot in-context learning BLOOM-7B
48.8
28
Zero-shot mT0-XL
48.8
29
Baseline Random
48.6
30
three-shot in-context learning mT0-XL
48.6
31
five-shot in-context learning mT0-XL
48.6
32
three-shot in-context learning LLaMA-7B
47.8
33
three-shot in-context learning BLOOM-7B
46.4