Subjective-kor-Jang
Task Identifier: subjective-2013-jang-kor
Cluster: Subjectivity Analysis
Data Type: kor
Score Metric: Macro-F1
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs XLM-RoBERTa-Large
38.447
2
Finetuned LMs Bernice
37.7843
3
Finetuned LMs XLM-RoBERTa-Base
36.9916
4
Finetuned LMs InfoDCL
36.9519
5
Finetuned LMs mBERT
36.5324
6
Finetuned LMs XLM-Twitter
36.1484
7
Finetuned LMs TwHIN-BERT
33.1785
8
Zero-shot Chatgpt
27.4114
9
Zero-shot Chatgpt with translated prompts
15.8319
10
Zero-shot Bactrian-LLaMA-7B
13.4493
11
Zero-shot mT0-XL
12.7964
12
Zero-shot Vicuna-7B
12.7555
13
five-shot in-context learning BLOOM-7B
12.071
14
three-shot in-context learning BLOOM-7B
11.9119
15
five-shot in-context learning Vicuna-7B
11.3001
16
three-shot in-context learning Vicuna-7B
10.8871
17
Zero-shot BLOOMZ-P3-7B
10.7999
18
five-shot in-context learning BLOOMZ-P3-7B
10.7564
19
Baseline Random
10.7421
20
three-shot in-context learning BLOOMZ-P3-7B
10.4133
21
Zero-shot mT5-XL
9.84768
22
Baseline Majority
9.75781
23
five-shot in-context learning mT0-XL
8.61064
24
three-shot in-context learning mT0-XL
8.18351
25
Zero-shot Alpaca-7B
7.16955
26
Zero-shot LLaMA-7B
6.54775
27
three-shot in-context learning mT5-XL
6.37047
28
five-shot in-context learning mT5-XL
5.216
29
five-shot in-context learning LLaMA-7B
5.12634
30
three-shot in-context learning LLaMA-7B
4.37011
31
Zero-shot Bactrian-BLOOM
3.938
32
Zero-shot BLOOMZ-7B
3.15103
33
Zero-shot BLOOM-7B
2.32867