Sentiment-rus-Mozetic
Task Identifier: sentiment-2016-mozetic-rus
Cluster: Sentiment Analysis
Data Type: rus
Score Metric: Macro-F1
Paper/GitHub/Website URL: N/A


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs InfoDCL
80.3694
2
Finetuned LMs XLM-RoBERTa-Large
79.8727
3
Finetuned LMs Bernice
78.8352
4
Finetuned LMs XLM-RoBERTa-Base
78.3478
5
Finetuned LMs TwHIN-BERT
77.7503
6
Finetuned LMs XLM-Twitter
77.655
7
Finetuned LMs mBERT
75.2438
8
Zero-shot Chatgpt
61.6673
9
Zero-shot Chatgpt with translated prompts
59.2695
10
five-shot in-context learning Vicuna-7B
41.2242
11
three-shot in-context learning Vicuna-7B
33.0226
12
Baseline Random
32.3322
13
three-shot in-context learning BLOOM-7B
32.176
14
Zero-shot BLOOMZ-P3-7B
31.3326
15
Zero-shot Bactrian-BLOOM
30.6977
16
Zero-shot BLOOMZ-7B
30.4191
17
Zero-shot Bactrian-LLaMA-7B
29.4374
18
five-shot in-context learning BLOOMZ-P3-7B
29.0107
19
five-shot in-context learning LLaMA-7B
28.4605
20
three-shot in-context learning LLaMA-7B
27.9644
21
Zero-shot BLOOM-7B
26.7687
22
three-shot in-context learning BLOOMZ-P3-7B
26.0703
23
five-shot in-context learning BLOOM-7B
25.8786
24
Zero-shot Vicuna-7B
22.3505
25
three-shot in-context learning mT0-XL
22.1337
26
Zero-shot Alpaca-7B
21.7255
27
three-shot in-context learning mT5-XL
21.2122
28
Zero-shot mT0-XL
20.5971
29
five-shot in-context learning mT5-XL
20.0291
30
Baseline Majority
19.4554
31
Zero-shot LLaMA-7B
18.1944
32
five-shot in-context learning mT0-XL
17.9996
33
Zero-shot mT5-XL
14.9871