Humor-hin-Aggarwal
Task Identifier: humor-2020-aggarwal-hin
Cluster: Humor Detection
Data Type: hin
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs InfoDCL
80.4
2
Finetuned LMs XLM-Twitter
79.8
3
Finetuned LMs TwHIN-BERT
79.6
4
Finetuned LMs XLM-RoBERTa-Large
79.5333
5
Finetuned LMs XLM-RoBERTa-Base
78.8667
6
Finetuned LMs mBERT
78.2667
7
Finetuned LMs Bernice
78.2667
8
Zero-shot Chatgpt with translated prompts
60.8
9
Zero-shot Alpaca-7B
60.4
10
Baseline Majority
59.6558
11
Zero-shot BLOOM-7B
58.6
12
Zero-shot LLaMA-7B
56.8
13
Zero-shot Chatgpt
56
14
Zero-shot mT5-XL
52.2
15
five-shot in-context learning LLaMA-7B
52
16
Baseline Random
51.4
17
Zero-shot Bactrian-LLaMA-7B
51.4
18
three-shot in-context learning Vicuna-7B
49.4
19
three-shot in-context learning LLaMA-7B
49
20
five-shot in-context learning Vicuna-7B
48.8
21
three-shot in-context learning mT5-XL
41.8
22
five-shot in-context learning mT0-XL
41.6
23
Zero-shot Bactrian-BLOOM
40.8
24
five-shot in-context learning mT5-XL
40.8
25
five-shot in-context learning BLOOM-7B
40.2
26
three-shot in-context learning mT0-XL
40
27
Zero-shot mT0-XL
39.6
28
Zero-shot BLOOMZ-P3-7B
39.6
29
three-shot in-context learning BLOOMZ-P3-7B
39.6
30
five-shot in-context learning BLOOMZ-P3-7B
39.6
31
Zero-shot BLOOMZ-7B
39.6
32
three-shot in-context learning BLOOM-7B
39
33
Zero-shot Vicuna-7B
37.2