TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Natural Language Processing/Sarcasm Detection/BIG-bench (SNARKS)

Sarcasm Detection on BIG-bench (SNARKS)

Metric: Accuracy (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Accuracy▼Extra DataPaperDate↕Code
1PaLM 2(few-shot, k=3, CoT)84.8NoPaLM 2 Technical Report2023-05-17Code
2PaLM 2 (few-shot, k=3, Direct)78.7NoPaLM 2 Technical Report2023-05-17Code
3PaLM 540B (few-shot, k=3)78.1NoBloombergGPT: A Large Language Model for Finance2023-03-30Code
4BLOOM 176B (few-shot, k=3)72.47NoBloombergGPT: A Large Language Model for Finance2023-03-30Code
5Bloomberg GPT (few-shot, k=3)69.66NoBloombergGPT: A Large Language Model for Finance2023-03-30Code
6GPT-NeoX (few-shot, k=3)62.36NoBloombergGPT: A Large Language Model for Finance2023-03-30Code
7Chinchilla-70B (few-shot, k=5)58.6NoTraining Compute-Optimal Large Language Models2022-03-29Code
8Gopher-280B (few-shot, k=5)48.3NoScaling Language Models: Methods, Analysis & Ins...2021-12-08Code