Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/AlexaTM 20B

AlexaTM 20B

Reported on 7 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing7 results

Question AnsweringonCOPA
Accuracy· 2022-08-02
78
best: 100 (PaLM 540B (finetuned) )
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Question AnsweringonMultiRC
F1· 2022-08-02
59.6
best: 90.1 (PaLM 540B (finetuned) )
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Question AnsweringonBoolQ
Accuracy· 2022-08-02
69.4
best: 99.87 (Mistral-Nemo 12B (HPT))
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Common Sense ReasoningonReCoRD
F1· 2022-08-02
88.4
best: 96.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Word Sense DisambiguationonWords in Context
Accuracy· 2022-08-02
53.3
best: 85.3 (COSINE + Transductive Learning)
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Natural Language InferenceonCommitmentBank
Accuracy· 2022-08-02
67.9
best: 100 (PaLM 540B (finetuned))
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448
Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2022-08-02
68.3
best: 100 (PaLM 540B (fine-tuned))
AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model arXiv:2208.01448