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.

Models/RoBERTa-large

RoBERTa-large

Reported on 18 benchmarks across 8 tasks · 4 papers · 6 SOTA

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

Natural Language Processing19 results

  • Text ClassificationonCHIP-CTC
    Macro F1· uses extra data· 2021-06-15
    70.9
    SOTA
    CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkarXiv:2106.08087
  • Question AnsweringonTorque
    C· 2020-05-01
    34.5
    best: 37 (ECONET)
    SOTA
    TORQUE: A Reading Comprehension Dataset of Temporal Ordering QuestionsarXiv:2005.00242
  • Question AnsweringonTorque
    EM· 2020-05-01
    51.1
    best: 52 (ECONET)
    SOTA
    TORQUE: A Reading Comprehension Dataset of Temporal Ordering QuestionsarXiv:2005.00242
  • Question AnsweringonTorque
    F1· 2020-05-01
    75.2
    best: 76.3 (ECONET)
    SOTA
    TORQUE: A Reading Comprehension Dataset of Temporal Ordering QuestionsarXiv:2005.00242
  • Sentiment AnalysisonIMDb
    Accuracy· 2024-03-23
    96.54
    best: 96.68 (RoBERTa-large with LlamBERT)
    LlamBERT: Large-scale low-cost data annotation in NLParXiv:2403.15938
  • Reading ComprehensiononReClor
    Test· 2020-02-11
    55.6
    best: 80.6 (Rational Reasoner / IDOL)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Reading ComprehensiononReClor
    Accuracy· 2020-02-11
    55.6
    best: 56 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Reading ComprehensiononReClor
    Accuracy (easy)· 2020-02-11
    75.5
    best: 75.7 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Reading ComprehensiononReClor
    Accuracy (hard)· 2020-02-11
    40
    best: 40.5 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy· 2020-02-11
    55.6
    best: 56 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy (easy)· 2020-02-11
    75.5
    best: 75.7 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy (hard)· 2020-02-11
    40
    best: 40.5 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy· 2020-02-11
    55.6
    best: 56 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy (easy)· 2020-02-11
    75.5
    best: 75.7 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Question AnsweringonReClor
    Accuracy (hard)· 2020-02-11
    40
    best: 40.5 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Visual Question Answering (VQA)onReClor
    Accuracy· 2020-02-11
    55.6
    best: 56 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Visual Question Answering (VQA)onReClor
    Accuracy (easy)· 2020-02-11
    75.5
    best: 75.7 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Visual Question Answering (VQA)onReClor
    Accuracy (hard)· 2020-02-11
    40
    best: 40.5 (XLNet-large)
    ReClor: A Reading Comprehension Dataset Requiring Logical ReasoningarXiv:2002.04326
  • Sentence CompletiononHONEST
    HONEST
    2.62
    best: 3.33 (BERT-large)

Other1 result

  • Sentence ClassificationonCHIP-CTC
    Macro F1· uses extra data· 2021-06-15
    70.9
    SOTA
    CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkarXiv:2106.08087

Methodology1 result

  • ClassificationonCHIP-CTC
    Macro F1· uses extra data· 2021-06-15
    70.9
    SOTA
    CBLUE: A Chinese Biomedical Language Understanding Evaluation BenchmarkarXiv:2106.08087