{"url":"/sota/semantic-textual-similarity-on-mrpc","task":{"name":"Semantic Textual Similarity","url":"/task/semantic-textual-similarity","note":null},"dataset":{"name":"MRPC","url":"/dataset/mrpc"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":"Semantic textual similarity deals with determining how similar two pieces of texts are.\r\nThis can take the form of assigning a score from 1 to 5. Related tasks are paraphrase or duplicate identification.\r\n\r\nImage source: [Learning Semantic Textual Similarity from Conversations](https://arxiv.org/pdf/1804.07754.pdf)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","F1":"higher"}},"counts":{"rows":45,"rows_with_code":38,"rows_with_paper_page":44,"rows_dated":44,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MT-DNN-SMART","metrics":{"Accuracy":"93.7%","F1":"91.7"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"ALBERT","metrics":{"Accuracy":"93.4%"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/albert-a-lite-bert-for-self-supervised","paper_url":"https://arxiv.org/abs/1909.11942v6","paper_title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","code":"https://github.com/huggingface/transformers","n_code_links":48,"syntology":{"n_ran":68,"n_unverified":58,"n_samples":126,"n_pointer_only_licence":22}},{"rank_in_archive_order":3,"model":"RoBERTa (ensemble)","metrics":{"Accuracy":"92.3%"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","paper_url":"https://arxiv.org/abs/1907.11692v1","paper_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","code":"https://github.com/huggingface/transformers","n_code_links":67,"syntology":{"n_ran":37,"n_unverified":11,"n_samples":48,"n_pointer_only_licence":23}},{"rank_in_archive_order":4,"model":"StructBERTRoBERTa ensemble","metrics":{"Accuracy":"91.5%","F1":"93.6%"},"uses_additional_data":false,"paper_date":"2019-08-13","paper":"/paper/structbert-incorporating-language-structures","paper_url":"https://arxiv.org/abs/1908.04577v3","paper_title":"StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"FLOATER-large","metrics":{"Accuracy":"91.4%"},"uses_additional_data":false,"paper_date":"2020-03-13","paper":"/paper/learning-to-encode-position-for-transformer","paper_url":"https://arxiv.org/abs/2003.09229v1","paper_title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","code":"https://github.com/xuanqing94/FLOATER","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":6,"model":"SMART","metrics":{"Accuracy":"91.3%"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"RoBERTa-large 355M (MLP quantized vector-wise, fine-tuned)","metrics":{"Accuracy":"91.0%"},"uses_additional_data":false,"paper_date":"2022-08-15","paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","paper_url":"https://arxiv.org/abs/2208.07339v2","paper_title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","code":"https://github.com/timdettmers/bitsandbytes","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"SpanBERT","metrics":{"Accuracy":"90.9%"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/spanbert-improving-pre-training-by","paper_url":"https://arxiv.org/abs/1907.10529v3","paper_title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","code":"https://github.com/facebookresearch/SpanBERT","n_code_links":6,"syntology":{"n_ran":6,"n_unverified":9,"n_samples":15,"n_pointer_only_licence":4}},{"rank_in_archive_order":9,"model":"XLNet (single model)","metrics":{"Accuracy":"90.8%"},"uses_additional_data":false,"paper_date":"2019-06-19","paper":"/paper/xlnet-generalized-autoregressive-pretraining","paper_url":"https://arxiv.org/abs/1906.08237v2","paper_title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":27,"syntology":{"n_ran":10,"n_unverified":14,"n_samples":24,"n_pointer_only_licence":3}},{"rank_in_archive_order":10,"model":"AutoBERT-Zero (Large)","metrics":{"Accuracy":"90.7%"},"uses_additional_data":false,"paper_date":"2021-07-15","paper":"/paper/autobert-zero-evolving-bert-backbone-from","paper_url":"https://arxiv.org/abs/2107.07445v2","paper_title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"MLM+ del-word+ reorder","metrics":{"Accuracy":"90.6%"},"uses_additional_data":false,"paper_date":"2020-12-31","paper":"/paper/clear-contrastive-learning-for-sentence","paper_url":"https://arxiv.org/abs/2012.15466v1","paper_title":"CLEAR: Contrastive Learning for Sentence Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"AutoBERT-Zero (Base)","metrics":{"Accuracy":"90.5%"},"uses_additional_data":false,"paper_date":"2021-07-15","paper":"/paper/autobert-zero-evolving-bert-backbone-from","paper_url":"https://arxiv.org/abs/2107.07445v2","paper_title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"PSQ (Chen et al., 2020)","metrics":{"Accuracy":"90.4"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/a-statistical-framework-for-low-bitwidth","paper_url":"https://arxiv.org/abs/2010.14298v1","paper_title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","code":"https://github.com/cjf00000/StatQuant","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":14,"model":"DistilBERT 66M","metrics":{"Accuracy":"90.2%"},"uses_additional_data":false,"paper_date":"2019-10-02","paper":"/paper/distilbert-a-distilled-version-of-bert","paper_url":"https://arxiv.org/abs/1910.01108v4","paper_title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":20,"n_unverified":7,"n_samples":27,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"T5-11B","metrics":{"Accuracy":"90.0%","F1":"91.9"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"T5-Large","metrics":{"Accuracy":"89.9%","F1":"92.4"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"Q8BERT (Zafrir et al., 2019)","metrics":{"Accuracy":"89.7"},"uses_additional_data":false,"paper_date":"2019-10-14","paper":"/paper/q8bert-quantized-8bit-bert","paper_url":"https://arxiv.org/abs/1910.06188v2","paper_title":"Q8BERT: Quantized 8Bit BERT","code":"https://github.com/NervanaSystems/nlp-architect/blob/master/nlp_architect/models/transformers/quantized_bert.py","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":18,"model":"ELECTRA","metrics":{"Accuracy":"89.6%"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"T5-3B","metrics":{"Accuracy":"89.2%","F1":"92.5"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"MobileBERT","metrics":{"Accuracy":"88.8%"},"uses_additional_data":false,"paper_date":"2020-04-06","paper":"/paper/mobilebert-a-compact-task-agnostic-bert-for","paper_url":"https://arxiv.org/abs/2004.02984v2","paper_title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","code":"https://github.com/tensorflow/models/tree/master/official/nlp/projects/mobilebert","n_code_links":7,"syntology":null},{"rank_in_archive_order":21,"model":"ERNIE","metrics":{"Accuracy":"88.2%"},"uses_additional_data":false,"paper_date":"2019-05-17","paper":"/paper/ernie-enhanced-language-representation-with","paper_url":"https://arxiv.org/abs/1905.07129v3","paper_title":"ERNIE: Enhanced Language Representation with Informative Entities","code":"https://github.com/thunlp/ERNIE","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"Q-BERT (Shen et al., 2020)","metrics":{"Accuracy":"88.2"},"uses_additional_data":false,"paper_date":"2019-09-12","paper":"/paper/q-bert-hessian-based-ultra-low-precision","paper_url":"https://arxiv.org/abs/1909.05840v2","paper_title":"Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"FNet-Large","metrics":{"Accuracy":"88%"},"uses_additional_data":false,"paper_date":"2021-05-09","paper":"/paper/fnet-mixing-tokens-with-fourier-transforms","paper_url":"https://arxiv.org/abs/2105.03824v4","paper_title":"FNet: Mixing Tokens with Fourier Transforms","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":12,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":24,"model":"SqueezeBERT","metrics":{"Accuracy":"87.8%"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/squeezebert-what-can-computer-vision-teach","paper_url":"https://arxiv.org/abs/2006.11316v1","paper_title":"SqueezeBERT: What can computer vision teach NLP about efficient neural networks?","code":"https://github.com/huggingface/transformers/blob/main/src/transformers/models/squeezebert/modeling_squeezebert.py","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"Charformer-Tall","metrics":{"Accuracy":"87.5%","F1":"91.4"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/charformer-fast-character-transformers-via","paper_url":"https://arxiv.org/abs/2106.12672v3","paper_title":"Charformer: Fast Character Transformers via Gradient-based Subword Tokenization","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"T5-Base","metrics":{"Accuracy":"87.5%","F1":"90.7"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"24hBERT","metrics":{"Accuracy":"87.5%"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/how-to-train-bert-with-an-academic-budget","paper_url":"https://arxiv.org/abs/2104.07705v2","paper_title":"How to Train BERT with an Academic Budget","code":"https://github.com/peteriz/academic-budget-bert","n_code_links":4,"syntology":null},{"rank_in_archive_order":28,"model":"ERNIE 2.0 Large","metrics":{"Accuracy":"87.4%"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/ernie-20-a-continual-pre-training-framework","paper_url":"https://arxiv.org/abs/1907.12412v2","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":29,"model":"TinyBERT-6 67M","metrics":{"Accuracy":"87.3%"},"uses_additional_data":false,"paper_date":"2019-09-23","paper":"/paper/190910351","paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":30,"model":"RealFormer","metrics":{"Accuracy":"87.01%","F1":"90.91%"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/informer-transformer-likes-informed-attention","paper_url":"https://arxiv.org/abs/2012.11747v3","paper_title":"RealFormer: Transformer Likes Residual Attention","code":"https://github.com/google-research/google-research","n_code_links":5,"syntology":null},{"rank_in_archive_order":31,"model":"RoBERTa + SubRegWeigh (K-means)","metrics":{"Accuracy":"86.82%"},"uses_additional_data":false,"paper_date":"2024-09-10","paper":"/paper/subregweigh-effective-and-efficient","paper_url":"https://arxiv.org/abs/2409.06216v2","paper_title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","code":"https://github.com/4ldk/SubRegWeigh","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"T5-Small","metrics":{"Accuracy":"86.6%","F1":"89.7"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":21,"n_unverified":10,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"TinyBERT-4 14.5M","metrics":{"Accuracy":"86.4%"},"uses_additional_data":false,"paper_date":"2019-09-23","paper":"/paper/190910351","paper_url":"https://arxiv.org/abs/1909.10351v5","paper_title":"TinyBERT: Distilling BERT for Natural Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/tinybert","n_code_links":10,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":34,"model":"ERNIE 2.0 Base","metrics":{"Accuracy":"86.1%"},"uses_additional_data":false,"paper_date":"2019-07-29","paper":"/paper/ernie-20-a-continual-pre-training-framework","paper_url":"https://arxiv.org/abs/1907.12412v2","paper_title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-1.0","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":35,"model":"TF-KLD","metrics":{"Accuracy":"80.4%","F1":"85.9%"},"uses_additional_data":false,"paper_date":"2013-10-01","paper":"/paper/discriminative-improvements-to-distributional","paper_url":"https://aclanthology.org/D13-1090","paper_title":"Discriminative Improvements to Distributional Sentence Similarity","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"GenSen","metrics":{"Accuracy":"78.6%","F1":"84.4%"},"uses_additional_data":false,"paper_date":"2018-03-30","paper":"/paper/learning-general-purpose-distributed-sentence","paper_url":"http://arxiv.org/abs/1804.00079v1","paper_title":"Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning","code":"https://github.com/facebookresearch/InferSent","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":37,"model":"InferSent","metrics":{"Accuracy":"76.2%","F1":"83.1%"},"uses_additional_data":false,"paper_date":"2017-05-05","paper":"/paper/supervised-learning-of-universal-sentence","paper_url":"http://arxiv.org/abs/1705.02364v5","paper_title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","code":"https://github.com/facebookresearch/InferSent","n_code_links":23,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":38,"model":"BigBird","metrics":{"F1":"91.5"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/big-bird-transformers-for-longer-sequences","paper_url":"https://arxiv.org/abs/2007.14062v2","paper_title":"Big Bird: Transformers for Longer Sequences","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":11}},{"rank_in_archive_order":39,"model":"RoBERTa-large 355M + Entailment as Few-shot Learner","metrics":{"F1":"91.0"},"uses_additional_data":false,"paper_date":"2021-04-29","paper":"/paper/entailment-as-few-shot-learner","paper_url":"https://arxiv.org/abs/2104.14690v1","paper_title":"Entailment as Few-Shot Learner","code":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/few_shot/efl","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"BERT-LARGE","metrics":{"F1":"89.3"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":208,"n_unverified":451,"n_samples":659,"n_pointer_only_licence":149}},{"rank_in_archive_order":41,"model":"Nyströmformer","metrics":{"F1":"88.1%"},"uses_additional_data":false,"paper_date":"2021-02-07","paper":"/paper/nystromformer-a-nystrom-based-algorithm-for","paper_url":"https://arxiv.org/abs/2102.03902v3","paper_title":"Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention","code":"https://github.com/facebookresearch/xformers","n_code_links":10,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":42,"model":"BERT-Base","metrics":{},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/intrinsic-dimensionality-explains-the","paper_url":"https://arxiv.org/abs/2012.13255v1","paper_title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","code":"https://github.com/rabeehk/compacter","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":43,"model":"BERT-Large","metrics":{},"uses_additional_data":false,"paper_date":"2020-12-22","paper":"/paper/intrinsic-dimensionality-explains-the","paper_url":"https://arxiv.org/abs/2012.13255v1","paper_title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","code":"https://github.com/rabeehk/compacter","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":44,"model":"SMART-BERT","metrics":{},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":45,"model":"SMARTRoBERTa","metrics":{},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/smart-robust-and-efficient-fine-tuning-for","paper_url":"https://arxiv.org/abs/1911.03437v5","paper_title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","code":"https://github.com/namisan/mt-dnn","n_code_links":6,"syntology":{"n_ran":8,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":1}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":34,"rows_with_any_sample_ran":30,"distinct_papers_with_graph_line":24,"distinct_papers_with_any_sample_ran":22,"samples_over_distinct_papers":{"n_ran":426,"n_unverified":590,"n_samples":1016,"n_pointer_only_licence":242,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":535,"n_unverified":635,"n_samples":1170,"n_pointer_only_licence":251,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}