{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/language-modelling-on-wikitext-2","task":{"name":"Language Modelling","url":"/task/language-modelling","note":null},"dataset":{"name":"WikiText-2","url":"/dataset/wikitext-2"},"category":"Natural Language Processing","categories":["Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.\r\n\r\nLarge language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model. \r\n\r\nSource: [Wikipedia](https://en.wikipedia.org/wiki/Language_model)","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":["Test perplexity","Validation perplexity","Number of params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Test perplexity":"lower","Validation perplexity":"lower","Number of params":"lower"}},"counts":{"rows":38,"rows_with_code":37,"rows_with_paper_page":38,"rows_dated":38,"rows_using_additional_data":11},"rows":[{"rank_in_archive_order":1,"model":"SparseGPT (175B, 50% Sparsity)","metrics":{"Test perplexity":"8.21"},"uses_additional_data":true,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":2,"model":"OPT-175B","metrics":{"Test perplexity":"8.34"},"uses_additional_data":true,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":3,"model":"SparseGPT (175B, 4:8 Sparsity)","metrics":{"Test perplexity":"8.45"},"uses_additional_data":true,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":4,"model":"SparseGPT (175B, 2:4 Sparsity)","metrics":{"Test perplexity":"8.73"},"uses_additional_data":true,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":5,"model":"GPT-2 (fine-tuned)","metrics":{"Number of params":"1542M","Test perplexity":"15.17","Validation perplexity":"15.69"},"uses_additional_data":true,"paper_date":"2021-10-16","paper":"/paper/hydra-a-system-for-large-multi-model-deep","paper_url":"https://arxiv.org/abs/2110.08633v7","paper_title":"Hydra: A System for Large Multi-Model Deep Learning","code":"https://github.com/knagrecha/hydra","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"GPT-2","metrics":{"Number of params":"1542M","Test perplexity":"18.34"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"GPT-2 (large)","metrics":{"Number of params":"762M","Test perplexity":"19.93"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"GPT-2 (medium)","metrics":{"Number of params":"345M","Test perplexity":"22.76"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"GPT-2 (small)","metrics":{"Number of params":"117M","Test perplexity":"29.41"},"uses_additional_data":true,"paper_date":"2019-02-14","paper":"/paper/language-models-are-unsupervised-multitask","paper_url":"https://d4mucfpksywv.cloudfront.net/better-language-models/language-models.pdf","paper_title":"Language Models are Unsupervised Multitask Learners","code":"https://github.com/huggingface/transformers","n_code_links":21,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"BERT-Large-CAS","metrics":{"Number of params":"395M","Test perplexity":"34.1","Validation perplexity":"37.7"},"uses_additional_data":true,"paper_date":"2019-04-20","paper":"/paper/190409408","paper_url":"https://arxiv.org/abs/1904.09408v2","paper_title":"Language Models with Transformers","code":"https://github.com/cgraywang/gluon-nlp-1","n_code_links":1,"official":{"repos":["cgraywang/gluon-nlp-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/190409408#ran","syntology_url":"https://syntology.ai/paper/1904.09408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09408"}}}},{"rank_in_archive_order":11,"model":"Mogrifier LSTM + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"38.6","Validation perplexity":"40.2"},"uses_additional_data":false,"paper_date":"2019-09-04","paper":"/paper/mogrifier-lstm","paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","code":"https://github.com/deepmind/lamb","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"adversarial + AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"38.65","Validation perplexity":"40.27"},"uses_additional_data":false,"paper_date":"2019-06-10","paper":"/paper/improving-neural-language-modeling-via","paper_url":"https://arxiv.org/abs/1906.03805v2","paper_title":"Improving Neural Language Modeling via Adversarial Training","code":"https://github.com/ChengyueGongR/advsoft","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"FRAGE + AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"39.14","Validation perplexity":"40.85"},"uses_additional_data":false,"paper_date":"2018-09-18","paper":"/paper/frage-frequency-agnostic-word-representation","paper_url":"https://arxiv.org/abs/1809.06858v2","paper_title":"FRAGE: Frequency-Agnostic Word Representation","code":"https://github.com/ChengyueGongR/FrequencyAgnostic","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"Past Decode Reg. + AWD-LSTM-MoS + dyn. eval.","metrics":{"Number of params":"35M","Test perplexity":"40.3","Validation perplexity":"42.0"},"uses_additional_data":false,"paper_date":"2018-08-14","paper":"/paper/improved-language-modeling-by-decoding-the","paper_url":"http://arxiv.org/abs/1808.05908v4","paper_title":"Improved Language Modeling by Decoding the Past","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"GL-LWGC + AWD-MoS-LSTM + dynamic eval","metrics":{"Number of params":"38M","Test perplexity":"40.46","Validation perplexity":"42.19"},"uses_additional_data":false,"paper_date":"2017-08-29","paper":"/paper/gradual-learning-of-recurrent-neural-networks","paper_url":"http://arxiv.org/abs/1708.08863v2","paper_title":"Gradual Learning of Recurrent Neural Networks","code":"https://github.com/zivaharoni/gradual-learning-rnn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"AWD-LSTM-MoS + dynamic eval","metrics":{"Number of params":"35M","Test perplexity":"40.68","Validation perplexity":"42.41"},"uses_additional_data":false,"paper_date":"2017-11-10","paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","paper_url":"http://arxiv.org/abs/1711.03953v4","paper_title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","code":"https://github.com/zihangdai/mos","n_code_links":9,"official":{"repos":["zihangdai/mos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":11,"n_samples":23,"n_pointer_only_licence":1,"sample_list":"/paper/breaking-the-softmax-bottleneck-a-high-rank#ran","syntology_url":"https://syntology.ai/paper/1711.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03953"}}}},{"rank_in_archive_order":17,"model":"AWD-LSTM-DRILL + dynamic eval","metrics":{"Number of params":"34M","Test perplexity":"42.0","Validation perplexity":"43.9"},"uses_additional_data":false,"paper_date":"2019-05-14","paper":"/paper/deep-residual-output-layers-for-neural","paper_url":"https://arxiv.org/abs/1905.05513v2","paper_title":"Deep Residual Output Layers for Neural Language Generation","code":"https://github.com/idiap/drill","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"AWD-LSTM + dynamic eval","metrics":{"Number of params":"33M","Test perplexity":"44.3","Validation perplexity":"46.4"},"uses_additional_data":false,"paper_date":"2017-09-21","paper":"/paper/dynamic-evaluation-of-neural-sequence-models","paper_url":"http://arxiv.org/abs/1709.07432v2","paper_title":"Dynamic Evaluation of Neural Sequence Models","code":"https://github.com/benkrause/dynamic-evaluation","n_code_links":3,"official":{"repos":["benkrause/dynamic-evaluation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-evaluation-of-neural-sequence-models#ran","syntology_url":"https://syntology.ai/paper/1709.07432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07432"}}}},{"rank_in_archive_order":19,"model":"AWD-LSTM + continuous cache pointer","metrics":{"Number of params":"33M","Test perplexity":"52.0","Validation perplexity":"53.8"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/regularizing-and-optimizing-lstm-language","paper_url":"http://arxiv.org/abs/1708.02182v1","paper_title":"Regularizing and Optimizing LSTM Language Models","code":"https://github.com/google-research/google-research/tree/master/enas_lm","n_code_links":45,"official":{"repos":["salesforce/awd-lstm-lm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/regularizing-and-optimizing-lstm-language#ran","syntology_url":"https://syntology.ai/paper/1708.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02182"}}}},{"rank_in_archive_order":20,"model":"AWD-LSTM-DOC x5","metrics":{"Number of params":"185M","Test perplexity":"53.09","Validation perplexity":"54.19"},"uses_additional_data":false,"paper_date":"2018-08-30","paper":"/paper/direct-output-connection-for-a-high-rank","paper_url":"http://arxiv.org/abs/1808.10143v2","paper_title":"Direct Output Connection for a High-Rank Language Model","code":"https://github.com/nttcslab-nlp/doc_lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"Ensemble of All","metrics":{"Test perplexity":"53.73","Validation perplexity":"55.4"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/advancing-state-of-the-art-in-language","paper_url":"https://arxiv.org/abs/2312.03735v1","paper_title":"Advancing State of the Art in Language Modeling","code":"https://github.com/davidherel/sota_lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"Mogrifier LSTM","metrics":{"Number of params":"35M","Test perplexity":"55.1","Validation perplexity":"57.3"},"uses_additional_data":false,"paper_date":"2019-09-04","paper":"/paper/mogrifier-lstm","paper_url":"https://arxiv.org/abs/1909.01792v2","paper_title":"Mogrifier LSTM","code":"https://github.com/deepmind/lamb","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"AWD-LSTM-DOC + Partial Shuffle","metrics":{"Number of params":"37M","Test perplexity":"57.85","Validation perplexity":"60.16"},"uses_additional_data":false,"paper_date":"2019-03-11","paper":"/paper/partially-shuffling-the-training-data-to-1","paper_url":"http://arxiv.org/abs/1903.04167v2","paper_title":"Partially Shuffling the Training Data to Improve Language Models","code":"https://github.com/ofirpress/PartialShuffle","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"AWD-LSTM-DOC","metrics":{"Number of params":"37M","Test perplexity":"58.03","Validation perplexity":"60.29"},"uses_additional_data":false,"paper_date":"2018-08-30","paper":"/paper/direct-output-connection-for-a-high-rank","paper_url":"http://arxiv.org/abs/1808.10143v2","paper_title":"Direct Output Connection for a High-Rank Language Model","code":"https://github.com/nttcslab-nlp/doc_lm","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"AWD-LSTM-MoS + Partial Shuffle","metrics":{"Number of params":"35M","Test perplexity":"59.98","Validation perplexity":"62.38"},"uses_additional_data":false,"paper_date":"2019-03-11","paper":"/paper/partially-shuffling-the-training-data-to-1","paper_url":"http://arxiv.org/abs/1903.04167v2","paper_title":"Partially Shuffling the Training Data to Improve Language Models","code":"https://github.com/ofirpress/PartialShuffle","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"AWD-LSTM-MoS","metrics":{"Number of params":"35M","Test perplexity":"61.45","Validation perplexity":"63.88"},"uses_additional_data":false,"paper_date":"2017-11-10","paper":"/paper/breaking-the-softmax-bottleneck-a-high-rank","paper_url":"http://arxiv.org/abs/1711.03953v4","paper_title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","code":"https://github.com/zihangdai/mos","n_code_links":9,"official":{"repos":["zihangdai/mos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":11,"n_samples":23,"n_pointer_only_licence":1,"sample_list":"/paper/breaking-the-softmax-bottleneck-a-high-rank#ran","syntology_url":"https://syntology.ai/paper/1711.03953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.03953"}}}},{"rank_in_archive_order":27,"model":"AWD-FWM Schlag et al. (2020)","metrics":{"Number of params":"37M","Test perplexity":"61.65","Validation perplexity":"54.48"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/learning-associative-inference-using-fast-1","paper_url":"https://arxiv.org/abs/2011.07831v2","paper_title":"Learning Associative Inference Using Fast Weight Memory","code":"https://github.com/ischlag/Fast-Weight-Memory-public","n_code_links":1,"official":{"repos":["ischlag/Fast-Weight-Memory-public"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/learning-associative-inference-using-fast-1#ran","syntology_url":"https://syntology.ai/paper/2011.07831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.07831"}}}},{"rank_in_archive_order":28,"model":"AWD-LSTM-DRILL","metrics":{"Number of params":"34M","Test perplexity":"61.9","Validation perplexity":"64.9"},"uses_additional_data":false,"paper_date":"2019-05-14","paper":"/paper/deep-residual-output-layers-for-neural","paper_url":"https://arxiv.org/abs/1905.05513v2","paper_title":"Deep Residual Output Layers for Neural Language Generation","code":"https://github.com/idiap/drill","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"AWD-LSTM 3-layer with Fraternal dropout","metrics":{"Number of params":"34M","Test perplexity":"64.1","Validation perplexity":"66.8"},"uses_additional_data":false,"paper_date":"2017-10-31","paper":"/paper/fraternal-dropout","paper_url":"http://arxiv.org/abs/1711.00066v4","paper_title":"Fraternal Dropout","code":"https://github.com/kondiz/fraternal-dropout","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"AWD-LSTM + ATOI","metrics":{"Number of params":"33M","Test perplexity":"64.73","Validation perplexity":"67.47"},"uses_additional_data":false,"paper_date":"2019-09-18","paper":"/paper/alleviating-sequence-information-loss-with","paper_url":"https://arxiv.org/abs/1909.08700v1","paper_title":"Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes","code":"https://github.com/nkcr/overlap-ml","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"AWD-LSTM","metrics":{"Number of params":"33M","Test perplexity":"65.8","Validation perplexity":"68.6"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/regularizing-and-optimizing-lstm-language","paper_url":"http://arxiv.org/abs/1708.02182v1","paper_title":"Regularizing and Optimizing LSTM Language Models","code":"https://github.com/google-research/google-research/tree/master/enas_lm","n_code_links":45,"official":{"repos":["salesforce/awd-lstm-lm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/regularizing-and-optimizing-lstm-language#ran","syntology_url":"https://syntology.ai/paper/1708.02182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02182"}}}},{"rank_in_archive_order":32,"model":"Melis et al. (2017) - 1-layer LSTM (tied)","metrics":{"Number of params":"24M","Test perplexity":"65.9","Validation perplexity":"69.3"},"uses_additional_data":false,"paper_date":"2017-07-18","paper":"/paper/on-the-state-of-the-art-of-evaluation-in","paper_url":"http://arxiv.org/abs/1707.05589v2","paper_title":"On the State of the Art of Evaluation in Neural Language Models","code":"https://github.com/deepmind/lamb","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"Grave et al. (2016) - LSTM + continuous cache pointer","metrics":{"Test perplexity":"68.9"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/improving-neural-language-models-with-a","paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","code":"https://github.com/dmlc/gluon-nlp","n_code_links":14,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"EGRU","metrics":{"Test perplexity":"68.9"},"uses_additional_data":false,"paper_date":"2022-06-13","paper":"/paper/egru-event-based-gru-for-activity-sparse","paper_url":"https://arxiv.org/abs/2206.06178v3","paper_title":"Efficient recurrent architectures through activity sparsity and sparse back-propagation through time","code":"https://github.com/khaleelkhan/evnn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"Inan et al. (2016) - Variational LSTM (tied) (h=650) + augmented loss","metrics":{"Test perplexity":"87.0","Validation perplexity":"91.5"},"uses_additional_data":false,"paper_date":"2016-11-04","paper":"/paper/tying-word-vectors-and-word-classifiers-a","paper_url":"http://arxiv.org/abs/1611.01462v3","paper_title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","code":"https://github.com/JianGoForIt/YellowFin_Pytorch","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"Inan et al. (2016) - Variational LSTM (tied) (h=650)","metrics":{"Test perplexity":"87.7","Validation perplexity":"92.3"},"uses_additional_data":false,"paper_date":"2016-11-04","paper":"/paper/tying-word-vectors-and-word-classifiers-a","paper_url":"http://arxiv.org/abs/1611.01462v3","paper_title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","code":"https://github.com/JianGoForIt/YellowFin_Pytorch","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"Grave et al. (2016) - LSTM","metrics":{"Test perplexity":"99.3"},"uses_additional_data":false,"paper_date":"2016-12-13","paper":"/paper/improving-neural-language-models-with-a","paper_url":"http://arxiv.org/abs/1612.04426v1","paper_title":"Improving Neural Language Models with a Continuous Cache","code":"https://github.com/dmlc/gluon-nlp","n_code_links":14,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"OPT-175B (50% Sparsity)","metrics":{"Test perplexity":"234.77"},"uses_additional_data":true,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}}],"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,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 28 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,590 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 12 proposed a result; of those 12, 11 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 1 was placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":38,"metric_columns":3,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1590,"candidates":28,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":12,"no_cell_passed_checks":11,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":1,"placed_entries_listed":1,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): 1 placed; 12 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":12,"shown_on_page":12,"no_cell_split":{"no_cell_passed_checks_in_ledger":11,"rows_refused_by_rule":11,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.14715","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2607.20757","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2607.08780","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2606.24650","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.21847","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2606.05175","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.15491","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.04084","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the model gave no value to check against the cell"},{"arxiv_id":"2604.01609","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.25385","outcome":"placed","reason":null},{"arxiv_id":"2603.19664","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.20984","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["Test perplexity"],"entries":[{"paper":"/paper/arxiv-2603-25385","paper_title":"GlowQ: Group-Shared LOw-Rank Approximation for Quantized LLMs","arxiv_id":"2603.25385","model":"GlowQ INT4, g128 · LLaMA 2 · 13B","row_label":"GlowQ INT4, g128","configuration":"LLaMA 2 · 13B","configuration_in_model":true,"configuration_not_shown_because":null,"values":{"Test perplexity":"4.96"},"date":"2026-03-26","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “GlowQ INT4, g128”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: WikiText-2 test perplexity (lower is better). GlowQ-S restores 51% of…","caption_on_page":"percentage_figure","cells":[{"column":"Test perplexity","cell_text":"4.96","column_header":"LLaMA 2 / 13B","value":4.96,"table_index_0based":0,"row":9,"col":3}],"code":"3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","samples_harvested":3,"sample_list":"/paper/arxiv-2603-25385#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2603.25385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2603.25385"}}}}]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran 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).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":12,"rows_with_any_sample_ran":11,"rows_with_a_run_with_no_instrument_failure":11,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":12,"rows_whose_official_repository_has_a_sample_that_ran":9,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":4,"rows_community_repositories_only":2,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"distinct_papers_with_a_run_with_no_instrument_failure":5,"samples_over_distinct_papers":{"n_ran":31,"n_constructed":0,"n_ran_checked":23,"n_instrument":8,"n_unverified":17,"n_samples":48,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":85,"n_constructed":0,"n_ran_checked":64,"n_instrument":21,"n_unverified":41,"n_samples":126,"n_pointer_only_licence":63,"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"}},"record_sha256":"8977bbd0034050248d483cc6230b38e6bba62e874291129d17dd2dd007a182d9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}