{"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":"/task/continual-pretraining","name":"Continual Pretraining","slug":"continual-pretraining","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":70,"papers_with_code":34,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/continual-pretraining-on-acl-arc","slug":"continual-pretraining-on-acl-arc","dataset":"ACL-ARC","dataset_url":"/dataset/acl-arc-1","rows_in_archive":1,"metrics":["F1 (macro)"],"first_row_in_archive_order":{"model":"DAS","paper_title":"Continual Pre-training of Language Models","paper_url":"/paper/continual-learning-of-language-models","paper_date":"2023-02-07","arxiv_id":"2302.03241","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"},{"title":"UIC-Liu-Lab/ContinualLM","url":"https://github.com/UIC-Liu-Lab/ContinualLM"}],"syntology":null}},{"leaderboard":"/sota/continual-pretraining-on-ag-news","slug":"continual-pretraining-on-ag-news","dataset":"AG News","dataset_url":"/dataset/ag-news","rows_in_archive":1,"metrics":["F1 - macro"],"first_row_in_archive_order":{"model":"CPT","paper_title":"Continual Training of Language Models for Few-Shot Learning","paper_url":"/paper/continual-training-of-language-models-for-few","paper_date":"2022-10-11","arxiv_id":"2210.05549","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"},{"title":"UIC-Liu-Lab/ContinualLM","url":"https://github.com/UIC-Liu-Lab/ContinualLM"},{"title":"uic-liu-lab/cpt","url":"https://github.com/uic-liu-lab/cpt"}],"syntology":null}},{"leaderboard":"/sota/continual-pretraining-on-scierc","slug":"continual-pretraining-on-scierc","dataset":"SciERC","dataset_url":"/dataset/scierc","rows_in_archive":1,"metrics":["F1 (macro)"],"first_row_in_archive_order":{"model":"DAS","paper_title":"Continual Pre-training of Language Models","paper_url":"/paper/continual-learning-of-language-models","paper_date":"2023-02-07","arxiv_id":"2302.03241","code_links":[{"title":"zixuanke/pycontinual","url":"https://github.com/zixuanke/pycontinual"},{"title":"UIC-Liu-Lab/ContinualLM","url":"https://github.com/UIC-Liu-Lab/ContinualLM"}],"syntology":null}}],"datasets":[{"url":"/dataset/ag-news","name":"AG News","full_name":"AG’s News Corpus","num_papers_in_archive":969},{"url":"/dataset/scierc","name":"SciERC","full_name":"","num_papers_in_archive":134},{"url":"/dataset/acl-arc-1","name":"ACL ARC","full_name":"","num_papers_in_archive":14}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":70,"of":70,"of_with_code":34,"tagged_in_all":70,"counts":{"archive_papers_tagged":70,"with_a_code_link":34,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":70,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/rho-1-not-all-tokens-are-what-you-need","slug":"rho-1-not-all-tokens-are-what-you-need","title":"Rho-1: Not All Tokens Are What You Need","date":"2024-04-11","arxiv_id":"2404.07965","repositories_listed":3,"syntology":null},{"url":"/paper/continual-training-of-language-models-for-few","slug":"continual-training-of-language-models-for-few","title":"Continual Training of Language Models for Few-Shot Learning","date":"2022-10-11","arxiv_id":"2210.05549","repositories_listed":3,"syntology":null},{"url":"/paper/automathtext-autonomous-data-selection-with","slug":"automathtext-autonomous-data-selection-with","title":"Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts","date":"2024-02-12","arxiv_id":"2402.07625","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/automathtext-autonomous-data-selection-with#ran","syntology_url":"https://syntology.ai/paper/2402.07625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07625"}},"official":{"repos":["hiyouga/llama-factory","yifanzhang-pro/automathtext"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/effective-long-context-scaling-of-foundation","slug":"effective-long-context-scaling-of-foundation","title":"Effective Long-Context Scaling of Foundation Models","date":"2023-09-27","arxiv_id":"2309.16039","repositories_listed":2,"syntology":null},{"url":"/paper/gfm-building-geospatial-foundation-models-via","slug":"gfm-building-geospatial-foundation-models-via","title":"Towards Geospatial Foundation Models via Continual Pretraining","date":"2023-02-09","arxiv_id":"2302.04476","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/gfm-building-geospatial-foundation-models-via#ran","syntology_url":"https://syntology.ai/paper/2302.04476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04476"}},"official":{"repos":["mmendiet/gfm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/continual-learning-of-language-models","slug":"continual-learning-of-language-models","title":"Continual Pre-training of Language Models","date":"2023-02-07","arxiv_id":"2302.03241","repositories_listed":2,"syntology":null},{"url":"/paper/deer-a-data-efficient-language-model-for","slug":"deer-a-data-efficient-language-model-for","title":"ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning","date":"2020-12-30","arxiv_id":"2012.15283","repositories_listed":2,"syntology":null},{"url":"/paper/domain-specific-language-model-pretraining","slug":"domain-specific-language-model-pretraining","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","date":"2020-07-31","arxiv_id":"2007.15779","repositories_listed":2,"syntology":null},{"url":"/paper/simulating-training-data-leakage-in-multiple","slug":"simulating-training-data-leakage-in-multiple","title":"Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation","date":"2025-05-30","arxiv_id":"2505.24263","repositories_listed":1,"syntology":null},{"url":"/paper/a-japanese-language-model-and-three-new","slug":"a-japanese-language-model-and-three-new","title":"A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP","date":"2025-05-22","arxiv_id":"2505.16661","repositories_listed":1,"syntology":null},{"url":"/paper/tic-lm-a-web-scale-benchmark-for-time","slug":"tic-lm-a-web-scale-benchmark-for-time","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","date":"2025-04-02","arxiv_id":"2504.02107","repositories_listed":1,"syntology":null},{"url":"/paper/robust-data-watermarking-in-language-models","slug":"robust-data-watermarking-in-language-models","title":"Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge","date":"2025-03-06","arxiv_id":"2503.04036","repositories_listed":1,"syntology":null},{"url":"/paper/demystifying-domain-adaptive-post-training","slug":"demystifying-domain-adaptive-post-training","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","date":"2025-01-09","arxiv_id":"2501.04961","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/demystifying-domain-adaptive-post-training#ran","syntology_url":"https://syntology.ai/paper/2501.04961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04961"}},"official":{"repos":["salesforceairesearch/findap"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/nyayaanumana-inlegalllama-the-largest-indian","slug":"nyayaanumana-inlegalllama-the-largest-indian","title":"NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis","date":"2024-12-11","arxiv_id":"2412.08385","repositories_listed":1,"syntology":null},{"url":"/paper/alchemy-amplifying-theorem-proving-capability","slug":"alchemy-amplifying-theorem-proving-capability","title":"Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation","date":"2024-10-21","arxiv_id":"2410.15748","repositories_listed":1,"syntology":null},{"url":"/paper/langsamp-language-script-aware-multilingual","slug":"langsamp-language-script-aware-multilingual","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","date":"2024-09-26","arxiv_id":"2409.18199","repositories_listed":1,"syntology":null},{"url":"/paper/a-practitioner-s-guide-to-continual","slug":"a-practitioner-s-guide-to-continual","title":"A Practitioner's Guide to Continual Multimodal Pretraining","date":"2024-08-26","arxiv_id":"2408.14471","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-granite-code-models-to-128k-context","slug":"scaling-granite-code-models-to-128k-context","title":"Scaling Granite Code Models to 128K Context","date":"2024-07-18","arxiv_id":"2407.13739","repositories_listed":1,"syntology":null},{"url":"/paper/towards-lifelong-learning-of-large-language","slug":"towards-lifelong-learning-of-large-language","title":"Towards Lifelong Learning of Large Language Models: A Survey","date":"2024-06-10","arxiv_id":"2406.06391","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-guided-soft-contrastive-learning","slug":"multi-label-guided-soft-contrastive-learning","title":"Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining","date":"2024-05-30","arxiv_id":"2405.20462","repositories_listed":1,"syntology":null},{"url":"/paper/mora-high-rank-updating-for-parameter","slug":"mora-high-rank-updating-for-parameter","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","date":"2024-05-20","arxiv_id":"2405.12130","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mora-high-rank-updating-for-parameter#ran","syntology_url":"https://syntology.ai/paper/2405.12130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12130"}},"official":{"repos":["kongds/mora"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-head-mechanistically-explains-long","slug":"retrieval-head-mechanistically-explains-long","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","date":"2024-04-24","arxiv_id":"2404.15574","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-head-mechanistically-explains-long#ran","syntology_url":"https://syntology.ai/paper/2404.15574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15574"}},"official":{"repos":["nightdessert/retrieval_head"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/yi-open-foundation-models-by-01-ai","slug":"yi-open-foundation-models-by-01-ai","title":"Yi: Open Foundation Models by 01.AI","date":"2024-03-07","arxiv_id":"2403.04652","repositories_listed":1,"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/yi-open-foundation-models-by-01-ai#ran","syntology_url":"https://syntology.ai/paper/2403.04652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04652"}},"official":{"repos":["01-ai/yi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/data-engineering-for-scaling-language-models","slug":"data-engineering-for-scaling-language-models","title":"Data Engineering for Scaling Language Models to 128K Context","date":"2024-02-15","arxiv_id":"2402.10171","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/data-engineering-for-scaling-language-models#ran","syntology_url":"https://syntology.ai/paper/2402.10171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10171"}},"official":{"repos":["franxyao/long-context-data-engineering"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pecop-parameter-efficient-continual","slug":"pecop-parameter-efficient-continual","title":"PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment","date":"2023-11-11","arxiv_id":"2311.07603","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"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","sample_list":"/paper/pecop-parameter-efficient-continual#ran","syntology_url":"https://syntology.ai/paper/2311.07603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07603"}},"official":{"repos":["plrbear/pecop"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/ctp-towards-vision-language-continual","slug":"ctp-towards-vision-language-continual","title":"CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","date":"2023-08-14","arxiv_id":"2308.07146","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ctp-towards-vision-language-continual#ran","syntology_url":"https://syntology.ai/paper/2308.07146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07146"}},"official":{"repos":["kevinlight831/ctp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ctp-towards-vision-language-continual-1","slug":"ctp-towards-vision-language-continual-1","title":"CTP:Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/cbeaf-adapting-enhanced-continual-pretraining","slug":"cbeaf-adapting-enhanced-continual-pretraining","title":"AF Adapter: Continual Pretraining for Building Chinese Biomedical Language Model","date":"2022-11-21","arxiv_id":"2211.11363","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-domain-adaptation-for-sparse","slug":"unsupervised-domain-adaptation-for-sparse","title":"Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps","date":"2022-11-08","arxiv_id":"2211.03988","repositories_listed":1,"syntology":null},{"url":"/paper/continual-pre-training-mitigates-forgetting","slug":"continual-pre-training-mitigates-forgetting","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","date":"2022-05-19","arxiv_id":"2205.09357","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continual-pre-training-mitigates-forgetting#ran","syntology_url":"https://syntology.ai/paper/2205.09357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09357"}},"official":{"repos":["andreacossu/continual-pretraining-nlp-vision"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-label-wise-attention-transformer","slug":"hierarchical-label-wise-attention-transformer","title":"Hierarchical Label-wise Attention Transformer Model for Explainable ICD Coding","date":"2022-04-22","arxiv_id":"2204.10716","repositories_listed":1,"syntology":null},{"url":"/paper/fortunately-discourse-markers-can-enhance","slug":"fortunately-discourse-markers-can-enhance","title":"Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis","date":"2022-01-06","arxiv_id":"2201.02026","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-reading-comprehension","slug":"on-the-robustness-of-reading-comprehension","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-10-16","arxiv_id":"2110.08555","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-contrastive-learning-via-novel-data","slug":"efficient-contrastive-learning-via-novel-data","title":"Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning","date":"2021-09-10","arxiv_id":"2109.05941","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"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) · 6 unverified","sample_list":"/paper/efficient-contrastive-learning-via-novel-data#ran","syntology_url":"https://syntology.ai/paper/2109.05941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05941"}},"official":{"repos":["vano1205/efficientcl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":null,"slug":"biomed-enriched-a-biomedical-dataset-enriched","title":"Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content","date":"2025-06-25","arxiv_id":"2506.20331","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-c-continual-improved-visual-instruction","title":"LLaVA-c: Continual Improved Visual Instruction Tuning","date":"2025-06-10","arxiv_id":"2506.08666","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhance-mobile-agents-thinking-process-via","title":"Enhance Mobile Agents Thinking Process Via Iterative Preference Learning","date":"2025-05-18","arxiv_id":"2505.12299","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-hidden-thoughts-from-texts-evaluating","title":"Mining Hidden Thoughts from Texts: Evaluating Continual Pretraining with Synthetic Data for LLM Reasoning","date":"2025-05-15","arxiv_id":"2505.10182","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-domain-adaptive-continual","title":"Efficient Domain-adaptive Continual Pretraining for the Process Industry in the German Language","date":"2025-04-28","arxiv_id":"2504.19856","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-domain-specific-encoder-models-with","title":"Enhancing Domain-Specific Encoder Models with LLM-Generated Data: How to Leverage Ontologies, and How to Do Without Them","date":"2025-03-27","arxiv_id":"2503.22006","repositories_listed":0,"syntology":null},{"url":null,"slug":"afroxlmr-social-adapting-pre-trained-language","title":"AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text","date":"2025-03-24","arxiv_id":"2503.18247","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-vocabulary-mismatch-vocabulary","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","date":"2025-03-24","arxiv_id":"2503.19123","repositories_listed":0,"syntology":null},{"url":"/paper/multilingual-machine-translation-with-open","slug":"multilingual-machine-translation-with-open","title":"Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study","date":"2025-02-04","arxiv_id":"2502.02481","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multilingual-machine-translation-with-open#ran","syntology_url":"https://syntology.ai/paper/2502.02481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02481"}},"official":null}},{"url":null,"slug":"breaking-the-stage-barrier-a-novel-single","title":"Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models","date":"2024-12-10","arxiv_id":"2412.07171","repositories_listed":0,"syntology":null},{"url":null,"slug":"dopamine-domain-specific-pre-training","title":"DoPAMine: Domain-specific Pre-training Adaptation from seed-guided data Mining","date":"2024-09-30","arxiv_id":"2410.00260","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-construction-of-instruction-tuned-llms","title":"The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging","date":"2024-09-30","arxiv_id":"2409.19854","repositories_listed":0,"syntology":null},{"url":null,"slug":"astromlab-2-astrollama-2-70b-model-and","title":"AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy","date":"2024-09-29","arxiv_id":"2409.19750","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-democratizing-multilingual-large","title":"Towards Democratizing Multilingual Large Language Models For Medicine Through A Two-Stage Instruction Fine-tuning Approach","date":"2024-09-09","arxiv_id":"2409.05732","repositories_listed":0,"syntology":null},{"url":null,"slug":"redwhale-an-adapted-korean-llm-through","title":"RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining","date":"2024-08-21","arxiv_id":"2408.11294","repositories_listed":0,"syntology":null},{"url":null,"slug":"bilingual-adaptation-of-monolingual","title":"Bilingual Adaptation of Monolingual Foundation Models","date":"2024-07-13","arxiv_id":"2407.12869","repositories_listed":0,"syntology":null},{"url":null,"slug":"70b-parameter-large-language-models-in","title":"70B-parameter large language models in Japanese medical question-answering","date":"2024-06-21","arxiv_id":"2406.14882","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-generative-large-language-models-for","title":"Open Generative Large Language Models for Galician","date":"2024-06-19","arxiv_id":"2406.13893","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-rope-extensions-of-long","title":"Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective","date":"2024-06-19","arxiv_id":"2406.13282","repositories_listed":0,"syntology":null},{"url":null,"slug":"bambino-lm-bilingual-human-inspired-continual","title":"BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM","date":"2024-06-17","arxiv_id":"2406.11418","repositories_listed":0,"syntology":null},{"url":null,"slug":"longskywork-a-training-recipe-for-efficiently","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","date":"2024-06-02","arxiv_id":"2406.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-sensor-self-supervised-training-and","title":"Cross-sensor self-supervised training and alignment for remote sensing","date":"2024-05-16","arxiv_id":"2405.09922","repositories_listed":0,"syntology":null},{"url":null,"slug":"chuxin-1-6b-technical-report","title":"ChuXin: 1.6B Technical Report","date":"2024-05-08","arxiv_id":"2405.04828","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-and-updating-language-and-domain","title":"Pretraining and Updates of Domain-Specific LLM: A Case Study in the Japanese Business Domain","date":"2024-04-12","arxiv_id":"2404.08262","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-can-continue-evolving","title":"CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes","date":"2024-04-11","arxiv_id":"2404.08707","repositories_listed":0,"syntology":null},{"url":null,"slug":"aurora-m-the-first-open-source-multilingual","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","date":"2024-03-30","arxiv_id":"2404.00399","repositories_listed":0,"syntology":null},{"url":null,"slug":"paramanu-ayn-an-efficient-novel-generative","title":"PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation?","date":"2024-03-20","arxiv_id":"2403.13681","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-continual-pretraining-in-large","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","date":"2024-02-27","arxiv_id":"2402.17400","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-for-large-language-models","title":"Continual Learning for Large Language Models: A Survey","date":"2024-02-02","arxiv_id":"2402.01364","repositories_listed":0,"syntology":null},{"url":null,"slug":"romansetu-efficiently-unlocking-multilingual","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","date":"2024-01-25","arxiv_id":"2401.14280","repositories_listed":0,"syntology":null},{"url":null,"slug":"dd-tig-at-constraint-acl2022-multimodal","title":"DD-TIG at Constraint@ACL2022: Multimodal Understanding and Reasoning for Role Labeling of Entities in Hateful Memes","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaprompt-adaptive-model-training-for-prompt","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","date":"2022-02-10","arxiv_id":"2202.04824","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-robustness-of-reading-comprehension-1","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-domain-adaptation-worth-your-investment","title":"Is Domain Adaptation Worth Your Investment? Comparing BERT and FinBERT on Financial Tasks","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-pretraining-continually-adapting","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","date":"2021-10-16","arxiv_id":"2110.08534","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-pretraining-with-adapters","title":"Revisiting Pretraining with Adapters","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/continual-pretraining-on-acl-arc","since_archive":"/sota/continual-pretraining-on-acl-arc#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/continual-pretraining/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/continual-pretraining/papers/ran/1","json":"/task/continual-pretraining/papers/ran/1.json","rows":12}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"39e53e52f3fcce970184e9e641e7f8bc06e3958dbaaed22bf8569b8b0e624281","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}