{"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/knowledge-probing","name":"Knowledge Probing","slug":"knowledge-probing","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":46,"papers_with_code":23,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":5,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/popqa","name":"PopQA","full_name":"","num_papers_in_archive":91},{"url":"/dataset/tofu","name":"TOFU","full_name":"Task of Fictitious Unlearning","num_papers_in_archive":51},{"url":"/dataset/biolama","name":"BioLAMA","full_name":"","num_papers_in_archive":14},{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1},{"url":"/dataset/spectral-detection-and-analysis-based-paper","name":"Spectral Detection and Analysis Based Paper(SDAAP) dataset","full_name":"","num_papers_in_archive":1}],"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":46,"of":46,"of_with_code":23,"tagged_in_all":46,"counts":{"archive_papers_tagged":46,"with_a_code_link":23,"where_syntology_ran_a_sample":10,"not_listed_spam_title":0,"listed":46,"listed_where_code_ran":10,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","repositories_listed":10,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 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/gpt-understands-too#ran","syntology_url":"https://syntology.ai/paper/2103.10385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10385"}},"official":{"repos":["THUDM/P-tuning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/can-language-models-solve-graph-problems-in","slug":"can-language-models-solve-graph-problems-in","title":"Can Language Models Solve Graph Problems in Natural Language?","date":"2023-05-17","arxiv_id":"2305.10037","repositories_listed":2,"syntology":{"n":22,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/can-language-models-solve-graph-problems-in#ran","syntology_url":"https://syntology.ai/paper/2305.10037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10037"}},"official":{"repos":["arthur-heng/nlgraph"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/promptkg-a-prompt-learning-framework-for","slug":"promptkg-a-prompt-learning-framework-for","title":"LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings","date":"2022-10-01","arxiv_id":"2210.00305","repositories_listed":2,"syntology":null},{"url":"/paper/correlation-and-navigation-in-the-vocabulary","slug":"correlation-and-navigation-in-the-vocabulary","title":"Correlation and Navigation in the Vocabulary Key Representation Space of Language Models","date":"2024-10-03","arxiv_id":"2410.02284","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/correlation-and-navigation-in-the-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2410.02284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02284"}},"official":{"repos":["KomeijiForce/KeyNavi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bear-a-unified-framework-for-evaluating","slug":"bear-a-unified-framework-for-evaluating","title":"BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language Models","date":"2024-04-05","arxiv_id":"2404.04113","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":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) · 0 unverified","sample_list":"/paper/bear-a-unified-framework-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2404.04113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04113"}},"official":{"repos":["lm-pub-quiz/lm-pub-quiz"],"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/unveiling-llms-the-evolution-of-latent","slug":"unveiling-llms-the-evolution-of-latent","title":"Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph","date":"2024-04-04","arxiv_id":"2404.03623","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unveiling-llms-the-evolution-of-latent#ran","syntology_url":"https://syntology.ai/paper/2404.03623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03623"}},"official":{"repos":["Ipazia-AI/latent-explorer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tracing-the-roots-of-facts-in-multilingual","slug":"tracing-the-roots-of-facts-in-multilingual","title":"Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge","date":"2024-03-08","arxiv_id":"2403.05189","repositories_listed":1,"syntology":null},{"url":"/paper/promptcblue-a-chinese-prompt-tuning-benchmark","slug":"promptcblue-a-chinese-prompt-tuning-benchmark","title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain","date":"2023-10-22","arxiv_id":"2310.14151","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-the-reliability-of-large-language","slug":"assessing-the-reliability-of-large-language","title":"Assessing the Reliability of Large Language Model Knowledge","date":"2023-10-15","arxiv_id":"2310.09820","repositories_listed":1,"syntology":null},{"url":"/paper/using-large-language-models-for-knowledge","slug":"using-large-language-models-for-knowledge","title":"Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata","date":"2023-09-15","arxiv_id":"2309.08491","repositories_listed":1,"syntology":null},{"url":"/paper/lexfiles-and-legallama-facilitating-english","slug":"lexfiles-and-legallama-facilitating-english","title":"LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development","date":"2023-05-12","arxiv_id":"2305.07507","repositories_listed":1,"syntology":null},{"url":"/paper/is-bert-blind-exploring-the-effect-of-vision","slug":"is-bert-blind-exploring-the-effect-of-vision","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","date":"2023-03-21","arxiv_id":"2303.12513","repositories_listed":1,"syntology":null},{"url":"/paper/when-not-to-trust-language-models","slug":"when-not-to-trust-language-models","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","date":"2022-12-20","arxiv_id":"2212.10511","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/when-not-to-trust-language-models#ran","syntology_url":"https://syntology.ai/paper/2212.10511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10511"}},"official":{"repos":["alextmallen/adaptive-retrieval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/injecting-domain-knowledge-in-language-models","slug":"injecting-domain-knowledge-in-language-models","title":"Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems","date":"2022-12-15","arxiv_id":"2212.08120","repositories_listed":1,"syntology":null},{"url":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 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) · 0 unverified","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/copen-probing-conceptual-knowledge-in-pre","slug":"copen-probing-conceptual-knowledge-in-pre","title":"COPEN: Probing Conceptual Knowledge in Pre-trained Language Models","date":"2022-11-08","arxiv_id":"2211.04079","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/copen-probing-conceptual-knowledge-in-pre#ran","syntology_url":"https://syntology.ai/paper/2211.04079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04079"}},"official":{"repos":["thu-keg/copen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/calibrating-factual-knowledge-in-pretrained","slug":"calibrating-factual-knowledge-in-pretrained","title":"Calibrating Factual Knowledge in Pretrained Language Models","date":"2022-10-07","arxiv_id":"2210.03329","repositories_listed":1,"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/calibrating-factual-knowledge-in-pretrained#ran","syntology_url":"https://syntology.ai/paper/2210.03329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03329"}},"official":{"repos":["dqxiu/calinet"],"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"]}}},{"url":"/paper/lm-core-language-models-with-contextually-1","slug":"lm-core-language-models-with-contextually-1","title":"LM-CORE: Language Models with Contextually Relevant External Knowledge","date":"2022-08-12","arxiv_id":"2208.06458","repositories_listed":1,"syntology":null},{"url":"/paper/mgpt-few-shot-learners-go-multilingual","slug":"mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","repositories_listed":1,"syntology":null},{"url":"/paper/dkplm-decomposable-knowledge-enhanced-pre","slug":"dkplm-decomposable-knowledge-enhanced-pre","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","date":"2021-12-02","arxiv_id":"2112.01047","repositories_listed":1,"syntology":null},{"url":"/paper/rewire-then-probe-a-contrastive-recipe-for","slug":"rewire-then-probe-a-contrastive-recipe-for","title":"Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models","date":"2021-10-15","arxiv_id":"2110.08173","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-on-few-shot-knowledge","slug":"an-empirical-study-on-few-shot-knowledge","title":"An Empirical Study on Few-shot Knowledge Probing for Pretrained Language Models","date":"2021-09-06","arxiv_id":"2109.02772","repositories_listed":1,"syntology":null},{"url":"/paper/colake-contextualized-language-and-knowledge","slug":"colake-contextualized-language-and-knowledge","title":"CoLAKE: Contextualized Language and Knowledge Embedding","date":"2020-10-01","arxiv_id":"2010.00309","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/colake-contextualized-language-and-knowledge#ran","syntology_url":"https://syntology.ai/paper/2010.00309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00309"}},"official":{"repos":["txsun1997/CoLAKE"],"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":null,"slug":"do-we-know-what-llms-don-t-know-a-study-of","title":"Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing","date":"2025-05-27","arxiv_id":"2505.21701","repositories_listed":0,"syntology":null},{"url":null,"slug":"let-s-argue-both-sides-argument-generation","title":"\"Let's Argue Both Sides\": Argument Generation Can Force Small Models to Utilize Previously Inaccessible Reasoning Capabilities","date":"2024-10-16","arxiv_id":"2410.12997","repositories_listed":0,"syntology":null},{"url":null,"slug":"lm-pub-quiz-a-comprehensive-framework-for","title":"LM-PUB-QUIZ: A Comprehensive Framework for Zero-Shot Evaluation of Relational Knowledge in Language Models","date":"2024-08-28","arxiv_id":"2408.15729","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-probing-for-graph-representation","title":"Knowledge Probing for Graph Representation Learning","date":"2024-08-07","arxiv_id":"2408.03877","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-matters-in-learning-facts-in-language","title":"What Matters in Memorizing and Recalling Facts? Multifaceted Benchmarks for Knowledge Probing in Language Models","date":"2024-06-18","arxiv_id":"2406.12277","repositories_listed":0,"syntology":null},{"url":null,"slug":"chaos-with-keywords-exposing-large-language","title":"Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies","date":"2024-06-06","arxiv_id":"2406.03827","repositories_listed":0,"syntology":null},{"url":null,"slug":"trelm-towards-robust-and-efficient-pre","title":"TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models","date":"2024-03-17","arxiv_id":"2403.11203","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-trust-your-feelings-leveraging","title":"Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation","date":"2024-01-27","arxiv_id":"2401.15449","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-representation-projection-can-we","title":"Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?","date":"2023-11-07","arxiv_id":"2311.03788","repositories_listed":0,"syntology":null},{"url":null,"slug":"give-me-the-facts-a-survey-on-factual","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","date":"2023-10-25","arxiv_id":"2310.16570","repositories_listed":0,"syntology":null},{"url":null,"slug":"kiki-or-bouba-sound-symbolism-in-vision-and","title":"Kiki or Bouba? Sound Symbolism in Vision-and-Language Models","date":"2023-10-25","arxiv_id":"2310.16781","repositories_listed":0,"syntology":null},{"url":null,"slug":"pop-quiz-do-pre-trained-code-models-possess","title":"Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?","date":"2023-09-14","arxiv_id":"2309.07804","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-augmented-frame-semantic-parsing","title":"Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning","date":"2023-03-25","arxiv_id":"2303.14375","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-variance-evaluation-of-pretrained","title":"Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing","date":"2022-11-18","arxiv_id":"2211.10265","repositories_listed":0,"syntology":null},{"url":null,"slug":"pre-training-language-models-with","title":"Pre-training Language Models with Deterministic Factual Knowledge","date":"2022-10-20","arxiv_id":"2210.11165","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptgen-automatically-generate-prompts","title":"PromptGen: Automatically Generate Prompts using Generative Models","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-learning-for-fine-grained-entity-1","title":"Prompt-Learning for Fine-Grained Entity Typing","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rewire-then-probe-a-contrastive-recipe-for-1","title":"Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Models","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fully-self-supervised-learning-of","title":"Towards Fully Self-Supervised Learning of Knowledge from Unstructured Text","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-transformers-and-knowledge-graphs","title":"Integrating Transformers and Knowledge Graphs for Twitter Stance Detection","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-learning-for-fine-grained-entity","title":"Prompt-Learning for Fine-Grained Entity Typing","date":"2021-08-24","arxiv_id":"2108.10604","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aware-language-model-pretraining","title":"Knowledge-Aware Language Model Pretraining","date":"2020-06-29","arxiv_id":"2007.00655","repositories_listed":0,"syntology":null}],"syntology_records":10,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":10,"papers_where_code_ran_first_page":"/task/knowledge-probing/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/knowledge-probing/papers/ran/1","json":"/task/knowledge-probing/papers/ran/1.json","rows":10}],"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":"77ac556bf3fdb76f7e73d28850fbca0459be18e379a025d9eb2b2cc71b2516b9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}