{"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/language-modeling/papers/42","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":42,"pages_in_order":142,"rows_per_page":100,"rows":[4101,4200],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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"},"first_page":"/task/language-modeling","prev":"/task/language-modeling/papers/41","next":"/task/language-modeling/papers/43","papers":[{"url":"/paper/very-large-language-model-as-a-unified","slug":"very-large-language-model-as-a-unified","title":"Very Large Language Model as a Unified Methodology of Text Mining","date":"2022-12-19","arxiv_id":"2212.09271","repositories_listed":1,"syntology":null},{"url":"/paper/visconde-multi-document-qa-with-gpt-3-and","slug":"visconde-multi-document-qa-with-gpt-3-and","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","date":"2022-12-19","arxiv_id":"2212.09656","repositories_listed":1,"syntology":null},{"url":"/paper/can-retriever-augmented-language-models","slug":"can-retriever-augmented-language-models","title":"Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model","date":"2022-12-18","arxiv_id":"2212.09146","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-role-of-scale-for-in-context","slug":"rethinking-the-role-of-scale-for-in-context","title":"Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale","date":"2022-12-18","arxiv_id":"2212.09095","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-the-role-of-scale-for-in-context#ran","syntology_url":"https://syntology.ai/paper/2212.09095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09095"}},"official":{"repos":["amazon-science/llm-interpret"],"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":["official"]}}},{"url":"/paper/claim-optimization-in-computational","slug":"claim-optimization-in-computational","title":"Claim Optimization in Computational Argumentation","date":"2022-12-17","arxiv_id":"2212.08913","repositories_listed":1,"syntology":null},{"url":"/paper/hype-better-pre-trained-language-model-fine","slug":"hype-better-pre-trained-language-model-fine","title":"HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation","date":"2022-12-17","arxiv_id":"2212.08853","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-multi-modal-and-multi-hop-question","slug":"enhancing-multi-modal-and-multi-hop-question","title":"Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation","date":"2022-12-16","arxiv_id":"2212.08632","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-long-sequence-modeling-via-state","slug":"efficient-long-sequence-modeling-via-state","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","date":"2022-12-15","arxiv_id":"2212.08136","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-long-sequence-modeling-via-state#ran","syntology_url":"https://syntology.ai/paper/2212.08136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08136"}},"official":{"repos":["microsoft/efficientlongsequencemodeling"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-pre-training-of-masked-language","slug":"efficient-pre-training-of-masked-language","title":"Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking","date":"2022-12-15","arxiv_id":"2212.07617","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":1,"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/efficient-pre-training-of-masked-language#ran","syntology_url":"https://syntology.ai/paper/2212.07617","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.07617"}},"official":{"repos":["koreamglee/concept-based-curriculum-masking"],"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/joint-processing-of-linguistic-properties-in","slug":"joint-processing-of-linguistic-properties-in","title":"Joint processing of linguistic properties in brains and language models","date":"2022-12-15","arxiv_id":"2212.08094","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/joint-processing-of-linguistic-properties-in#ran","syntology_url":"https://syntology.ai/paper/2212.08094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08094"}},"official":null}},{"url":"/paper/on-second-thought-let-s-not-think-step-by","slug":"on-second-thought-let-s-not-think-step-by","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","date":"2022-12-15","arxiv_id":"2212.08061","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-second-thought-let-s-not-think-step-by#ran","syntology_url":"https://syntology.ai/paper/2212.08061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08061"}},"official":{"repos":["salt-nlp/chain-of-thought-bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-effects-of-in-domain-corpus-size-on-pre","slug":"the-effects-of-in-domain-corpus-size-on-pre","title":"The Effects of In-domain Corpus Size on pre-training BERT","date":"2022-12-15","arxiv_id":"2212.07914","repositories_listed":1,"syntology":null},{"url":"/paper/do-text-to-text-multi-task-learners-suffer","slug":"do-text-to-text-multi-task-learners-suffer","title":"Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?","date":"2022-12-13","arxiv_id":"2212.06645","repositories_listed":1,"syntology":null},{"url":"/paper/ernie-code-beyond-english-centric-cross","slug":"ernie-code-beyond-english-centric-cross","title":"ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages","date":"2022-12-13","arxiv_id":"2212.06742","repositories_listed":1,"syntology":null},{"url":"/paper/prompting-is-programming-a-query-language-for","slug":"prompting-is-programming-a-query-language-for","title":"Prompting Is Programming: A Query Language for Large Language Models","date":"2022-12-12","arxiv_id":"2212.06094","repositories_listed":1,"syntology":null},{"url":"/paper/reveal-retrieval-augmented-visual-language","slug":"reveal-retrieval-augmented-visual-language","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","date":"2022-12-10","arxiv_id":"2212.05221","repositories_listed":1,"syntology":null},{"url":"/paper/from-clozing-to-comprehending-retrofitting","slug":"from-clozing-to-comprehending-retrofitting","title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","date":"2022-12-09","arxiv_id":"2212.04755","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 2 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) · 1 unverified","sample_list":"/paper/from-clozing-to-comprehending-retrofitting#ran","syntology_url":"https://syntology.ai/paper/2212.04755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04755"}},"official":{"repos":["damo-nlp-sg/pmr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-like-a-language-model-analysing-ai","slug":"structured-like-a-language-model-analysing-ai","title":"Structured Like a Language Model: Analysing AI as an Automated Subject","date":"2022-12-08","arxiv_id":"2212.05058","repositories_listed":1,"syntology":null},{"url":"/paper/a-generative-approach-for-script-event-1","slug":"a-generative-approach-for-script-event-1","title":"A Generative Approach for Script Event Prediction via Contrastive Fine-tuning","date":"2022-12-07","arxiv_id":"2212.03496","repositories_listed":1,"syntology":null},{"url":"/paper/g-map-general-memory-augmented-pre-trained","slug":"g-map-general-memory-augmented-pre-trained","title":"G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks","date":"2022-12-07","arxiv_id":"2212.03613","repositories_listed":1,"syntology":null},{"url":"/paper/poda-prompt-driven-zero-shot-domain","slug":"poda-prompt-driven-zero-shot-domain","title":"PØDA: Prompt-driven Zero-shot Domain Adaptation","date":"2022-12-06","arxiv_id":"2212.03241","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/poda-prompt-driven-zero-shot-domain#ran","syntology_url":"https://syntology.ai/paper/2212.03241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03241"}},"official":{"repos":["astra-vision/poda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-lingual-similarity-of-multilingual","slug":"cross-lingual-similarity-of-multilingual","title":"Cross-lingual Similarity of Multilingual Representations Revisited","date":"2022-12-04","arxiv_id":"2212.01924","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-stochastic-autoregressive-image","slug":"exploring-stochastic-autoregressive-image","title":"Exploring Stochastic Autoregressive Image Modeling for Visual Representation","date":"2022-12-03","arxiv_id":"2212.01610","repositories_listed":1,"syntology":null},{"url":"/paper/nonparametric-masked-language-modeling","slug":"nonparametric-masked-language-modeling","title":"Nonparametric Masked Language Modeling","date":"2022-12-02","arxiv_id":"2212.01349","repositories_listed":1,"syntology":null},{"url":"/paper/reinforced-language-modeling-for-end-to-end","slug":"reinforced-language-modeling-for-end-to-end","title":"KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning","date":"2022-11-30","arxiv_id":"2211.16773","repositories_listed":1,"syntology":null},{"url":"/paper/coder-reviewer-reranking-for-code-generation","slug":"coder-reviewer-reranking-for-code-generation","title":"Coder Reviewer Reranking for Code Generation","date":"2022-11-29","arxiv_id":"2211.16490","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/coder-reviewer-reranking-for-code-generation#ran","syntology_url":"https://syntology.ai/paper/2211.16490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16490"}},"official":{"repos":["facebookresearch/coder_reviewer_reranking"],"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/composition-based-oxidation-state-prediction","slug":"composition-based-oxidation-state-prediction","title":"Composition based oxidation state prediction of materials using deep learning","date":"2022-11-29","arxiv_id":"2211.15895","repositories_listed":1,"syntology":null},{"url":"/paper/syntactic-substitutability-as-unsupervised","slug":"syntactic-substitutability-as-unsupervised","title":"Syntactic Substitutability as Unsupervised Dependency Syntax","date":"2022-11-29","arxiv_id":"2211.16031","repositories_listed":1,"syntology":null},{"url":"/paper/conal-anticipating-outliers-with-large","slug":"conal-anticipating-outliers-with-large","title":"Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models","date":"2022-11-28","arxiv_id":"2211.15718","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conal-anticipating-outliers-with-large#ran","syntology_url":"https://syntology.ai/paper/2211.15718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15718"}},"official":{"repos":["albertkx/conal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusionbert-improving-generative-masked","slug":"diffusionbert-improving-generative-masked","title":"DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models","date":"2022-11-28","arxiv_id":"2211.15029","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diffusionbert-improving-generative-masked#ran","syntology_url":"https://syntology.ai/paper/2211.15029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15029"}},"official":{"repos":["hzfinfdu/diffusion-bert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-what-you-miss-vision-language-pre","slug":"seeing-what-you-miss-vision-language-pre","title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","date":"2022-11-24","arxiv_id":"2211.13437","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-attribute-detection","slug":"open-vocabulary-attribute-detection","title":"Open-vocabulary Attribute Detection","date":"2022-11-23","arxiv_id":"2211.12914","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-attribute-detection#ran","syntology_url":"https://syntology.ai/paper/2211.12914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12914"}},"official":{"repos":["OVAD-Benchmark/ovad-bechmark-code"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/torchscale-transformers-at-scale","slug":"torchscale-transformers-at-scale","title":"TorchScale: Transformers at Scale","date":"2022-11-23","arxiv_id":"2211.13184","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-model-with-unlikelihood","slug":"unified-multimodal-model-with-unlikelihood","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","date":"2022-11-23","arxiv_id":"2211.13235","repositories_listed":1,"syntology":null},{"url":"/paper/converge-to-the-truth-factual-error","slug":"converge-to-the-truth-factual-error","title":"Converge to the Truth: Factual Error Correction via Iterative Constrained Editing","date":"2022-11-22","arxiv_id":"2211.12130","repositories_listed":1,"syntology":null},{"url":"/paper/coreference-resolution-through-a-seq2seq","slug":"coreference-resolution-through-a-seq2seq","title":"Coreference Resolution through a seq2seq Transition-Based System","date":"2022-11-22","arxiv_id":"2211.12142","repositories_listed":1,"syntology":null},{"url":"/paper/human-level-play-in-the-game-of-diplomacy-by","slug":"human-level-play-in-the-game-of-diplomacy-by","title":"Human-level play in the game of Diplomacy by combining language models with strategic reasoning","date":"2022-11-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mariancg-a-code-generation-transformer-model","slug":"mariancg-a-code-generation-transformer-model","title":"MarianCG: a code generation transformer model inspired by machine translation","date":"2022-11-22","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/enhancing-crisis-related-tweet-classification","slug":"enhancing-crisis-related-tweet-classification","title":"Enhancing Crisis-Related Tweet Classification with Entity-Masked Language Modeling and Multi-Task Learning","date":"2022-11-21","arxiv_id":"2211.11468","repositories_listed":1,"syntology":null},{"url":"/paper/multi-level-knowledge-distillation-for-out-of","slug":"multi-level-knowledge-distillation-for-out-of","title":"Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text","date":"2022-11-21","arxiv_id":"2211.11300","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/multi-level-knowledge-distillation-for-out-of#ran","syntology_url":"https://syntology.ai/paper/2211.11300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11300"}},"official":{"repos":["microsoft/KC"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/perceiver-vl-efficient-vision-and-language","slug":"perceiver-vl-efficient-vision-and-language","title":"Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention","date":"2022-11-21","arxiv_id":"2211.11701","repositories_listed":1,"syntology":null},{"url":"/paper/validating-large-language-models-with-relm","slug":"validating-large-language-models-with-relm","title":"Validating Large Language Models with ReLM","date":"2022-11-21","arxiv_id":"2211.15458","repositories_listed":1,"syntology":null},{"url":"/paper/you-need-multiple-exiting-dynamic-early","slug":"you-need-multiple-exiting-dynamic-early","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","date":"2022-11-21","arxiv_id":"2211.11152","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-fine-grained-information-via","slug":"modeling-fine-grained-information-via","title":"Modeling Fine-grained Information via Knowledge-aware Hierarchical Graph for Zero-shot Entity Retrieval","date":"2022-11-20","arxiv_id":"2211.10991","repositories_listed":1,"syntology":null},{"url":"/paper/abinet-autonomous-bidirectional-and-iterative","slug":"abinet-autonomous-bidirectional-and-iterative","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","date":"2022-11-19","arxiv_id":"2211.10578","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graph-generation-from-text","slug":"knowledge-graph-generation-from-text","title":"Knowledge Graph Generation From Text","date":"2022-11-18","arxiv_id":"2211.10511","repositories_listed":1,"syntology":null},{"url":"/paper/protein-language-model-rescue-mutations","slug":"protein-language-model-rescue-mutations","title":"Protein language model rescue mutations highlight variant effects and structure in clinically relevant genes","date":"2022-11-18","arxiv_id":"2211.10000","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/protein-language-model-rescue-mutations#ran","syntology_url":"https://syntology.ai/paper/2211.10000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10000"}},"official":{"repos":["dimenwarper/llm-for-clinical-variants"],"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/ignore-previous-prompt-attack-techniques-for","slug":"ignore-previous-prompt-attack-techniques-for","title":"Ignore Previous Prompt: Attack Techniques For Language Models","date":"2022-11-17","arxiv_id":"2211.09527","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"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 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) · 4 unverified","sample_list":"/paper/ignore-previous-prompt-attack-techniques-for#ran","syntology_url":"https://syntology.ai/paper/2211.09527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09527"}},"official":{"repos":["agencyenterprise/promptinject"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/controllable-citation-text-generation","slug":"controllable-citation-text-generation","title":"Controllable Citation Sentence Generation with Language Models","date":"2022-11-14","arxiv_id":"2211.07066","repositories_listed":1,"syntology":null},{"url":"/paper/replacing-language-model-for-style-transfer","slug":"replacing-language-model-for-style-transfer","title":"Replacing Language Model for Style Transfer","date":"2022-11-14","arxiv_id":"2211.07343","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-classifier-aligns-better-with","slug":"language-model-classifier-aligns-better-with","title":"Language Model Classifier Aligns Better with Physician Word Sensitivity than XGBoost on Readmission Prediction","date":"2022-11-13","arxiv_id":"2211.07047","repositories_listed":1,"syntology":null},{"url":"/paper/xu-at-semeval-2022-task-4-pre-bert-neural-1","slug":"xu-at-semeval-2022-task-4-pre-bert-neural-1","title":"Xu at SemEval-2022 Task 4: Pre-BERT Neural Network Methods vs Post-BERT RoBERTa Approach for Patronizing and Condescending Language Detection","date":"2022-11-13","arxiv_id":"2211.06874","repositories_listed":1,"syntology":null},{"url":"/paper/multi-epoch-matrix-factorization-mechanisms","slug":"multi-epoch-matrix-factorization-mechanisms","title":"Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning","date":"2022-11-12","arxiv_id":"2211.06530","repositories_listed":1,"syntology":null},{"url":"/paper/lert-a-linguistically-motivated-pre-trained","slug":"lert-a-linguistically-motivated-pre-trained","title":"LERT: A Linguistically-motivated Pre-trained Language Model","date":"2022-11-10","arxiv_id":"2211.05344","repositories_listed":1,"syntology":null},{"url":"/paper/msdt-masked-language-model-scoring-defense-in","slug":"msdt-masked-language-model-scoring-defense-in","title":"MSDT: Masked Language Model Scoring Defense in Text Domain","date":"2022-11-10","arxiv_id":"2211.05371","repositories_listed":1,"syntology":null},{"url":"/paper/nano-nested-human-in-the-loop-reward-learning","slug":"nano-nested-human-in-the-loop-reward-learning","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","date":"2022-11-10","arxiv_id":"2211.05750","repositories_listed":1,"syntology":null},{"url":"/paper/third-party-aligner-for-neural-word","slug":"third-party-aligner-for-neural-word","title":"Third-Party Aligner for Neural Word Alignments","date":"2022-11-08","arxiv_id":"2211.04198","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/afrolm-a-self-active-learning-based","slug":"afrolm-a-self-active-learning-based","title":"AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages","date":"2022-11-07","arxiv_id":"2211.03263","repositories_listed":1,"syntology":null},{"url":"/paper/ax-mabsa-a-framework-for-extremely-weakly","slug":"ax-mabsa-a-framework-for-extremely-weakly","title":"AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis","date":"2022-11-07","arxiv_id":"2211.03837","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-fairness-disparities-in-peer","slug":"investigating-fairness-disparities-in-peer","title":"Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach","date":"2022-11-07","arxiv_id":"2211.06398","repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-textual-similarity-via","slug":"learning-semantic-textual-similarity-via","title":"Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables","date":"2022-11-07","arxiv_id":"2211.03616","repositories_listed":1,"syntology":null},{"url":"/paper/suffix-retrieval-augmented-language-modeling","slug":"suffix-retrieval-augmented-language-modeling","title":"Suffix Retrieval-Augmented Language Modeling","date":"2022-11-06","arxiv_id":"2211.03053","repositories_listed":1,"syntology":null},{"url":"/paper/kglm-integrating-knowledge-graph-structure-in","slug":"kglm-integrating-knowledge-graph-structure-in","title":"KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction","date":"2022-11-04","arxiv_id":"2211.02744","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kglm-integrating-knowledge-graph-structure-in#ran","syntology_url":"https://syntology.ai/paper/2211.02744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.02744"}},"official":{"repos":["ibpa/kglm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/contextual-information-integration-for-stance","slug":"contextual-information-integration-for-stance","title":"Contextual information integration for stance detection via cross-attention","date":"2022-11-03","arxiv_id":"2211.01874","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-the-carbon-footprint-of-bloom-a","slug":"estimating-the-carbon-footprint-of-bloom-a","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","date":"2022-11-03","arxiv_id":"2211.02001","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-language-models-via-epistemic","slug":"fine-tuning-language-models-via-epistemic","title":"Fine-Tuning Language Models via Epistemic Neural Networks","date":"2022-11-03","arxiv_id":"2211.01568","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/fine-tuning-language-models-via-epistemic#ran","syntology_url":"https://syntology.ai/paper/2211.01568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01568"}},"official":{"repos":["deepmind/neural_testbed"],"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/fine-tuning-pre-trained-language-models","slug":"fine-tuning-pre-trained-language-models","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","date":"2022-11-03","arxiv_id":"2211.01642","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 1 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) · 1 unverified","sample_list":"/paper/fine-tuning-pre-trained-language-models#ran","syntology_url":"https://syntology.ai/paper/2211.01642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.01642"}},"official":{"repos":["zhanghaojie077/dps"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lmentry-a-language-model-benchmark-of","slug":"lmentry-a-language-model-benchmark-of","title":"LMentry: A Language Model Benchmark of Elementary Language Tasks","date":"2022-11-03","arxiv_id":"2211.02069","repositories_listed":1,"syntology":null},{"url":"/paper/overcoming-barriers-to-skill-injection-in","slug":"overcoming-barriers-to-skill-injection-in","title":"Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic","date":"2022-11-03","arxiv_id":"2211.02098","repositories_listed":1,"syntology":null},{"url":"/paper/data2vec-aqc-search-for-the-right-teaching","slug":"data2vec-aqc-search-for-the-right-teaching","title":"data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setup","date":"2022-11-02","arxiv_id":"2211.01246","repositories_listed":1,"syntology":null},{"url":"/paper/improving-variational-autoencoders-with","slug":"improving-variational-autoencoders-with","title":"Improving Variational Autoencoders with Density Gap-based Regularization","date":"2022-11-01","arxiv_id":"2211.00321","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/improving-variational-autoencoders-with#ran","syntology_url":"https://syntology.ai/paper/2211.00321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.00321"}},"official":{"repos":["zhangjf-nlp/dg-vaes"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-solve-voxel-building-embodied","slug":"learning-to-solve-voxel-building-embodied","title":"Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions","date":"2022-11-01","arxiv_id":"2211.00688","repositories_listed":1,"syntology":null},{"url":"/paper/t5lephone-bridging-speech-and-text-self","slug":"t5lephone-bridging-speech-and-text-self","title":"T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5","date":"2022-11-01","arxiv_id":"2211.00586","repositories_listed":1,"syntology":null},{"url":"/paper/1cademy-causal-news-corpus-2022-enhance","slug":"1cademy-causal-news-corpus-2022-enhance","title":"1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector","date":"2022-10-31","arxiv_id":"2210.17157","repositories_listed":1,"syntology":null},{"url":"/paper/blank-collapse-compressing-ctc-emission-for","slug":"blank-collapse-compressing-ctc-emission-for","title":"Blank Collapse: Compressing CTC emission for the faster decoding","date":"2022-10-31","arxiv_id":"2210.17017","repositories_listed":1,"syntology":null},{"url":"/paper/codeeditor-learning-to-edit-source-code-with","slug":"codeeditor-learning-to-edit-source-code-with","title":"CodeEditor: Learning to Edit Source Code with Pre-trained Models","date":"2022-10-31","arxiv_id":"2210.17040","repositories_listed":1,"syntology":null},{"url":"/paper/improving-temporal-generalization-of-pre","slug":"improving-temporal-generalization-of-pre","title":"Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change","date":"2022-10-31","arxiv_id":"2210.17127","repositories_listed":1,"syntology":null},{"url":"/paper/l-greco-an-efficient-and-general-framework","slug":"l-greco-an-efficient-and-general-framework","title":"L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning","date":"2022-10-31","arxiv_id":"2210.17357","repositories_listed":1,"syntology":null},{"url":"/paper/when-flue-meets-flang-benchmarks-and-large","slug":"when-flue-meets-flang-benchmarks-and-large","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","date":"2022-10-31","arxiv_id":"2211.00083","repositories_listed":1,"syntology":null},{"url":"/paper/when-language-model-meets-private-library","slug":"when-language-model-meets-private-library","title":"When Language Model Meets Private Library","date":"2022-10-31","arxiv_id":"2210.17236","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-data-augmentation-for","slug":"differentiable-data-augmentation-for","title":"Differentiable Data Augmentation for Contrastive Sentence Representation Learning","date":"2022-10-29","arxiv_id":"2210.16536","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":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) · 1 unverified","sample_list":"/paper/differentiable-data-augmentation-for#ran","syntology_url":"https://syntology.ai/paper/2210.16536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16536"}},"official":{"repos":["tianduowang/diffaug"],"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/leveraging-label-correlations-in-a-multi","slug":"leveraging-label-correlations-in-a-multi","title":"Leveraging Label Correlations in a Multi-label Setting: A Case Study in Emotion","date":"2022-10-28","arxiv_id":"2210.15842","repositories_listed":1,"syntology":null},{"url":"/paper/rochbert-towards-robust-bert-fine-tuning-for","slug":"rochbert-towards-robust-bert-fine-tuning-for","title":"RoChBert: Towards Robust BERT Fine-tuning for Chinese","date":"2022-10-28","arxiv_id":"2210.15944","repositories_listed":1,"syntology":null},{"url":"/paper/you-can-t-pick-your-neighbors-or-can-you-when","slug":"you-can-t-pick-your-neighbors-or-can-you-when","title":"You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM","date":"2022-10-28","arxiv_id":"2210.15859","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/you-can-t-pick-your-neighbors-or-can-you-when#ran","syntology_url":"https://syntology.ai/paper/2210.15859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15859"}},"official":{"repos":["iesl/knnlm-retrieval-quality"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/coco-dr-combating-distribution-shifts-in-zero","slug":"coco-dr-combating-distribution-shifts-in-zero","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","date":"2022-10-27","arxiv_id":"2210.15212","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/coco-dr-combating-distribution-shifts-in-zero#ran","syntology_url":"https://syntology.ai/paper/2210.15212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15212"}},"official":{"repos":["openmatch/coco-dr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-oriented-masking-pre-training","slug":"retrieval-oriented-masking-pre-training","title":"Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval","date":"2022-10-27","arxiv_id":"2210.15133","repositories_listed":1,"syntology":null},{"url":"/paper/truncation-sampling-as-language-model","slug":"truncation-sampling-as-language-model","title":"Truncation Sampling as Language Model Desmoothing","date":"2022-10-27","arxiv_id":"2210.15191","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/truncation-sampling-as-language-model#ran","syntology_url":"https://syntology.ai/paper/2210.15191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15191"}},"official":{"repos":["john-hewitt/truncation-sampling"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-language-model-to-train-if-you-have-one","slug":"what-language-model-to-train-if-you-have-one","title":"What Language Model to Train if You Have One Million GPU Hours?","date":"2022-10-27","arxiv_id":"2210.15424","repositories_listed":1,"syntology":null},{"url":"/paper/a-robust-bias-mitigation-procedure-based-on","slug":"a-robust-bias-mitigation-procedure-based-on","title":"A Robust Bias Mitigation Procedure Based on the Stereotype Content Model","date":"2022-10-26","arxiv_id":"2210.14552","repositories_listed":1,"syntology":null},{"url":"/paper/inducer-tuning-connecting-prefix-tuning-and","slug":"inducer-tuning-connecting-prefix-tuning-and","title":"Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning","date":"2022-10-26","arxiv_id":"2210.14469","repositories_listed":1,"syntology":null},{"url":"/paper/residual-learning-of-neural-text-generation","slug":"residual-learning-of-neural-text-generation","title":"$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model","date":"2022-10-26","arxiv_id":"2210.14431","repositories_listed":1,"syntology":null},{"url":"/paper/will-we-run-out-of-data-an-analysis-of-the","slug":"will-we-run-out-of-data-an-analysis-of-the","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","date":"2022-10-26","arxiv_id":"2211.04325","repositories_listed":1,"syntology":null},{"url":"/paper/a-single-cell-gene-expression-language-model","slug":"a-single-cell-gene-expression-language-model","title":"A single-cell gene expression language model","date":"2022-10-25","arxiv_id":"2210.14330","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/a-single-cell-gene-expression-language-model#ran","syntology_url":"https://syntology.ai/paper/2210.14330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14330"}},"official":{"repos":["keiserlab/exceiver"],"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"]}}},{"url":"/paper/help-me-write-a-poem-instruction-tuning-as-a","slug":"help-me-write-a-poem-instruction-tuning-as-a","title":"Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing","date":"2022-10-25","arxiv_id":"2210.13669","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/help-me-write-a-poem-instruction-tuning-as-a#ran","syntology_url":"https://syntology.ai/paper/2210.13669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13669"}},"official":{"repos":["vishakhpk/creative-instructions"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/how-long-is-enough-exploring-the-optimal","slug":"how-long-is-enough-exploring-the-optimal","title":"How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling","date":"2022-10-25","arxiv_id":"2211.07713","repositories_listed":1,"syntology":null},{"url":"/paper/memonet-memorizing-representations-of-all","slug":"memonet-memorizing-representations-of-all","title":"MemoNet: Memorizing All Cross Features' Representations Efficiently via Multi-Hash Codebook Network for CTR Prediction","date":"2022-10-25","arxiv_id":"2211.01334","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-text-generation-with-differential","slug":"synthetic-text-generation-with-differential","title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe","date":"2022-10-25","arxiv_id":"2210.14348","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/synthetic-text-generation-with-differential#ran","syntology_url":"https://syntology.ai/paper/2210.14348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.14348"}},"official":{"repos":["microsoft/dp-transformers"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"39ae90fb98a1e482e3fe9934179e3c76de08ea454a1ef9635a25467c1391611d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}