{"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":"/method/discriminative-fine-tuning/papers/18","list_of":"/method/discriminative-fine-tuning","method":"Discriminative Fine-Tuning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":18,"pages_in_order":20,"rows_per_page":100,"rows":[1701,1800],"of":1990,"counts":{"archive_papers_tagged":1990,"with_a_code_link":794,"where_syntology_ran_a_sample":271,"not_listed_spam_title":0,"listed":1990,"listed_where_code_ran":271,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":223,"every_run_a_failure_of_syntologys_instrument":48,"listed_with_a_run_with_no_instrument_failure":223,"listed_every_run_a_failure_of_syntologys_instrument":48,"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":"/method/discriminative-fine-tuning","prev":"/method/discriminative-fine-tuning/papers/17","next":"/method/discriminative-fine-tuning/papers/19","papers":[{"paper":null,"slug":"rockgpt-reconstructing-three-dimensional","title":"RockGPT: Reconstructing three-dimensional digital rocks from single two-dimensional slice from the perspective of video generation","date":"2021-08-05","arxiv_id":"2108.03132","n_code_links":0,"syntology":null},{"paper":"/paper/q-pain-a-question-answering-dataset-to","slug":"q-pain-a-question-answering-dataset-to","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","date":"2021-08-03","arxiv_id":"2108.01764","n_code_links":0,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-making-high-accuracy-non","title":"Best of Both Worlds: Making High Accuracy Non-incremental Transformer-based Disfluency Detection Incremental","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/employing-argumentation-knowledge-graphs-for","slug":"employing-argumentation-knowledge-graphs-for","title":"Employing Argumentation Knowledge Graphs for Neural Argument Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/explanations-for-commonsenseqa-new-dataset","slug":"explanations-for-commonsenseqa-new-dataset","title":"Explanations for CommonsenseQA: New Dataset and Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"kuileixi-a-chinese-open-ended-text-adventure","title":"KuiLeiXi: a Chinese Open-Ended Text Adventure Game","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pral-a-tailored-pre-training-model-for-task","title":"PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tgea-an-error-annotated-dataset-and-benchmark","title":"TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"unleash-gpt-2-power-for-event-detection","title":"Unleash GPT-2 Power for Event Detection","date":"2021-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-gpt-gpt-2-and-bert-language-models","title":"Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition","date":"2021-07-29","arxiv_id":"2108.07789","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-ulmfit-and-self-distillation-with","title":"Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System","date":"2021-07-20","arxiv_id":"2107.09625","n_code_links":0,"syntology":null},{"paper":"/paper/chimera-efficiently-training-large-scale","slug":"chimera-efficiently-training-large-scale","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","date":"2021-07-14","arxiv_id":"2107.06925","n_code_links":1,"syntology":null},{"paper":"/paper/scalable-memory-protection-in-the-penglai","slug":"scalable-memory-protection-in-the-penglai","title":"Scalable Memory Protection in the PENGLAI Enclave","date":"2021-07-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-trained-on","slug":"evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","arxiv_id":"2107.03374","n_code_links":13,"syntology":{"ran":26,"of":39,"n_ran_checked":24,"n_instrument":2,"unverified":13,"pointer_only":4,"phrase":"26 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","official":{"repos":["openai/human-eval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["found_in_text","listed","official"]}}},{"paper":null,"slug":"scarecrow-a-framework-for-scrutinizing","title":"Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text","date":"2021-07-02","arxiv_id":"2107.01294","n_code_links":0,"syntology":null},{"paper":"/paper/symbolicgpt-a-generative-transformer-model","slug":"symbolicgpt-a-generative-transformer-model","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","date":"2021-06-27","arxiv_id":"2106.14131","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["git.uwaterloo.ca/data-analytics-lab/symbolicgpt2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"toward-less-hidden-cost-of-code-completion","title":"Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models","date":"2021-06-26","arxiv_id":"2106.13928","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-transformer-based-framework-on","title":"Pre-training transformer-based framework on large-scale pediatric claims data for downstream population-specific tasks","date":"2021-06-24","arxiv_id":"2106.13095","n_code_links":0,"syntology":null},{"paper":"/paper/lora-low-rank-adaptation-of-large-language","slug":"lora-low-rank-adaptation-of-large-language","title":"LoRA: Low-Rank Adaptation of Large Language Models","date":"2021-06-17","arxiv_id":"2106.09685","n_code_links":74,"syntology":{"ran":51,"of":84,"n_ran_checked":44,"n_instrument":7,"unverified":33,"pointer_only":30,"phrase":"51 ran (of which 19 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 7 where Syntology's instrument failed) · 33 unverified","official":{"repos":["microsoft/LoRA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"textual-data-distributions-kullback-leibler","title":"Textual Data Distributions: Kullback Leibler Textual Distributions Contrasts on GPT-2 Generated Texts, with Supervised, Unsupervised Learning on Vaccine & Market Topics & Sentiment","date":"2021-06-15","arxiv_id":"2107.02025","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-models-past-present-and-future","title":"Pre-Trained Models: Past, Present and Future","date":"2021-06-14","arxiv_id":"2106.07139","n_code_links":0,"syntology":null},{"paper":"/paper/generate-annotate-and-learn-generative-models","slug":"generate-annotate-and-learn-generative-models","title":"Generate, Annotate, and Learn: NLP with Synthetic Text","date":"2021-06-11","arxiv_id":"2106.06168","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["xlhex/gal_syntex"],"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"]}}},{"paper":null,"slug":"engines-of-power-electricity-ai-and-general","title":"Engines of Power: Electricity, AI, and General-Purpose Military Transformations","date":"2021-06-08","arxiv_id":"2106.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-syntactic-probes-probe-syntax-experiments","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","date":"2021-06-04","arxiv_id":"2106.02559","n_code_links":0,"syntology":null},{"paper":null,"slug":"auto-tagging-of-short-conversational","title":"Auto-tagging of Short Conversational Sentences using Transformer Methods","date":"2021-06-03","arxiv_id":"2106.01735","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-comprehensive-understanding-and","title":"Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers","date":"2021-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-adversarial-imitation-learning-for","title":"Generative Adversarial Imitation Learning for Empathy-based AI","date":"2021-05-27","arxiv_id":"2105.13328","n_code_links":0,"syntology":null},{"paper":"/paper/data-curation-and-quality-assurance-for","slug":"data-curation-and-quality-assurance-for","title":"Data Curation and Quality Assurance for Machine Learning-based Cyber Intrusion Detection","date":"2021-05-20","arxiv_id":"2105.10041","n_code_links":1,"syntology":null},{"paper":"/paper/methods-for-detoxification-of-texts-for-the","slug":"methods-for-detoxification-of-texts-for-the","title":"Methods for Detoxification of Texts for the Russian Language","date":"2021-05-19","arxiv_id":"2105.09052","n_code_links":3,"syntology":null},{"paper":null,"slug":"neural-predictive-text-for-grammatical-error","title":"Neural Predictive Text for Grammatical Error Prevention","date":"2021-05-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/slgpt-using-transfer-learning-to-directly","slug":"slgpt-using-transfer-learning-to-directly","title":"SLGPT: Using Transfer Learning to Directly Generate Simulink Model Files and Find Bugs in the Simulink Toolchain","date":"2021-05-16","arxiv_id":"2105.07465","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-busters-outlier-layernorm-dimensions","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","date":"2021-05-14","arxiv_id":"2105.06990","n_code_links":0,"syntology":null},{"paper":"/paper/bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","slug":"bert-is-to-nlp-what-alexnet-is-to-cv-can-pre","title":"BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?","date":"2021-05-11","arxiv_id":"2105.04949","n_code_links":1,"syntology":null},{"paper":"/paper/el-attention-memory-efficient-lossless","slug":"el-attention-memory-efficient-lossless","title":"EL-Attention: Memory Efficient Lossless Attention for Generation","date":"2021-05-11","arxiv_id":"2105.04779","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/fastseq"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","slug":"e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","arxiv_id":"2105.03761","n_code_links":2,"syntology":{"ran":7,"of":15,"n_ran_checked":6,"n_instrument":1,"unverified":8,"pointer_only":15,"phrase":"7 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["maximek3/e-ViL"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"mitigating-political-bias-in-language-models","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","date":"2021-04-30","arxiv_id":"2104.14795","n_code_links":0,"syntology":null},{"paper":null,"slug":"extractive-and-abstractive-explanations-for","title":"Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News","date":"2021-04-27","arxiv_id":"2104.12918","n_code_links":0,"syntology":null},{"paper":null,"slug":"uot-uwf-partai-at-semeval-2021-task-5-self","title":"UoT-UWF-PartAI at SemEval-2021 Task 5: Self Attention Based Bi-GRU with Multi-Embedding Representation for Toxicity Highlighter","date":"2021-04-27","arxiv_id":"2104.13164","n_code_links":0,"syntology":null},{"paper":null,"slug":"accounting-for-agreement-phenomena-in","title":"Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention","date":"2021-04-26","arxiv_id":"2104.12874","n_code_links":0,"syntology":null},{"paper":"/paper/easy-and-efficient-transformer-scalable","slug":"easy-and-efficient-transformer-scalable","title":"Easy and Efficient Transformer : Scalable Inference Solution For large NLP model","date":"2021-04-26","arxiv_id":"2104.12470","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-covid-19-tweets-with-transformer","title":"Analyzing COVID-19 Tweets with Transformer-based Language Models","date":"2021-04-20","arxiv_id":"2104.10259","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-pre-training-objectives-for","title":"Efficient pre-training objectives for Transformers","date":"2021-04-20","arxiv_id":"2104.09694","n_code_links":0,"syntology":null},{"paper":"/paper/surface-form-competition-why-the-highest","slug":"surface-form-competition-why-the-highest","title":"Surface Form Competition: Why the Highest Probability Answer Isn't Always Right","date":"2021-04-16","arxiv_id":"2104.08315","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["peterwestuw/surface-form-competition"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/nareor-the-narrative-reordering-problem","slug":"nareor-the-narrative-reordering-problem","title":"NAREOR: The Narrative Reordering Problem","date":"2021-04-14","arxiv_id":"2104.06669","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-transformers-for-bot-detection","slug":"understanding-transformers-for-bot-detection","title":"Understanding Transformers for Bot Detection in Twitter","date":"2021-04-13","arxiv_id":"2104.06182","n_code_links":1,"syntology":null},{"paper":"/paper/whose-heritage-classification-of-unesco-world","slug":"whose-heritage-classification-of-unesco-world","title":"WHOSe Heritage: Classification of UNESCO World Heritage \"Outstanding Universal Value\" Documents with Soft Labels","date":"2021-04-12","arxiv_id":"2104.05547","n_code_links":1,"syntology":null},{"paper":null,"slug":"ki-bert-infusing-knowledge-context-for-better","title":"KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding","date":"2021-04-09","arxiv_id":"2104.08145","n_code_links":0,"syntology":null},{"paper":"/paper/knowledge-aware-graph-enhanced-gpt-2-for","slug":"knowledge-aware-graph-enhanced-gpt-2-for","title":"Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking","date":"2021-04-09","arxiv_id":"2104.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-2-to-create-synthetic-data-to","title":"Using GPT-2 to Create Synthetic Data to Improve the Prediction Performance of NLP Machine Learning Classification Models","date":"2021-04-02","arxiv_id":"2104.10658","n_code_links":0,"syntology":null},{"paper":null,"slug":"thinking-aloud-dynamic-context-generation","title":"Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2","date":"2021-03-24","arxiv_id":"2103.13033","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nlp-cookbook-modern-recipes-for","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","date":"2021-03-23","arxiv_id":"2104.10640","n_code_links":0,"syntology":null},{"paper":"/paper/l3cubemahasent-a-marathi-tweet-based","slug":"l3cubemahasent-a-marathi-tweet-based","title":"L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset","date":"2021-03-21","arxiv_id":"2103.11408","n_code_links":1,"syntology":null},{"paper":null,"slug":"play-the-shannon-game-with-language-models-a","title":"Play the Shannon Game With Language Models: A Human-Free Approach to Summary Evaluation","date":"2021-03-19","arxiv_id":"2103.10918","n_code_links":0,"syntology":null},{"paper":"/paper/all-nlp-tasks-are-generation-tasks-a-general","slug":"all-nlp-tasks-are-generation-tasks-a-general","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","date":"2021-03-18","arxiv_id":"2103.10360","n_code_links":8,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["THUDM/GLM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/gpt-understands-too","slug":"gpt-understands-too","title":"GPT Understands, Too","date":"2021-03-18","arxiv_id":"2103.10385","n_code_links":10,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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","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"]}}},{"paper":"/paper/language-models-have-a-moral-dimension","slug":"language-models-have-a-moral-dimension","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","date":"2021-03-08","arxiv_id":"2103.11790","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["ml-research/MoRT_NMI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decomposing-lexical-and-compositional-syntax","title":"Disentangling Syntax and Semantics in the Brain with Deep Networks","date":"2021-03-02","arxiv_id":"2103.01620","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-document-summarization-in-a-low-resource","title":"Long Document Summarization in a Low Resource Setting using Pretrained Language Models","date":"2021-03-01","arxiv_id":"2103.00751","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-universal-language-model-to-downstream","title":"From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection","date":"2021-02-24","arxiv_id":"2102.12162","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-transferable-anomaly-detection-in","title":"Robust and Transferable Anomaly Detection in Log Data using Pre-Trained Language Models","date":"2021-02-23","arxiv_id":"2102.11570","n_code_links":0,"syntology":null},{"paper":null,"slug":"theaitre-1-0-interactive-generation-of","title":"THEaiTRE 1.0: Interactive generation of theatre play scripts","date":"2021-02-17","arxiv_id":"2102.08892","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-transformers-in-natural-language","slug":"exploring-transformers-in-natural-language","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","date":"2021-02-16","arxiv_id":"2102.08036","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-corruptive-force-of-ai-generated-advice","title":"The corruptive force of AI-generated advice","date":"2021-02-15","arxiv_id":"2102.07536","n_code_links":0,"syntology":null},{"paper":"/paper/augpt-dialogue-with-pre-trained-language","slug":"augpt-dialogue-with-pre-trained-language","title":"AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models","date":"2021-02-09","arxiv_id":"2102.05126","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-hybrid-task-oriented-dialog-system-with","title":"A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining","date":"2021-02-08","arxiv_id":"2102.04506","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-fake-cyber-threat-intelligence","title":"Generating Fake Cyber Threat Intelligence Using Transformer-Based Models","date":"2021-02-08","arxiv_id":"2102.04351","n_code_links":0,"syntology":null},{"paper":"/paper/how-true-is-gpt-2-an-empirical-analysis-of","slug":"how-true-is-gpt-2-an-empirical-analysis-of","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","date":"2021-02-08","arxiv_id":"2102.04130","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oxai/intersectional_gpt2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"jointly-improving-language-understanding-and","title":"Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling","date":"2021-02-06","arxiv_id":"2102.03551","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-data-to-text-generation-with-lm-based","title":"Neural Data-to-Text Generation with LM-based Text Augmentation","date":"2021-02-06","arxiv_id":"2102.03556","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesizing-monolingual-data-for-neural","title":"Synthesizing Monolingual Data for Neural Machine Translation","date":"2021-01-29","arxiv_id":"2101.12462","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-transformer-model-for-detecting-arabic","title":"BERT Transformer model for Detecting Arabic GPT2 Auto-Generated Tweets","date":"2021-01-22","arxiv_id":"2101.09345","n_code_links":0,"syntology":null},{"paper":"/paper/towards-facilitating-empathic-conversations","slug":"towards-facilitating-empathic-conversations","title":"Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach","date":"2021-01-19","arxiv_id":"2101.07714","n_code_links":1,"syntology":null},{"paper":null,"slug":"experimental-evaluation-of-deep-learning","title":"Experimental Evaluation of Deep Learning models for Marathi Text Classification","date":"2021-01-13","arxiv_id":"2101.04899","n_code_links":0,"syntology":null},{"paper":"/paper/ladiff-ulmfit-a-layer-differentiated-training","slug":"ladiff-ulmfit-a-layer-differentiated-training","title":"LaDiff ULMFiT: A Layer Differentiated training approach for ULMFiT","date":"2021-01-13","arxiv_id":"2101.04965","n_code_links":1,"syntology":null},{"paper":null,"slug":"adding-recurrence-to-pretrained-transformers-1","title":"Adding Recurrence to Pretrained Transformers","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ketg-a-knowledge-enhanced-text-generation","title":"KETG: A Knowledge Enhanced Text Generation Framework","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/polyjuice-automated-general-purpose","slug":"polyjuice-automated-general-purpose","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","date":"2021-01-01","arxiv_id":"2101.00288","n_code_links":1,"syntology":null},{"paper":"/paper/prefix-tuning-optimizing-continuous-prompts","slug":"prefix-tuning-optimizing-continuous-prompts","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","date":"2021-01-01","arxiv_id":"2101.00190","n_code_links":13,"syntology":{"ran":4,"of":6,"n_ran_checked":2,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["XiangLi1999/PrefixTuning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"pretrain-knowledge-aware-language-models","title":"Pretrain Knowledge-Aware Language Models","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-generation-of-temporally-ordered","title":"Conditional Generation of Temporally-ordered Event Sequences","date":"2020-12-31","arxiv_id":"2012.15786","n_code_links":0,"syntology":null},{"paper":"/paper/directed-beam-search-plug-and-play-lexically","slug":"directed-beam-search-plug-and-play-lexically","title":"Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation","date":"2020-12-31","arxiv_id":"2012.15416","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["dapascual/DirectedBeamSearch"],"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"]}}},{"paper":"/paper/the-pile-an-800gb-dataset-of-diverse-text-for","slug":"the-pile-an-800gb-dataset-of-diverse-text-for","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","date":"2020-12-31","arxiv_id":"2101.00027","n_code_links":22,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["EleutherAI/The-Pile"],"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"]}}},{"paper":"/paper/robust-dialogue-utterance-rewriting-as","slug":"robust-dialogue-utterance-rewriting-as","title":"Robust Dialogue Utterance Rewriting as Sequence Tagging","date":"2020-12-29","arxiv_id":"2012.14535","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-and-surprisal-jointly-deliver-the","title":"Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition","date":"2020-12-22","arxiv_id":"2012.12007","n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-and-contextualised-writing-tool","title":"Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models","date":"2020-12-19","arxiv_id":"2101.03216","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-expansion-with-artificially-generated","title":"Query expansion with artificially generated texts","date":"2020-12-16","arxiv_id":"2012.08787","n_code_links":0,"syntology":null},{"paper":"/paper/recipenlg-a-cooking-recipes-dataset-for-semi","slug":"recipenlg-a-cooking-recipes-dataset-for-semi","title":"RecipeNLG: A Cooking Recipes Dataset for Semi-Structured Text Generation","date":"2020-12-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/extracting-training-data-from-large-language","slug":"extracting-training-data-from-large-language","title":"Extracting Training Data from Large Language Models","date":"2020-12-14","arxiv_id":"2012.07805","n_code_links":3,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ftramer/LM_Memorization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/as-good-as-new-how-to-successfully-recycle","slug":"as-good-as-new-how-to-successfully-recycle","title":"As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages","date":"2020-12-10","arxiv_id":"2012.05628","n_code_links":1,"syntology":null},{"paper":"/paper/towards-neural-programming-interfaces-1","slug":"towards-neural-programming-interfaces-1","title":"Towards Neural Programming Interfaces","date":"2020-12-10","arxiv_id":"2012.05983","n_code_links":1,"syntology":null},{"paper":"/paper/cx-db8-a-queryable-extractive-summarizer-and","slug":"cx-db8-a-queryable-extractive-summarizer-and","title":"CX DB8: A queryable extractive summarizer and semantic search engine","date":"2020-12-07","arxiv_id":"2012.03942","n_code_links":2,"syntology":null},{"paper":"/paper/ubar-towards-fully-end-to-end-task-oriented","slug":"ubar-towards-fully-end-to-end-task-oriented","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","date":"2020-12-07","arxiv_id":"2012.03539","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhanced-offensive-language-detection-through","title":"Enhanced Offensive Language Detection Through Data Augmentation","date":"2020-12-05","arxiv_id":"2012.02954","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-pretrained-transformers-towards","title":"RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation","date":"2020-12-04","arxiv_id":"2012.02469","n_code_links":0,"syntology":null},{"paper":"/paper/how-can-we-know-when-language-models-know","slug":"how-can-we-know-when-language-models-know","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","date":"2020-12-02","arxiv_id":"2012.00955","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-deep-generative-approach-to-native-language","title":"A Deep Generative Approach to Native Language Identification","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-probabilistic-distributional-and","title":"Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hinglishnlp-at-semeval-2020-task-9-fine-tuned","slug":"hinglishnlp-at-semeval-2020-task-9-fine-tuned","title":"HinglishNLP at SemEval-2020 Task 9: Fine-tuned Language Models for Hinglish Sentiment Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-11-an-empirical","title":"Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hitachi-at-semeval-2020-task-7-stacking-at","title":"Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humor Recognition","date":"2020-12-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"7551c07b7e32f562f08710cb93beca6856e511605091df2ecf6c67b89ddabd37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}