{"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/weight-decay/papers/58","list_of":"/method/weight-decay","method":"Weight Decay","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":58,"pages_in_order":108,"rows_per_page":100,"rows":[5701,5800],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/weight-decay","prev":"/method/weight-decay/papers/57","next":"/method/weight-decay/papers/59","papers":[{"paper":null,"slug":"promptcap-prompt-guided-image-captioning-for","title":"PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3","date":"2023-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-with-retrieval-faithful-large","slug":"rethinking-with-retrieval-faithful-large","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","date":"2022-12-31","arxiv_id":"2301.00303","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-covid-19-public","title":"Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method","date":"2022-12-31","arxiv_id":"2301.00096","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-attention-via-the-lens-of","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","date":"2022-12-30","arxiv_id":"2212.14852","n_code_links":0,"syntology":null},{"paper":null,"slug":"distant-reading-of-the-german-coalition-deal","title":"Distant Reading of the German Coalition Deal: Recognizing Policy Positions with BERT-based Text Classification","date":"2022-12-30","arxiv_id":"2212.14648","n_code_links":0,"syntology":null},{"paper":null,"slug":"targeted-phishing-campaigns-using-large-scale","title":"Targeted Phishing Campaigns using Large Scale Language Models","date":"2022-12-30","arxiv_id":"2301.00665","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-takes-the-bar-exam","slug":"gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","n_code_links":5,"syntology":null},{"paper":null,"slug":"maximizing-use-case-specificity-through","title":"Maximizing Use-Case Specificity through Precision Model Tuning","date":"2022-12-29","arxiv_id":"2212.14206","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-geometry-of-reinforcement-learning-in","title":"On the Geometry of Reinforcement Learning in Continuous State and Action Spaces","date":"2022-12-29","arxiv_id":"2301.00009","n_code_links":0,"syntology":null},{"paper":"/paper/cramming-training-a-language-model-on-a","slug":"cramming-training-a-language-model-on-a","title":"Cramming: Training a Language Model on a Single GPU in One Day","date":"2022-12-28","arxiv_id":"2212.14034","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jonasgeiping/cramming"],"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"]}}},{"paper":null,"slug":"a-survey-on-knowledge-enhanced-pre-trained","title":"A Survey on Knowledge-Enhanced Pre-trained Language Models","date":"2022-12-27","arxiv_id":"2212.13428","n_code_links":0,"syntology":null},{"paper":"/paper/deepcuts-single-shot-interpretability-based","slug":"deepcuts-single-shot-interpretability-based","title":"DeepCuts: Single-Shot Interpretability based Pruning for BERT","date":"2022-12-27","arxiv_id":"2212.13392","n_code_links":1,"syntology":null},{"paper":null,"slug":"tegformer-topic-to-essay-generation-with-good","title":"TegFormer: Topic-to-Essay Generation with Good Topic Coverage and High Text Coherence","date":"2022-12-27","arxiv_id":"2212.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-to-generate","title":"Using Large Language Models to Generate Engaging Captions for Data Visualizations","date":"2022-12-27","arxiv_id":"2212.14047","n_code_links":0,"syntology":null},{"paper":null,"slug":"biologically-inspired-design-concept","title":"Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers","date":"2022-12-26","arxiv_id":"2212.13196","n_code_links":0,"syntology":null},{"paper":"/paper/benchmark-for-uncertainty-robustness-in-self","slug":"benchmark-for-uncertainty-robustness-in-self","title":"Benchmark for Uncertainty & Robustness in Self-Supervised Learning","date":"2022-12-23","arxiv_id":"2212.12411","n_code_links":1,"syntology":null},{"paper":"/paper/finetuning-for-sarcasm-detection-with-a","slug":"finetuning-for-sarcasm-detection-with-a","title":"Finetuning for Sarcasm Detection with a Pruned Dataset","date":"2022-12-23","arxiv_id":"2212.12213","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-does-surprisal-from-larger-transformer","title":"Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?","date":"2022-12-23","arxiv_id":"2212.12131","n_code_links":0,"syntology":null},{"paper":null,"slug":"camembert-cascading-assistant-mediated","title":"CAMeMBERT: Cascading Assistant-Mediated Multilingual BERT","date":"2022-12-22","arxiv_id":"2212.11456","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-the-prediction-of-disease-outcomes","title":"Enhancing the prediction of disease outcomes using electronic health records and pretrained deep learning models","date":"2022-12-22","arxiv_id":"2212.12067","n_code_links":0,"syntology":null},{"paper":"/paper/analyzing-semantic-faithfulness-of-language","slug":"analyzing-semantic-faithfulness-of-language","title":"Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering","date":"2022-12-21","arxiv_id":"2212.10696","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-emotion-modelling-in-written","slug":"automatic-emotion-modelling-in-written","title":"Automatic Emotion Modelling in Written Stories","date":"2022-12-21","arxiv_id":"2212.11382","n_code_links":1,"syntology":null},{"paper":"/paper/cross-linguistic-syntactic-difference-in","slug":"cross-linguistic-syntactic-difference-in","title":"Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?","date":"2022-12-21","arxiv_id":"2212.10879","n_code_links":1,"syntology":null},{"paper":"/paper/entropy-and-distance-based-predictors-from","slug":"entropy-and-distance-based-predictors-from","title":"Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal","date":"2022-12-21","arxiv_id":"2212.11185","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["byungdoh/attn_dist"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"jasmine-arabic-gpt-models-for-few-shot","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","date":"2022-12-21","arxiv_id":"2212.10755","n_code_links":0,"syntology":null},{"paper":null,"slug":"kl-regularized-normalization-framework-for","title":"KL Regularized Normalization Framework for Low Resource Tasks","date":"2022-12-21","arxiv_id":"2212.11275","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-visual-simplification-of","title":"Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks","date":"2022-12-21","arxiv_id":"2212.10774","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-twitter-bert-approach-for-offensive","title":"A Twitter BERT Approach for Offensive Language Detection in Marathi","date":"2022-12-20","arxiv_id":"2212.10039","n_code_links":0,"syntology":null},{"paper":"/paper/bygpt5-end-to-end-style-conditioned-poetry","slug":"bygpt5-end-to-end-style-conditioned-poetry","title":"ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models","date":"2022-12-20","arxiv_id":"2212.10474","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["potamides/uniformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"controllable-text-generation-with-language","title":"Controllable Text Generation with Language Constraints","date":"2022-12-20","arxiv_id":"2212.10466","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-have-coherent-mental","slug":"do-language-models-have-coherent-mental","title":"Do language models have coherent mental models of everyday things?","date":"2022-12-20","arxiv_id":"2212.10029","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["allenai/everyday-things"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":"/paper/docasref-a-pilot-empirical-study-on","slug":"docasref-a-pilot-empirical-study-on","title":"DocAsRef: An Empirical Study on Repurposing Reference-Based Summary Quality Metrics Reference-Freely","date":"2022-12-20","arxiv_id":"2212.10013","n_code_links":1,"syntology":null},{"paper":null,"slug":"generic-temporal-reasoning-with-differential","title":"Generic Temporal Reasoning with Differential Analysis and Explanation","date":"2022-12-20","arxiv_id":"2212.10467","n_code_links":0,"syntology":null},{"paper":null,"slug":"go-tuning-improving-zero-shot-learning","title":"Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models","date":"2022-12-20","arxiv_id":"2212.10461","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-rule-neural-coreference-resolution","title":"Hybrid Rule-Neural Coreference Resolution System based on Actor-Critic Learning","date":"2022-12-20","arxiv_id":"2212.10087","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-and-manipulating-the-personality","title":"Identifying and Manipulating the Personality Traits of Language Models","date":"2022-12-20","arxiv_id":"2212.10276","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-and-out-of-domain-text-adversarial","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","date":"2022-12-20","arxiv_id":"2212.10258","n_code_links":0,"syntology":null},{"paper":"/paper/is-gpt-3-a-good-data-annotator","slug":"is-gpt-3-a-good-data-annotator","title":"Is GPT-3 a Good Data Annotator?","date":"2022-12-20","arxiv_id":"2212.10450","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-gpt-3-a-psychopath-evaluating-large","title":"Evaluating Psychological Safety of Large Language Models","date":"2022-12-20","arxiv_id":"2212.10529","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-reasoning-teachers","slug":"large-language-models-are-reasoning-teachers","title":"Large Language Models Are Reasoning Teachers","date":"2022-12-20","arxiv_id":"2212.10071","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["itsnamgyu/reasoning-teacher"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pairreranker-pairwise-reranking-for-natural","title":"PairReranker: Pairwise Reranking for Natural Language Generation","date":"2022-12-20","arxiv_id":"2212.10555","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-efficient-zero-shot-transfer-for","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","date":"2022-12-20","arxiv_id":"2212.10448","n_code_links":0,"syntology":null},{"paper":"/paper/pay-attention-to-your-tone-introducing-a-new","slug":"pay-attention-to-your-tone-introducing-a-new","title":"Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite","date":"2022-12-20","arxiv_id":"2212.10190","n_code_links":1,"syntology":null},{"paper":"/paper/pretraining-without-attention","slug":"pretraining-without-attention","title":"Pretraining Without Attention","date":"2022-12-20","arxiv_id":"2212.10544","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jxiw/bigs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"true-detective-a-challenging-benchmark-for","title":"True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4","date":"2022-12-20","arxiv_id":"2212.10114","n_code_links":0,"syntology":null},{"paper":"/paper/why-can-gpt-learn-in-context-language-models","slug":"why-can-gpt-learn-in-context-language-models","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","date":"2022-12-20","arxiv_id":"2212.10559","n_code_links":1,"syntology":null},{"paper":"/paper/do-conll-2003-named-entity-taggers-still-work","slug":"do-conll-2003-named-entity-taggers-still-work","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","date":"2022-12-19","arxiv_id":"2212.09747","n_code_links":1,"syntology":null},{"paper":"/paper/emergent-analogical-reasoning-in-large","slug":"emergent-analogical-reasoning-in-large","title":"Emergent Analogical Reasoning in Large Language Models","date":"2022-12-19","arxiv_id":"2212.09196","n_code_links":2,"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":["taylorwwebb/emergent_analogies_llm"],"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":"enriching-relation-extraction-with-openie","title":"Enriching Relation Extraction with OpenIE","date":"2022-12-19","arxiv_id":"2212.09376","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-human-language-model-interaction","slug":"evaluating-human-language-model-interaction","title":"Evaluating Human-Language Model Interaction","date":"2022-12-19","arxiv_id":"2212.09746","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-reasoners-with-self","slug":"large-language-models-are-reasoners-with-self","title":"Large Language Models are Better Reasoners with Self-Verification","date":"2022-12-19","arxiv_id":"2212.09561","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["WENGSYX/Self-Verification"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/lens-a-learnable-evaluation-metric-for-text","slug":"lens-a-learnable-evaluation-metric-for-text","title":"LENS: A Learnable Evaluation Metric for Text Simplification","date":"2022-12-19","arxiv_id":"2212.09739","n_code_links":1,"syntology":null},{"paper":null,"slug":"less-is-more-parameter-free-text","title":"Less is More: Parameter-Free Text Classification with Gzip","date":"2022-12-19","arxiv_id":"2212.09410","n_code_links":0,"syntology":null},{"paper":null,"slug":"mantis-at-tsar-2022-shared-task-improved","title":"MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders","date":"2022-12-19","arxiv_id":"2212.09855","n_code_links":0,"syntology":null},{"paper":"/paper/reasoning-with-language-model-prompting-a","slug":"reasoning-with-language-model-prompting-a","title":"Reasoning with Language Model Prompting: A Survey","date":"2022-12-19","arxiv_id":"2212.09597","n_code_links":2,"syntology":null},{"paper":"/paper/the-case-for-4-bit-precision-k-bit-inference","slug":"the-case-for-4-bit-precision-k-bit-inference","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","date":"2022-12-19","arxiv_id":"2212.09720","n_code_links":1,"syntology":null},{"paper":"/paper/bort-towards-explainable-neural-networks-with","slug":"bort-towards-explainable-neural-networks-with","title":"Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint","date":"2022-12-18","arxiv_id":"2212.09062","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["zbr17/bort"],"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"]}}},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-coreference-resolution-based-on","title":"Neural Coreference Resolution based on Reinforcement Learning","date":"2022-12-18","arxiv_id":"2212.09028","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-rankers-for-effective-screening","title":"Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search","date":"2022-12-18","arxiv_id":"2212.09017","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploiting-rich-textual-user-product-context","title":"Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis","date":"2022-12-17","arxiv_id":"2212.08888","n_code_links":0,"syntology":null},{"paper":null,"slug":"legalrelectra-mixed-domain-language-modeling","title":"LegalRelectra: Mixed-domain Language Modeling for Long-range Legal Text Comprehension","date":"2022-12-16","arxiv_id":"2212.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"murmur-modular-multi-step-reasoning-for-semi","title":"MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation","date":"2022-12-16","arxiv_id":"2212.08607","n_code_links":0,"syntology":null},{"paper":null,"slug":"plansformer-generating-symbolic-plans-using","title":"Plansformer: Generating Symbolic Plans using Transformers","date":"2022-12-16","arxiv_id":"2212.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"poibert-a-transformer-based-model-for-the","title":"POIBERT: A Transformer-based Model for the Tour Recommendation Problem","date":"2022-12-16","arxiv_id":"2212.13900","n_code_links":0,"syntology":null},{"paper":null,"slug":"preventing-rnn-from-using-sequence-length-as","title":"Preventing RNN from Using Sequence Length as a Feature","date":"2022-12-16","arxiv_id":"2212.08276","n_code_links":0,"syntology":null},{"paper":"/paper/reco-reliable-causal-chain-reasoning-via","slug":"reco-reliable-causal-chain-reasoning-via","title":"ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks","date":"2022-12-16","arxiv_id":"2212.08322","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":6,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["waste-wood/reco"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-prompting-large-language-models-for-open","slug":"self-prompting-large-language-models-for-open","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","date":"2022-12-16","arxiv_id":"2212.08635","n_code_links":1,"syntology":null},{"paper":null,"slug":"utilizing-distilbert-transformer-model-for","title":"Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses","date":"2022-12-16","arxiv_id":"2212.08407","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","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"]}}},{"paper":"/paper/revisiting-the-gold-standard-grounding","slug":"revisiting-the-gold-standard-grounding","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","date":"2022-12-15","arxiv_id":"2212.07981","n_code_links":2,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["yale-lily/rose"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/visually-augmented-pretrained-language-models","slug":"visually-augmented-pretrained-language-models","title":"Visually-augmented pretrained language models for NLP tasks without images","date":"2022-12-15","arxiv_id":"2212.07937","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-self-supervised-learning-with","slug":"efficient-self-supervised-learning-with","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","date":"2022-12-14","arxiv_id":"2212.07525","n_code_links":5,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["facebookresearch/fairseq"],"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":"explainability-of-text-processing-and","title":"Explainability of Text Processing and Retrieval Methods: A Critical Survey","date":"2022-12-14","arxiv_id":"2212.07126","n_code_links":0,"syntology":null},{"paper":"/paper/pac-man-multi-relation-network-in-social","slug":"pac-man-multi-relation-network-in-social","title":"PAC-MAN: Multi-Relation Network in Social Community for Personalized Hashtag Recommendation","date":"2022-12-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/crepe-can-vision-language-foundation-models","slug":"crepe-can-vision-language-foundation-models","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","date":"2022-12-13","arxiv_id":"2212.07796","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["raivnlab/crepe"],"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":null,"slug":"paraphrase-identification-with-deep-learning","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","date":"2022-12-13","arxiv_id":"2212.06933","n_code_links":0,"syntology":null},{"paper":"/paper/a-pre-trained-bert-model-for-android","slug":"a-pre-trained-bert-model-for-android","title":"DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecode","date":"2022-12-12","arxiv_id":"2212.05976","n_code_links":1,"syntology":null},{"paper":"/paper/classifying-the-ideological-orientation-of","slug":"classifying-the-ideological-orientation-of","title":"Classifying the Ideological Orientation of User-Submitted Texts in Social Media","date":"2022-12-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"off-policy-deep-reinforcement-learning-1","title":"Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks","date":"2022-12-11","arxiv_id":"2212.05572","n_code_links":0,"syntology":null},{"paper":"/paper/elixir-train-a-large-language-model-on-a","slug":"elixir-train-a-large-language-model-on-a","title":"Elixir: Train a Large Language Model on a Small GPU Cluster","date":"2022-12-10","arxiv_id":"2212.05339","n_code_links":2,"syntology":null},{"paper":null,"slug":"machine-intuition-uncovering-human-like","title":"Thinking Fast and Slow in Large Language Models","date":"2022-12-10","arxiv_id":"2212.05206","n_code_links":0,"syntology":null},{"paper":"/paper/punctuation-restoration-for-singaporean","slug":"punctuation-restoration-for-singaporean","title":"Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin","date":"2022-12-10","arxiv_id":"2212.05356","n_code_links":1,"syntology":null},{"paper":null,"slug":"structured-information-extraction-from","title":"Structured information extraction from complex scientific text with fine-tuned large language models","date":"2022-12-10","arxiv_id":"2212.05238","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-emotions-into-health-mention","slug":"incorporating-emotions-into-health-mention","title":"Incorporating Emotions into Health Mention Classification Task on Social Media","date":"2022-12-09","arxiv_id":"2212.05039","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-turing-deception","title":"The Turing Deception","date":"2022-12-09","arxiv_id":"2212.06721","n_code_links":0,"syntology":null},{"paper":null,"slug":"trbllmaker-transformer-reads-between-lyrics","title":"TRBLLmaker -- Transformer Reads Between Lyrics Lines maker","date":"2022-12-09","arxiv_id":"2212.04917","n_code_links":0,"syntology":null},{"paper":"/paper/explain-to-me-like-i-am-five-sentence","slug":"explain-to-me-like-i-am-five-sentence","title":"Explain to me like I am five -- Sentence Simplification Using Transformers","date":"2022-12-08","arxiv_id":"2212.04595","n_code_links":1,"syntology":null},{"paper":"/paper/llm-planner-few-shot-grounded-planning-for","slug":"llm-planner-few-shot-grounded-planning-for","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","date":"2022-12-08","arxiv_id":"2212.04088","n_code_links":1,"syntology":null},{"paper":"/paper/np4g-network-programming-for-generalization","slug":"np4g-network-programming-for-generalization","title":"NP4G : Network Programming for Generalization","date":"2022-12-08","arxiv_id":"2212.11118","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-role-of-ai-in-drug-discovery-challenges","title":"The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies","date":"2022-12-08","arxiv_id":"2212.08104","n_code_links":0,"syntology":null},{"paper":"/paper/a-study-on-extracting-named-entities-from","slug":"a-study-on-extracting-named-entities-from","title":"Memorization of Named Entities in Fine-tuned BERT Models","date":"2022-12-07","arxiv_id":"2212.03749","n_code_links":1,"syntology":null},{"paper":"/paper/deepspeed-data-efficiency-improving-deep","slug":"deepspeed-data-efficiency-improving-deep","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","date":"2022-12-07","arxiv_id":"2212.03597","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-embed-adopting-transformer-based","title":"Learning-To-Embed: Adopting Transformer based models for E-commerce Products Representation Learning","date":"2022-12-07","arxiv_id":"2212.03725","n_code_links":0,"syntology":null},{"paper":"/paper/simvtp-simple-video-text-pre-training-with","slug":"simvtp-simple-video-text-pre-training-with","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","date":"2022-12-07","arxiv_id":"2212.03490","n_code_links":0,"syntology":null},{"paper":null,"slug":"tweetdrought-a-deep-learning-drought-impacts","title":"TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data","date":"2022-12-07","arxiv_id":"2212.04001","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-testing-of-computer-vision-models","slug":"adaptive-testing-of-computer-vision-models","title":"Adaptive Testing of Computer Vision Models","date":"2022-12-06","arxiv_id":"2212.02774","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"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) · 2 unverified","official":{"repos":["i-gao/adavision"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/counterfactual-reasoning-do-language-models","slug":"counterfactual-reasoning-do-language-models","title":"Counterfactual reasoning: Do language models need world knowledge for causal understanding?","date":"2022-12-06","arxiv_id":"2212.03278","n_code_links":1,"syntology":null},{"paper":null,"slug":"cysecbert-a-domain-adapted-language-model-for","title":"CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain","date":"2022-12-06","arxiv_id":"2212.02974","n_code_links":0,"syntology":null},{"paper":null,"slug":"enabling-and-accelerating-dynamic-vision","title":"Vision Transformer Computation and Resilience for Dynamic Inference","date":"2022-12-06","arxiv_id":"2212.02687","n_code_links":0,"syntology":null}],"record_sha256":"683c846facb1ff917f1f31337bd729d48cd0056c6884679eaedd8d0ff8f231a4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}