{"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/glu/papers/5","list_of":"/method/glu","method":"Gated Linear Unit","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":5,"pages_in_order":8,"rows_per_page":100,"rows":[401,500],"of":798,"counts":{"archive_papers_tagged":798,"with_a_code_link":400,"where_syntology_ran_a_sample":115,"not_listed_spam_title":0,"listed":798,"listed_where_code_ran":115,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":99,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":99,"listed_every_run_a_failure_of_syntologys_instrument":16,"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/glu","prev":"/method/glu/papers/4","next":"/method/glu/papers/6","papers":[{"paper":null,"slug":"synthesis-of-mathematical-programs-from","title":"Synthesis of Mathematical programs from Natural Language Specifications","date":"2023-03-30","arxiv_id":"2304.03287","n_code_links":0,"syntology":null},{"paper":null,"slug":"summarizing-indian-languages-using","title":"Summarizing Indian Languages using Multilingual Transformers based Models","date":"2023-03-29","arxiv_id":"2303.16657","n_code_links":0,"syntology":null},{"paper":"/paper/explicit-planning-helps-language-models-in","slug":"explicit-planning-helps-language-models-in","title":"Explicit Planning Helps Language Models in Logical Reasoning","date":"2023-03-28","arxiv_id":"2303.15714","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cindermond/explicit-planning-for-reasoning","cindermond/leap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/neuralmind-unicamp-at-2022-trec-neuclir-large","slug":"neuralmind-unicamp-at-2022-trec-neuclir-large","title":"NeuralMind-UNICAMP at 2022 TREC NeuCLIR: Large Boring Rerankers for Cross-lingual Retrieval","date":"2023-03-28","arxiv_id":"2303.16145","n_code_links":1,"syntology":null},{"paper":"/paper/one-adapter-for-all-programming-languages","slug":"one-adapter-for-all-programming-languages","title":"One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization","date":"2023-03-28","arxiv_id":"2303.15822","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-generation-of-multiple-choice","title":"Automatic Generation of Multiple-Choice Questions","date":"2023-03-25","arxiv_id":"2303.14576","n_code_links":0,"syntology":null},{"paper":"/paper/dblp-quad-a-question-answering-dataset-over","slug":"dblp-quad-a-question-answering-dataset-over","title":"DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph","date":"2023-03-23","arxiv_id":"2303.13351","n_code_links":1,"syntology":null},{"paper":"/paper/gett-qa-graph-embedding-based-t2t-transformer","slug":"gett-qa-graph-embedding-based-t2t-transformer","title":"GETT-QA: Graph Embedding based T2T Transformer for Knowledge Graph Question Answering","date":"2023-03-23","arxiv_id":"2303.13284","n_code_links":1,"syntology":null},{"paper":"/paper/open-source-frame-semantic-parsing","slug":"open-source-frame-semantic-parsing","title":"Open-source Frame Semantic Parsing","date":"2023-03-22","arxiv_id":"2303.12788","n_code_links":1,"syntology":null},{"paper":"/paper/bangla-grammatical-error-detection-using-t5","slug":"bangla-grammatical-error-detection-using-t5","title":"Bangla Grammatical Error Detection Using T5 Transformer Model","date":"2023-03-19","arxiv_id":"2303.10612","n_code_links":2,"syntology":null},{"paper":null,"slug":"exploring-distributional-shifts-in-large","title":"Exploring Distributional Shifts in Large Language Models for Code Analysis","date":"2023-03-16","arxiv_id":"2303.09128","n_code_links":0,"syntology":null},{"paper":"/paper/typet5-seq2seq-type-inference-using-static","slug":"typet5-seq2seq-type-inference-using-static","title":"TypeT5: Seq2seq Type Inference using Static Analysis","date":"2023-03-16","arxiv_id":"2303.09564","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["utopia-group/typet5"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/presto-a-multilingual-dataset-for-parsing","slug":"presto-a-multilingual-dataset-for-parsing","title":"PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs","date":"2023-03-15","arxiv_id":"2303.08954","n_code_links":1,"syntology":null},{"paper":"/paper/proactive-prioritization-of-app-issues-via","slug":"proactive-prioritization-of-app-issues-via","title":"Proactive Prioritization of App Issues via Contrastive Learning","date":"2023-03-12","arxiv_id":"2303.06586","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-ai-generated","slug":"a-comprehensive-survey-of-ai-generated","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","date":"2023-03-07","arxiv_id":"2303.04226","n_code_links":1,"syntology":null},{"paper":null,"slug":"spelling-convention-sensitivity-in-neural","title":"Spelling convention sensitivity in neural language models","date":"2023-03-06","arxiv_id":"2303.03457","n_code_links":0,"syntology":null},{"paper":null,"slug":"n-best-t5-robust-asr-error-correction-using","title":"N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space","date":"2023-03-01","arxiv_id":"2303.00456","n_code_links":0,"syntology":null},{"paper":"/paper/are-character-level-translations-worth-the","slug":"are-character-level-translations-worth-the","title":"Are Character-level Translations Worth the Wait? Comparing ByT5 and mT5 for Machine Translation","date":"2023-02-28","arxiv_id":"2302.14220","n_code_links":1,"syntology":null},{"paper":null,"slug":"tiny-classifier-circuits-evolving","title":"Tiny Classifier Circuits: Evolving Accelerators for Tabular Data","date":"2023-02-28","arxiv_id":"2303.00031","n_code_links":0,"syntology":null},{"paper":"/paper/choice-fusion-as-knowledge-for-zero-shot","slug":"choice-fusion-as-knowledge-for-zero-shot","title":"Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking","date":"2023-02-25","arxiv_id":"2302.13013","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-based-learning-for-text-readability","slug":"prompt-based-learning-for-text-readability","title":"Prompt-based Learning for Text Readability Assessment","date":"2023-02-25","arxiv_id":"2302.13139","n_code_links":1,"syntology":null},{"paper":"/paper/does-deep-learning-learn-to-abstract-a","slug":"does-deep-learning-learn-to-abstract-a","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","date":"2023-02-23","arxiv_id":"2302.11978","n_code_links":1,"syntology":null},{"paper":"/paper/vlsp-2022-evjvqa-challenge-multilingual","slug":"vlsp-2022-evjvqa-challenge-multilingual","title":"EVJVQA Challenge: Multilingual Visual Question Answering","date":"2023-02-23","arxiv_id":"2302.11752","n_code_links":0,"syntology":null},{"paper":"/paper/bbt-fin-comprehensive-construction-of-chinese","slug":"bbt-fin-comprehensive-construction-of-chinese","title":"BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model, Corpus and Benchmark","date":"2023-02-18","arxiv_id":"2302.09432","n_code_links":2,"syntology":null},{"paper":"/paper/pac-prediction-sets-for-large-language-models","slug":"pac-prediction-sets-for-large-language-models","title":"PAC Prediction Sets for Large Language Models of Code","date":"2023-02-17","arxiv_id":"2302.08703","n_code_links":1,"syntology":null},{"paper":null,"slug":"commonsense-reasoning-for-conversational-ai-a","title":"Commonsense Reasoning for Conversational AI: A Survey of the State of the Art","date":"2023-02-15","arxiv_id":"2302.07926","n_code_links":0,"syntology":null},{"paper":null,"slug":"few-shot-learning-approaches-for-classifying","title":"Few-shot learning approaches for classifying low resource domain specific software requirements","date":"2023-02-14","arxiv_id":"2302.06951","n_code_links":0,"syntology":null},{"paper":null,"slug":"linguistic-ambiguity-analysis-in-chatgpt","title":"Linguistic ambiguity analysis in ChatGPT","date":"2023-02-13","arxiv_id":"2302.06426","n_code_links":0,"syntology":null},{"paper":null,"slug":"street-a-multi-task-structured-reasoning-and","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","date":"2023-02-13","arxiv_id":"2302.06729","n_code_links":0,"syntology":null},{"paper":"/paper/controllable-lexical-simplification-for","slug":"controllable-lexical-simplification-for","title":"Controllable Lexical Simplification for English","date":"2023-02-06","arxiv_id":"2302.02900","n_code_links":1,"syntology":null},{"paper":null,"slug":"idt5-indonesian-version-of-multilingual-t5","title":"idT5: Indonesian Version of Multilingual T5 Transformer","date":"2023-02-02","arxiv_id":"2302.00856","n_code_links":0,"syntology":null},{"paper":"/paper/hunsum-1-an-abstractive-summarization-dataset","slug":"hunsum-1-an-abstractive-summarization-dataset","title":"HunSum-1: an Abstractive Summarization Dataset for Hungarian","date":"2023-02-01","arxiv_id":"2302.00455","n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-a-small-language-model-for-spreadsheet","title":"FLAME: A small language model for spreadsheet formulas","date":"2023-01-31","arxiv_id":"2301.13779","n_code_links":0,"syntology":null},{"paper":"/paper/the-flan-collection-designing-data-and","slug":"the-flan-collection-designing-data-and","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","date":"2023-01-31","arxiv_id":"2301.13688","n_code_links":1,"syntology":null},{"paper":"/paper/specializing-smaller-language-models-towards","slug":"specializing-smaller-language-models-towards","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","date":"2023-01-30","arxiv_id":"2301.12726","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["FranxYao/FlanT5-CoT-Specialization"],"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/progressive-prompts-continual-learning-for","slug":"progressive-prompts-continual-learning-for","title":"Progressive Prompts: Continual Learning for Language Models","date":"2023-01-29","arxiv_id":"2301.12314","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["arazd/ProgressivePrompts"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/schema-guided-semantic-accuracy-faithfulness","slug":"schema-guided-semantic-accuracy-faithfulness","title":"Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation","date":"2023-01-29","arxiv_id":"2301.12568","n_code_links":1,"syntology":null},{"paper":"/paper/bipol-multi-axes-evaluation-of-bias-with","slug":"bipol-multi-axes-evaluation-of-bias-with","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","date":"2023-01-28","arxiv_id":"2301.12139","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-stability-analysis-of-fine-tuning-a-pre","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","date":"2023-01-24","arxiv_id":"2301.09820","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-instruction-based-prompting-for","title":"Multitask Instruction-based Prompting for Fallacy Recognition","date":"2023-01-24","arxiv_id":"2301.09992","n_code_links":0,"syntology":null},{"paper":"/paper/graphix-t5-mixing-pre-trained-transformers","slug":"graphix-t5-mixing-pre-trained-transformers","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","date":"2023-01-18","arxiv_id":"2301.07507","n_code_links":1,"syntology":null},{"paper":"/paper/there-is-no-big-brother-or-small-brother","slug":"there-is-no-big-brother-or-small-brother","title":"There is No Big Brother or Small Brother: Knowledge Infusion in Language Models for Link Prediction and Question Answering","date":"2023-01-10","arxiv_id":"2301.04013","n_code_links":2,"syntology":null},{"paper":null,"slug":"conditional-generation-of-paired-antibody","title":"Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model","date":"2023-01-06","arxiv_id":"2301.02748","n_code_links":0,"syntology":null},{"paper":"/paper/extending-source-code-pre-trained-language","slug":"extending-source-code-pre-trained-language","title":"Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries","date":"2023-01-04","arxiv_id":"2301.01701","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-based-geocoding","title":"Transformer Based Geocoding","date":"2023-01-02","arxiv_id":"2301.01170","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-inconsistencies-of-conditionals","slug":"on-the-inconsistencies-of-conditionals","title":"Inconsistencies in Masked Language Models","date":"2022-12-30","arxiv_id":"2301.00068","n_code_links":1,"syntology":null},{"paper":null,"slug":"error-syntax-aware-augmentation-of-feedback","title":"Error syntax aware augmentation of feedback comment generation dataset","date":"2022-12-29","arxiv_id":"2212.14293","n_code_links":0,"syntology":null},{"paper":"/paper/uncontrolled-lexical-exposure-leads-to","slug":"uncontrolled-lexical-exposure-leads-to","title":"Uncontrolled Lexical Exposure Leads to Overestimation of Compositional Generalization in Pretrained Models","date":"2022-12-21","arxiv_id":"2212.10769","n_code_links":1,"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":"/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":null,"slug":"krona-parameter-efficient-tuning-with","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","date":"2022-12-20","arxiv_id":"2212.10650","n_code_links":0,"syntology":null},{"paper":null,"slug":"receptive-field-alignment-enables-transformer","title":"Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis","date":"2022-12-20","arxiv_id":"2212.10356","n_code_links":0,"syntology":null},{"paper":"/paper/t-projection-high-quality-annotation","slug":"t-projection-high-quality-annotation","title":"T-Projection: High Quality Annotation Projection for Sequence Labeling Tasks","date":"2022-12-20","arxiv_id":"2212.10548","n_code_links":2,"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":null,"slug":"miga-a-unified-multi-task-generation","title":"MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL","date":"2022-12-19","arxiv_id":"2212.09278","n_code_links":0,"syntology":null},{"paper":null,"slug":"mu-2-slam-multitask-multilingual-speech-and","title":"Mu$^{2}$SLAM: Multitask, Multilingual Speech and Language Models","date":"2022-12-19","arxiv_id":"2212.09553","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-sequence-to-sequence-models-for","title":"Multilingual Sequence-to-Sequence Models for Hebrew NLP","date":"2022-12-19","arxiv_id":"2212.09682","n_code_links":0,"syntology":null},{"paper":null,"slug":"teaching-small-language-models-to-reason","title":"Teaching Small Language Models to Reason","date":"2022-12-16","arxiv_id":"2212.08410","n_code_links":0,"syntology":null},{"paper":"/paper/fido-fusion-in-decoder-optimized-for-stronger","slug":"fido-fusion-in-decoder-optimized-for-stronger","title":"FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference","date":"2022-12-15","arxiv_id":"2212.08153","n_code_links":0,"syntology":null},{"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":null,"slug":"evaluating-byte-and-wordpiece-level-models","title":"Evaluating Byte and Wordpiece Level Models for Massively Multilingual Semantic Parsing","date":"2022-12-14","arxiv_id":"2212.07223","n_code_links":0,"syntology":null},{"paper":"/paper/t5score-discriminative-fine-tuning-of","slug":"t5score-discriminative-fine-tuning-of","title":"T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics","date":"2022-12-12","arxiv_id":"2212.05726","n_code_links":2,"syntology":null},{"paper":"/paper/sparse-upcycling-training-mixture-of-experts","slug":"sparse-upcycling-training-mixture-of-experts","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","date":"2022-12-09","arxiv_id":"2212.05055","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["google-research/vmoe"],"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":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/hierarchical-multimodal-transformers-for","slug":"hierarchical-multimodal-transformers-for","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","date":"2022-12-07","arxiv_id":"2212.05935","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlled-text-generation-using-t5-based","title":"Controlled Text Generation using T5 based Encoder-Decoder Soft Prompt Tuning and Analysis of the Utility of Generated Text in AI","date":"2022-12-06","arxiv_id":"2212.02924","n_code_links":0,"syntology":null},{"paper":null,"slug":"languages-you-know-influence-those-you-learn","title":"Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer","date":"2022-12-04","arxiv_id":"2212.01757","n_code_links":0,"syntology":null},{"paper":null,"slug":"global-memory-transformer-for-processing-long","title":"Global memory transformer for processing long documents","date":"2022-12-03","arxiv_id":"2212.01650","n_code_links":0,"syntology":null},{"paper":"/paper/data-efficient-finetuning-using-cross-task","slug":"data-efficient-finetuning-using-cross-task","title":"Data-Efficient Finetuning Using Cross-Task Nearest Neighbors","date":"2022-12-01","arxiv_id":"2212.00196","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["allenai/data-efficient-finetuning"],"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"]}}},{"paper":null,"slug":"load-profile-inpainting-for-missing-load-data","title":"Load Profile Inpainting for Missing Load Data Restoration and Baseline Estimation","date":"2022-11-29","arxiv_id":"2211.16332","n_code_links":0,"syntology":null},{"paper":null,"slug":"detect-localize-repair-a-unified-framework","title":"Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5","date":"2022-11-27","arxiv_id":"2211.14875","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"hypertuning-toward-adapting-large-language","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","date":"2022-11-22","arxiv_id":"2211.12485","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-self-consistency-and-performance-of","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","date":"2022-11-21","arxiv_id":"2211.11875","n_code_links":0,"syntology":null},{"paper":"/paper/unifiedabsa-a-unified-absa-framework-based-on","slug":"unifiedabsa-a-unified-absa-framework-based-on","title":"UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning","date":"2022-11-20","arxiv_id":"2211.10986","n_code_links":0,"syntology":null},{"paper":"/paper/glami-1m-a-multilingual-image-text-fashion-1","slug":"glami-1m-a-multilingual-image-text-fashion-1","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","date":"2022-11-17","arxiv_id":"2211.14451","n_code_links":1,"syntology":null},{"paper":"/paper/unified-question-answering-in-slovene","slug":"unified-question-answering-in-slovene","title":"Unified Question Answering in Slovene","date":"2022-11-16","arxiv_id":"2211.09159","n_code_links":1,"syntology":null},{"paper":"/paper/breakpoint-transformers-for-modeling-and","slug":"breakpoint-transformers-for-modeling-and","title":"Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs","date":"2022-11-15","arxiv_id":"2211.07950","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["allenai/situation_modeling"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"empowering-language-models-with-knowledge","title":"Empowering Language Models with Knowledge Graph Reasoning for Question Answering","date":"2022-11-15","arxiv_id":"2211.08380","n_code_links":0,"syntology":null},{"paper":"/paper/cst5-data-augmentation-for-code-switched-1","slug":"cst5-data-augmentation-for-code-switched-1","title":"CST5: Data Augmentation for Code-Switched Semantic Parsing","date":"2022-11-14","arxiv_id":"2211.07514","n_code_links":1,"syntology":null},{"paper":"/paper/technological-taxonomies-for-hypernym-and","slug":"technological-taxonomies-for-hypernym-and","title":"Technological taxonomies for hypernym and hyponym retrieval in patent texts","date":"2022-11-14","arxiv_id":"2212.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"docut5-seq2seq-sql-generation-with-table","title":"DocuT5: Seq2seq SQL Generation with Table Documentation","date":"2022-11-11","arxiv_id":"2211.06193","n_code_links":0,"syntology":null},{"paper":null,"slug":"assistive-completion-of-agrammatic-aphasic","title":"Assistive Completion of Agrammatic Aphasic Sentences: A Transfer Learning Approach using Neurolinguistics-based Synthetic Dataset","date":"2022-11-10","arxiv_id":"2211.05557","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-with-controllable","title":"Large Language Models with Controllable Working Memory","date":"2022-11-09","arxiv_id":"2211.05110","n_code_links":0,"syntology":null},{"paper":"/paper/conciseness-an-overlooked-language-task","slug":"conciseness-an-overlooked-language-task","title":"Conciseness: An Overlooked Language Task","date":"2022-11-08","arxiv_id":"2211.04126","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-multi-order-gated-aggregation","slug":"efficient-multi-order-gated-aggregation","title":"MogaNet: Multi-order Gated Aggregation Network","date":"2022-11-07","arxiv_id":"2211.03295","n_code_links":7,"syntology":{"ran":12,"of":15,"n_ran_checked":10,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/crosslingual-generalization-through-multitask","slug":"crosslingual-generalization-through-multitask","title":"Crosslingual Generalization through Multitask Finetuning","date":"2022-11-03","arxiv_id":"2211.01786","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","official":{"repos":["bigscience-workshop/xmtf"],"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"]}}},{"paper":null,"slug":"using-large-pre-trained-language-model-to","title":"Using Large Pre-Trained Language Model to Assist FDA in Premarket Medical Device","date":"2022-11-03","arxiv_id":"2212.01217","n_code_links":0,"syntology":null},{"paper":"/paper/ediffi-text-to-image-diffusion-models-with-an","slug":"ediffi-text-to-image-diffusion-models-with-an","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","date":"2022-11-02","arxiv_id":"2211.01324","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"frsum-towards-faithful-abstractive-1","title":"FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness","date":"2022-11-01","arxiv_id":"2211.00294","n_code_links":0,"syntology":null},{"paper":null,"slug":"preserving-in-context-learning-ability-in","title":"Two-stage LLM Fine-tuning with Less Specialization and More Generalization","date":"2022-11-01","arxiv_id":"2211.00635","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":"/paper/gm-tcnet-gated-multi-scale-temporal","slug":"gm-tcnet-gated-multi-scale-temporal","title":"GM-TCNet: Gated Multi-scale Temporal Convolutional Network using Emotion Causality for Speech Emotion Recognition","date":"2022-10-28","arxiv_id":"2210.15834","n_code_links":1,"syntology":null},{"paper":null,"slug":"thermal-infrared-image-inpainting-via-edge","title":"Thermal Infrared Image Inpainting via Edge-Aware Guidance","date":"2022-10-28","arxiv_id":"2210.16000","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-english-centric-bitexts-for-better","title":"Beyond English-Centric Bitexts for Better Multilingual Language Representation Learning","date":"2022-10-26","arxiv_id":"2210.14867","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-affirmative-interpretations-from","slug":"leveraging-affirmative-interpretations-from","title":"Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding","date":"2022-10-26","arxiv_id":"2210.14486","n_code_links":1,"syntology":null},{"paper":"/paper/clarinet-a-music-retrieval-system","slug":"clarinet-a-music-retrieval-system","title":"Clarinet: A Music Retrieval System","date":"2022-10-23","arxiv_id":"2210.12648","n_code_links":1,"syntology":null},{"paper":"/paper/amos-an-adam-style-optimizer-with-adaptive","slug":"amos-an-adam-style-optimizer-with-adaptive","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","date":"2022-10-21","arxiv_id":"2210.11693","n_code_links":1,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["google-research/jestimator"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/decoding-a-neural-retriever-s-latent-space","slug":"decoding-a-neural-retriever-s-latent-space","title":"Decoding a Neural Retriever's Latent Space for Query Suggestion","date":"2022-10-21","arxiv_id":"2210.12084","n_code_links":1,"syntology":null},{"paper":"/paper/sling-sino-linguistic-evaluation-of-large","slug":"sling-sino-linguistic-evaluation-of-large","title":"SLING: Sino Linguistic Evaluation of Large Language Models","date":"2022-10-21","arxiv_id":"2210.11689","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["yixiao-song/sling_data_code"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"a18b50228c5de887253426b2ca5ba3169736e85c05e0ee8cbb2652a76734d171","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}