{"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/attention-dropout/papers/58","list_of":"/method/attention-dropout","method":"Attention Dropout","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":109,"rows_per_page":100,"rows":[5701,5800],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"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/attention-dropout","prev":"/method/attention-dropout/papers/57","next":"/method/attention-dropout/papers/59","papers":[{"paper":null,"slug":"multimodal-pre-training-framework-for","title":"Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning","date":"2023-03-21","arxiv_id":"2303.11879","n_code_links":0,"syntology":null},{"paper":"/paper/sift-sparse-iso-flop-transformations-for","slug":"sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","arxiv_id":"2303.11525","n_code_links":2,"syntology":{"ran":21,"of":24,"n_ran_checked":20,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cerebrasresearch/sift","cerebrasresearch/sparse-ift"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/capabilities-of-gpt-4-on-medical-challenge","slug":"capabilities-of-gpt-4-on-medical-challenge","title":"Capabilities of GPT-4 on Medical Challenge Problems","date":"2023-03-20","arxiv_id":"2303.13375","n_code_links":1,"syntology":null},{"paper":"/paper/character-word-or-both-revisiting-the","slug":"character-word-or-both-revisiting-the","title":"Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models","date":"2023-03-20","arxiv_id":"2303.10893","n_code_links":1,"syntology":null},{"paper":null,"slug":"mind-meets-machine-unravelling-gpt-4-s","title":"Mind meets machine: Unravelling GPT-4's cognitive psychology","date":"2023-03-20","arxiv_id":"2303.11436","n_code_links":0,"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":"/paper/ctran-cnn-transformer-based-network-for","slug":"ctran-cnn-transformer-based-network-for","title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","date":"2023-03-19","arxiv_id":"2303.10606","n_code_links":1,"syntology":null},{"paper":null,"slug":"paco-provocation-involving-action-culture-and","title":"PACO: Provocation Involving Action, Culture, and Oppression","date":"2023-03-19","arxiv_id":"2303.12808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-capability-analysis-of-gpt-3","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","date":"2023-03-18","arxiv_id":"2303.10420","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-pre-trained-language","slug":"an-empirical-study-of-pre-trained-language","title":"An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering","date":"2023-03-18","arxiv_id":"2303.10368","n_code_links":1,"syntology":null},{"paper":null,"slug":"noisyhate-benchmarking-content-moderation","title":"NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models","date":"2023-03-18","arxiv_id":"2303.10430","n_code_links":0,"syntology":null},{"paper":null,"slug":"spdf-sparse-pre-training-and-dense-fine","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","date":"2023-03-18","arxiv_id":"2303.10464","n_code_links":0,"syntology":null},{"paper":"/paper/gadformer-an-attention-based-model-for-group","slug":"gadformer-an-attention-based-model-for-group","title":"GADformer: A Transparent Transformer Model for Group Anomaly Detection on Trajectories","date":"2023-03-17","arxiv_id":"2303.09841","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpts-are-gpts-an-early-look-at-the-labor","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","date":"2023-03-17","arxiv_id":"2303.10130","n_code_links":0,"syntology":null},{"paper":"/paper/trained-on-100-million-words-and-still-in","slug":"trained-on-100-million-words-and-still-in","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","date":"2023-03-17","arxiv_id":"2303.09859","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["ltgoslo/ltg-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"block-wise-bit-compression-of-transformer","title":"Block-wise Bit-Compression of Transformer-based Models","date":"2023-03-16","arxiv_id":"2303.09184","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-generative-pre-trained-transformers-gpt","title":"Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?","date":"2023-03-16","arxiv_id":"2303.09325","n_code_links":0,"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":null,"slug":"instance-conditioned-gan-data-augmentation","title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","date":"2023-03-16","arxiv_id":"2303.09677","n_code_links":0,"syntology":null},{"paper":"/paper/jump-to-conclusions-short-cutting","slug":"jump-to-conclusions-short-cutting","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","date":"2023-03-16","arxiv_id":"2303.09435","n_code_links":2,"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":["sashayd/mat"],"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":null,"slug":"measuring-improvement-of-f-1-scores-in","title":"Measuring Improvement of F$_1$-Scores in Detection of Self-Admitted Technical Debt","date":"2023-03-16","arxiv_id":"2303.09617","n_code_links":0,"syntology":null},{"paper":"/paper/smartbert-a-promotion-of-dynamic-early","slug":"smartbert-a-promotion-of-dynamic-early","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","date":"2023-03-16","arxiv_id":"2303.09266","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"towards-the-scalable-evaluation-of","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","date":"2023-03-16","arxiv_id":"2303.13360","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":null,"slug":"automated-interactive-domain-specific","title":"Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs","date":"2023-03-15","arxiv_id":"2303.08941","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-uncertainty-estimation-with","title":"Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response Retrieval","date":"2023-03-15","arxiv_id":"2303.08599","n_code_links":0,"syntology":null},{"paper":null,"slug":"gcre-gpt-a-generative-model-for-comparative","title":"GCRE-GPT: A Generative Model for Comparative Relation Extraction","date":"2023-03-15","arxiv_id":"2303.08601","n_code_links":0,"syntology":null},{"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/selfcheckgpt-zero-resource-black-box","slug":"selfcheckgpt-zero-resource-black-box","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","date":"2023-03-15","arxiv_id":"2303.08896","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["potsawee/selfcheckgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-transformers-parse-while-predicting-the","title":"Do Transformers Parse while Predicting the Masked Word?","date":"2023-03-14","arxiv_id":"2303.08117","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","n_code_links":2,"syntology":null},{"paper":null,"slug":"features-matching-using-natural-language","title":"Features matching using natural language processing","date":"2023-03-14","arxiv_id":"2303.12804","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-the-needle-in-a-haystack-unsupervised","title":"Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers","date":"2023-03-14","arxiv_id":"2303.07991","n_code_links":0,"syntology":null},{"paper":null,"slug":"medbert-de-a-comprehensive-german-bert-model","title":"MEDBERT.de: A Comprehensive German BERT Model for the Medical Domain","date":"2023-03-14","arxiv_id":"2303.08179","n_code_links":0,"syntology":null},{"paper":"/paper/neuro-symbolic-commonsense-social-reasoning","slug":"neuro-symbolic-commonsense-social-reasoning","title":"Neuro-symbolic Commonsense Social Reasoning","date":"2023-03-14","arxiv_id":"2303.08264","n_code_links":3,"syntology":null},{"paper":null,"slug":"re-move-an-adaptive-policy-design-approach","title":"RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback","date":"2023-03-14","arxiv_id":"2303.07622","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-approach-for-classifying-the","title":"Deep Learning Approach for Classifying the Aggressive Comments on Social Media: Machine Translated Data Vs Real Life Data","date":"2023-03-13","arxiv_id":"2303.07484","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-the-workplace-a-case","title":"Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification","date":"2023-03-13","arxiv_id":"2303.07142","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-approaches-to-sentiment","title":"Transformer-based approaches to Sentiment Detection","date":"2023-03-13","arxiv_id":"2303.07292","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-know-your-contextual","slug":"large-language-models-know-your-contextual","title":"Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search","date":"2023-03-12","arxiv_id":"2303.06573","n_code_links":2,"syntology":null},{"paper":"/paper/luke-graph-a-transformer-based-approach-with","slug":"luke-graph-a-transformer-based-approach-with","title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","date":"2023-03-12","arxiv_id":"2303.06675","n_code_links":0,"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":null,"slug":"learning-combinatorial-prompts-for-universal","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","date":"2023-03-11","arxiv_id":"2303.06338","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithmic-ghost-in-the-research-shell-large","title":"Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research","date":"2023-03-10","arxiv_id":"2303.07304","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-in-hospital-meta-information-useful-for","title":"Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?","date":"2023-03-10","arxiv_id":"2303.06002","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-cpi-prediction-based-on-natural","title":"Research on CPI Prediction Based on Natural Language Processing","date":"2023-03-10","arxiv_id":"2303.05666","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-may-pass-the-bar-exam-soon-but-has-a","slug":"chatgpt-may-pass-the-bar-exam-soon-but-has-a","title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","date":"2023-03-09","arxiv_id":"2304.12202","n_code_links":1,"syntology":null},{"paper":"/paper/icl-d3ie-in-context-learning-with-diverse","slug":"icl-d3ie-in-context-learning-with-diverse","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","date":"2023-03-09","arxiv_id":"2303.05063","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-struggle-to-answer","title":"Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code","date":"2023-03-09","arxiv_id":"2303.08033","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-participates-in-a-computer-science","slug":"chatgpt-participates-in-a-computer-science","title":"ChatGPT Participates in a Computer Science Exam","date":"2023-03-08","arxiv_id":"2303.09461","n_code_links":1,"syntology":null},{"paper":"/paper/cost-effective-hyperparameter-optimization","slug":"cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","date":"2023-03-08","arxiv_id":"2303.04673","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/FLAML"],"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/on-the-risks-of-stealing-the-decoding","slug":"on-the-risks-of-stealing-the-decoding","title":"Stealing the Decoding Algorithms of Language Models","date":"2023-03-08","arxiv_id":"2303.04729","n_code_links":1,"syntology":null},{"paper":"/paper/x-pruner-explainable-pruning-for-vision","slug":"x-pruner-explainable-pruning-for-vision","title":"X-Pruner: eXplainable Pruning for Vision Transformers","date":"2023-03-08","arxiv_id":"2303.04935","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":"adelt-transpilation-between-deep-learning","title":"ADELT: Transpilation Between Deep Learning Frameworks","date":"2023-03-07","arxiv_id":"2303.03593","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-text-based-conspiracy-tweets","title":"Classifying Text-Based Conspiracy Tweets related to COVID-19 using Contextualized Word Embeddings","date":"2023-03-07","arxiv_id":"2303.03706","n_code_links":0,"syntology":null},{"paper":null,"slug":"german-bert-model-for-legal-named-entity","title":"German BERT Model for Legal Named Entity Recognition","date":"2023-03-07","arxiv_id":"2303.05388","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-free-structured-pruning-with","title":"Gradient-Free Structured Pruning with Unlabeled Data","date":"2023-03-07","arxiv_id":"2303.04185","n_code_links":0,"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":"/paper/towards-zero-shot-functional-compositionality","slug":"towards-zero-shot-functional-compositionality","title":"Towards Zero-Shot Functional Compositionality of Language Models","date":"2023-03-06","arxiv_id":"2303.03103","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-question-answering-using-clip-guided","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","date":"2023-03-06","arxiv_id":"2303.03131","n_code_links":0,"syntology":null},{"paper":null,"slug":"fqp-2-0-industry-trend-analysis-via","title":"Industry Risk Assessment via Hierarchical Financial Data Using Stock Market Sentiment Indicators","date":"2023-03-05","arxiv_id":"2303.02707","n_code_links":0,"syntology":null},{"paper":"/paper/robust-affine-feature-matching-via-quadratic","slug":"robust-affine-feature-matching-via-quadratic","title":"Robust affine point matching via quadratic assignment on Grassmannians","date":"2023-03-05","arxiv_id":"2303.02698","n_code_links":3,"syntology":null},{"paper":"/paper/a-fast-training-free-compression-framework","slug":"a-fast-training-free-compression-framework","title":"Training-Free Acceleration of ViTs with Delayed Spatial Merging","date":"2023-03-04","arxiv_id":"2303.02331","n_code_links":1,"syntology":null},{"paper":null,"slug":"early-warning-signals-of-social-instabilities","title":"Early Warning Signals of Social Instabilities in Twitter Data","date":"2023-03-03","arxiv_id":"2303.05401","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-data-augmentation-methods-on-social","title":"Exploring Data Augmentation Methods on Social Media Corpora","date":"2023-03-03","arxiv_id":"2303.02198","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-label-classification-of-artificial","title":"Multi label classification of Artificial Intelligence related patents using Modified D2SBERT and Sentence Attention mechanism","date":"2023-03-03","arxiv_id":"2303.03165","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-model-representations-and-their","title":"Pre-trained Model Representations and their Robustness against Noise for Speech Emotion Analysis","date":"2023-03-03","arxiv_id":"2303.03177","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-generate-then-cache-cascade-of","slug":"prompt-generate-then-cache-cascade-of","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","date":"2023-03-03","arxiv_id":"2303.02151","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["zrrskywalker/cafo"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/prompting-large-language-models-with-answer","slug":"prompting-large-language-models-with-answer","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","date":"2023-03-03","arxiv_id":"2303.01903","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["milvlg/prophet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/trojtext-test-time-invisible-textual-trojan","slug":"trojtext-test-time-invisible-textual-trojan","title":"TrojText: Test-time Invisible Textual Trojan Insertion","date":"2023-03-03","arxiv_id":"2303.02242","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"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":["ucf-ml-research/trojtext"],"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":"will-affective-computing-emerge-from","title":"Will Affective Computing Emerge from Foundation Models and General AI? A First Evaluation on ChatGPT","date":"2023-03-03","arxiv_id":"2303.03186","n_code_links":0,"syntology":null},{"paper":null,"slug":"adopting-the-multi-answer-questioning-task","title":"Adopting the Multi-answer Questioning Task with an Auxiliary Metric for Extreme Multi-label Text Classification Utilizing the Label Hierarchy","date":"2023-03-02","arxiv_id":"2303.01064","n_code_links":0,"syntology":null},{"paper":"/paper/can-bert-refrain-from-forgetting-on","slug":"can-bert-refrain-from-forgetting-on","title":"Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study","date":"2023-03-02","arxiv_id":"2303.01081","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-parameter-efficient-transfer","slug":"evaluating-parameter-efficient-transfer","title":"Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding","date":"2023-03-02","arxiv_id":"2303.03267","n_code_links":1,"syntology":null},{"paper":"/paper/ino-at-factify-2-structure-coherence-based","slug":"ino-at-factify-2-structure-coherence-based","title":"INO at Factify 2: Structure Coherence based Multi-Modal Fact Verification","date":"2023-03-02","arxiv_id":"2303.01510","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-moe-as-the-new-dropout-scaling-dense","slug":"sparse-moe-as-the-new-dropout-scaling-dense","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","date":"2023-03-02","arxiv_id":"2303.01610","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, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vita-group/random-moe-as-dropout"],"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":"/paper/wice-real-world-entailment-for-claims-in","slug":"wice-real-world-entailment-for-claims-in","title":"WiCE: Real-World Entailment for Claims in Wikipedia","date":"2023-03-02","arxiv_id":"2303.01432","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ryokamoi/wice"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-framework-to-generate-neurosymbolic-pddl","slug":"a-framework-to-generate-neurosymbolic-pddl","title":"A Framework for Neurosymbolic Robot Action Planning using Large Language Models","date":"2023-03-01","arxiv_id":"2303.00438","n_code_links":1,"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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["alessiocpt/teriyaki"],"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":"competence-based-analysis-of-language-models","title":"Competence-Based Analysis of Language Models","date":"2023-03-01","arxiv_id":"2303.00333","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-adapted-large-language-models-for","title":"Domain-adapted large language models for classifying nuclear medicine reports","date":"2023-03-01","arxiv_id":"2303.01258","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-robust-is-gpt-3-5-to-predecessors-a","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","date":"2023-03-01","arxiv_id":"2303.00293","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":null,"slug":"toxvis-enabling-interpretability-of-implicit","title":"ToxVis: Enabling Interpretability of Implicit vs. Explicit Toxicity Detection Models with Interactive Visualization","date":"2023-03-01","arxiv_id":"2303.09402","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":"automatically-classifying-emotions-based-on","title":"Automatically Classifying Emotions based on Text: A Comparative Exploration of Different Datasets","date":"2023-02-28","arxiv_id":"2302.14727","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-summarization-via-chatgpt","title":"Zero-Shot Cross-Lingual Summarization via Large Language Models","date":"2023-02-28","arxiv_id":"2302.14229","n_code_links":0,"syntology":null},{"paper":"/paper/information-restricted-neural-language-models","slug":"information-restricted-neural-language-models","title":"Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax and Context","date":"2023-02-28","arxiv_id":"2302.14389","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["alexandrepsq/information-restrited-nlms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-are-state-of-the-art","slug":"large-language-models-are-state-of-the-art","title":"Large Language Models Are State-of-the-Art Evaluators of Translation Quality","date":"2023-02-28","arxiv_id":"2302.14520","n_code_links":4,"syntology":null},{"paper":null,"slug":"sampled-transformer-for-point-sets","title":"Sampled Transformer for Point Sets","date":"2023-02-28","arxiv_id":"2302.14346","n_code_links":0,"syntology":null},{"paper":"/paper/text-classification-dataset-and-analysis-for","slug":"text-classification-dataset-and-analysis-for","title":"Text classification dataset and analysis for Uzbek language","date":"2023-02-28","arxiv_id":"2302.14494","n_code_links":1,"syntology":null},{"paper":null,"slug":"weighted-sampling-for-masked-language","title":"Weighted Sampling for Masked Language Modeling","date":"2023-02-28","arxiv_id":"2302.14225","n_code_links":0,"syntology":null},{"paper":null,"slug":"elementwise-language-representation","title":"Elementwise Language Representation","date":"2023-02-27","arxiv_id":"2302.13475","n_code_links":0,"syntology":null},{"paper":"/paper/inseq-an-interpretability-toolkit-for","slug":"inseq-an-interpretability-toolkit-for","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","date":"2023-02-27","arxiv_id":"2302.13942","n_code_links":2,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","n_code_links":57,"syntology":{"ran":37,"of":58,"n_ran_checked":25,"n_instrument":12,"unverified":21,"pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","official":{"repos":["facebookresearch/llama"],"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":["listed","unlocated"]}}},{"paper":"/paper/reward-design-with-language-models","slug":"reward-design-with-language-models","title":"Reward Design with Language Models","date":"2023-02-27","arxiv_id":"2303.00001","n_code_links":1,"syntology":null},{"paper":"/paper/systematic-rectification-of-language-models","slug":"systematic-rectification-of-language-models","title":"Systematic Rectification of Language Models via Dead-end Analysis","date":"2023-02-27","arxiv_id":"2302.14003","n_code_links":1,"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":["mcao516/rectification-lm"],"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":null,"slug":"using-auxiliary-tasks-in-multimodal-fusion-of","title":"Using Auxiliary Tasks In Multimodal Fusion Of Wav2vec 2.0 And BERT For Multimodal Emotion Recognition","date":"2023-02-27","arxiv_id":"2302.13661","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-sentence-level-suggestions-to","title":"Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication","date":"2023-02-26","arxiv_id":"2302.13382","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-ensemble-architecture-for","slug":"efficient-ensemble-architecture-for","title":"Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network","date":"2023-02-26","arxiv_id":"2302.13376","n_code_links":1,"syntology":null}],"record_sha256":"11e3161caf192d9fcfb4cb1420360cf500c880971ad9b70614c7fe092752a5d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}