{"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/linear-warmup-with-linear-decay/papers/23","list_of":"/method/linear-warmup-with-linear-decay","method":"Linear Warmup With Linear 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":23,"pages_in_order":71,"rows_per_page":100,"rows":[2201,2300],"of":7076,"counts":{"archive_papers_tagged":7076,"with_a_code_link":2913,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7076,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":531,"every_run_a_failure_of_syntologys_instrument":119,"listed_with_a_run_with_no_instrument_failure":531,"listed_every_run_a_failure_of_syntologys_instrument":119,"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/linear-warmup-with-linear-decay","prev":"/method/linear-warmup-with-linear-decay/papers/22","next":"/method/linear-warmup-with-linear-decay/papers/24","papers":[{"paper":null,"slug":"enhancing-multilingual-information-retrieval","title":"Enhancing Multilingual Information Retrieval in Mixed Human Resources Environments: A RAG Model Implementation for Multicultural Enterprise","date":"2024-01-03","arxiv_id":"2401.01511","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-mask-filling-an-effective-text","title":"Iterative Mask Filling: An Effective Text Augmentation Method Using Masked Language Modeling","date":"2024-01-03","arxiv_id":"2401.01830","n_code_links":0,"syntology":null},{"paper":null,"slug":"mlps-compass-what-is-learned-when-mlps-are","title":"MLPs Compass: What is learned when MLPs are combined with PLMs?","date":"2024-01-03","arxiv_id":"2401.01667","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-processing-and-multimodal","title":"Natural Language Processing and Multimodal Stock Price Prediction","date":"2024-01-03","arxiv_id":"2401.01487","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-counterfactual-problems-in","slug":"revisiting-counterfactual-problems-in","title":"Revisiting Counterfactual Problems in Referring Expression Comprehension","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-embedding-layers-and","title":"An Analysis of Embedding Layers and Similarity Scores using Siamese Neural Networks","date":"2023-12-31","arxiv_id":"2401.00582","n_code_links":0,"syntology":null},{"paper":"/paper/ragtruth-a-hallucination-corpus-for","slug":"ragtruth-a-hallucination-corpus-for","title":"RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models","date":"2023-12-31","arxiv_id":"2401.00396","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["particlemedia/ragtruth"],"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/advancing-ttp-analysis-harnessing-the-power","slug":"advancing-ttp-analysis-harnessing-the-power","title":"Advancing TTP Analysis: Harnessing the Power of Large Language Models with Retrieval Augmented Generation","date":"2023-12-30","arxiv_id":"2401.00280","n_code_links":1,"syntology":null},{"paper":"/paper/why-is-the-user-interface-a-dark-pattern","slug":"why-is-the-user-interface-a-dark-pattern","title":"Why is the User Interface a Dark Pattern? : Explainable Auto-Detection and its Analysis","date":"2023-12-30","arxiv_id":"2401.04119","n_code_links":1,"syntology":null},{"paper":"/paper/mosaicbert-a-bidirectional-encoder-optimized-1","slug":"mosaicbert-a-bidirectional-encoder-optimized-1","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","date":"2023-12-29","arxiv_id":"2312.17482","n_code_links":1,"syntology":null},{"paper":"/paper/tupy-e-detecting-hate-speech-in-brazilian","slug":"tupy-e-detecting-hate-speech-in-brazilian","title":"TuPy-E: detecting hate speech in Brazilian Portuguese social media with a novel dataset and comprehensive analysis of models","date":"2023-12-29","arxiv_id":"2312.17704","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-model-as-an-annotator-unsupervised","title":"Language Model as an Annotator: Unsupervised Context-aware Quality Phrase Generation","date":"2023-12-28","arxiv_id":"2312.17349","n_code_links":0,"syntology":null},{"paper":"/paper/sentinellms-encrypted-input-adaptation-and","slug":"sentinellms-encrypted-input-adaptation-and","title":"SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference","date":"2023-12-28","arxiv_id":"2312.17342","n_code_links":1,"syntology":null},{"paper":null,"slug":"relationship-between-auditory-and-semantic","title":"Relationship between auditory and semantic entrainment using Deep Neural Networks (DNN)","date":"2023-12-27","arxiv_id":"2312.16599","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-generalization-in-spoken","title":"Compositional Generalization in Spoken Language Understanding","date":"2023-12-25","arxiv_id":"2312.15815","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-biomedical-ner-through-multi","title":"Multi-level biomedical NER through multi-granularity embeddings and enhanced labeling","date":"2023-12-24","arxiv_id":"2312.15550","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-the-potential-of-fpga-based","slug":"understanding-the-potential-of-fpga-based","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","date":"2023-12-23","arxiv_id":"2312.15159","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficacy-of-machine-generated-instructions","title":"Efficacy of Machine-Generated Instructions","date":"2023-12-22","arxiv_id":"2312.14423","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-detecting-cascades-of-biased-medical","title":"Towards Detecting Cascades of Biased Medical Claims on Twitter","date":"2023-12-22","arxiv_id":"2312.15040","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-regularity-of-self","title":"How Smooth Is Attention?","date":"2023-12-22","arxiv_id":"2312.14820","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-auditory-and-semantic","title":"Unsupervised Auditory and Semantic Entrainment Models with Deep Neural Networks","date":"2023-12-22","arxiv_id":"2312.15098","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-as-a-commenter-to-the-news-can-llms","slug":"chatgpt-as-a-commenter-to-the-news-can-llms","title":"ChatGPT as a commenter to the news: can LLMs generate human-like opinions?","date":"2023-12-21","arxiv_id":"2312.13961","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-to-prune-your-language-model-recovering","title":"How to Prune Your Language Model: Recovering Accuracy on the \"Sparsity May Cry'' Benchmark","date":"2023-12-21","arxiv_id":"2312.13547","n_code_links":0,"syntology":null},{"paper":"/paper/lookahead-an-inference-acceleration-framework","slug":"lookahead-an-inference-acceleration-framework","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","date":"2023-12-20","arxiv_id":"2312.12728","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alipay/PainlessInferenceAcceleration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/detecting-technical-debt-using-natural","slug":"detecting-technical-debt-using-natural","title":"Self-Admitted Technical Debt Detection Approaches: A Decade Systematic Review","date":"2023-12-19","arxiv_id":"2312.15020","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-title-reranker-for-fast-and","title":"Efficient Title Reranker for Fast and Improved Knowledge-Intense NLP","date":"2023-12-19","arxiv_id":"2312.12430","n_code_links":0,"syntology":null},{"paper":"/paper/nomiracl-knowing-when-you-don-t-know-for","slug":"nomiracl-knowing-when-you-don-t-know-for","title":"\"Knowing When You Don't Know\": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation","date":"2023-12-18","arxiv_id":"2312.11361","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["project-miracl/nomiracl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-augmented-generation-for-large","slug":"retrieval-augmented-generation-for-large","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","date":"2023-12-18","arxiv_id":"2312.10997","n_code_links":4,"syntology":null},{"paper":"/paper/bengali-intent-classification-with-generative","slug":"bengali-intent-classification-with-generative","title":"Bengali Intent Classification with Generative Adversarial BERT","date":"2023-12-17","arxiv_id":"2312.10679","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-persistent-homology-whiten-transformer","title":"Can persistent homology whiten Transformer-based black-box models? A case study on BERT compression","date":"2023-12-17","arxiv_id":"2312.10702","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-concerns-multi-label-classification","slug":"decoding-concerns-multi-label-classification","title":"Decoding Concerns: Multi-label Classification of Vaccine Sentiments in Social Media","date":"2023-12-17","arxiv_id":"2312.10626","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-salient-representations-and","title":"Investigating salient representations and label Variance in Dimensional Speech Emotion Analysis","date":"2023-12-17","arxiv_id":"2312.16180","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-linguistic-offensive-language-detection","title":"Cross-Linguistic Offensive Language Detection: BERT-Based Analysis of Bengali, Assamese, & Bodo Conversational Hateful Content from Social Media","date":"2023-12-16","arxiv_id":"2312.10528","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-shallow-and-deep-learning","slug":"investigating-shallow-and-deep-learning","title":"Investigating Shallow and Deep Learning Techniques for Emotion Classification in Short Persian Texts","date":"2023-12-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/spt-fine-tuning-transformer-based-language","slug":"spt-fine-tuning-transformer-based-language","title":"SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification","date":"2023-12-16","arxiv_id":"2312.10365","n_code_links":1,"syntology":null},{"paper":null,"slug":"algorithms-for-automatic-intents-extraction","title":"Algorithms for automatic intents extraction and utterances classification for goal-oriented dialogue systems","date":"2023-12-15","arxiv_id":"2312.09658","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-automatic-text-simplification-of","slug":"exploring-automatic-text-simplification-of","title":"Exploring Automatic Text Simplification of German Narrative Documents","date":"2023-12-15","arxiv_id":"2312.09907","n_code_links":1,"syntology":null},{"paper":null,"slug":"no-skim-towards-efficiency-robustness","title":"No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models","date":"2023-12-15","arxiv_id":"2312.09494","n_code_links":0,"syntology":null},{"paper":"/paper/dissecting-vocabulary-biases-datasets-through","slug":"dissecting-vocabulary-biases-datasets-through","title":"Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference","date":"2023-12-14","arxiv_id":"2312.08747","n_code_links":1,"syntology":null},{"paper":"/paper/mono3dvg-3d-visual-grounding-in-monocular","slug":"mono3dvg-3d-visual-grounding-in-monocular","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","date":"2023-12-13","arxiv_id":"2312.08022","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhanyang-nwpu/mono3dvg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-engineering-assisted-malware-dynamic","slug":"prompt-engineering-assisted-malware-dynamic","title":"Prompt Engineering-assisted Malware Dynamic Analysis Using GPT-4","date":"2023-12-13","arxiv_id":"2312.08317","n_code_links":1,"syntology":null},{"paper":"/paper/harnessing-retrieval-augmented-generation-rag","slug":"harnessing-retrieval-augmented-generation-rag","title":"Harnessing Retrieval-Augmented Generation (RAG) for Uncovering Knowledge Gaps","date":"2023-12-12","arxiv_id":"2312.07796","n_code_links":1,"syntology":null},{"paper":null,"slug":"seopinion-summarization-and-exploration","title":"SEOpinion: Summarization and Exploration Opinion of E-Commerce Websites","date":"2023-12-12","arxiv_id":"2312.14171","n_code_links":0,"syntology":null},{"paper":"/paper/towards-equipping-transformer-with-the","slug":"towards-equipping-transformer-with-the","title":"Towards Equipping Transformer with the Ability of Systematic Compositionality","date":"2023-12-12","arxiv_id":"2312.07280","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-musculoskeletal-disorder-risk","title":"A Natural Language Processing-Based Classification and Mode-Based Ranking of Musculoskeletal Disorder Risk Factors","date":"2023-12-12","arxiv_id":"2312.11517","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-news-and-social-media-linking","title":"Contrastive News and Social Media Linking using BERT for Articles and Tweets across Dual Platforms","date":"2023-12-11","arxiv_id":"2312.07599","n_code_links":0,"syntology":null},{"paper":null,"slug":"label-smoothing-for-enhanced-text-sentiment","title":"Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification","date":"2023-12-11","arxiv_id":"2312.06522","n_code_links":0,"syntology":null},{"paper":null,"slug":"survey-on-foundation-models-for-prognostics","title":"Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems","date":"2023-12-11","arxiv_id":"2312.06261","n_code_links":0,"syntology":null},{"paper":"/paper/textual-prompt-guided-image-restoration","slug":"textual-prompt-guided-image-restoration","title":"Textual Prompt Guided Image Restoration","date":"2023-12-11","arxiv_id":"2312.06162","n_code_links":1,"syntology":null},{"paper":null,"slug":"where-exactly-does-contextualization-in-a-plm","title":"Where exactly does contextualization in a PLM happen?","date":"2023-12-11","arxiv_id":"2312.06514","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-or-retrieval-comparing-knowledge","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","date":"2023-12-10","arxiv_id":"2312.05934","n_code_links":0,"syntology":null},{"paper":null,"slug":"fp8-bert-post-training-quantization-for","title":"FP8-BERT: Post-Training Quantization for Transformer","date":"2023-12-10","arxiv_id":"2312.05725","n_code_links":0,"syntology":null},{"paper":"/paper/gamc-an-unsupervised-method-for-fake-news","slug":"gamc-an-unsupervised-method-for-fake-news","title":"GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking","date":"2023-12-10","arxiv_id":"2312.05739","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-review-of-hybrid-and-ensemble-in-deep","title":"A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processing","date":"2023-12-09","arxiv_id":"2312.05589","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-tuning-for-retrieval-augmented","title":"Context Tuning for Retrieval Augmented Generation","date":"2023-12-09","arxiv_id":"2312.05708","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-e-commerce-attribute-extraction","title":"Enhanced E-Commerce Attribute Extraction: Innovating with Decorative Relation Correction and LLAMA 2.0-Based Annotation","date":"2023-12-09","arxiv_id":"2312.06684","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-medical-specialty-assignment-to","title":"Enhancing Medical Specialty Assignment to Patients using NLP Techniques","date":"2023-12-09","arxiv_id":"2312.05585","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-content-detection","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","date":"2023-12-09","arxiv_id":"2312.05671","n_code_links":0,"syntology":null},{"paper":"/paper/labrador-exploring-the-limits-of-masked","slug":"labrador-exploring-the-limits-of-masked","title":"Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data","date":"2023-12-09","arxiv_id":"2312.11502","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":["davidbellamy/labrador"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sim-gpt-text-similarity-via-gpt-annotated","slug":"sim-gpt-text-similarity-via-gpt-annotated","title":"Sim-GPT: Text Similarity via GPT Annotated Data","date":"2023-12-09","arxiv_id":"2312.05603","n_code_links":1,"syntology":null},{"paper":null,"slug":"teamwork-dimensions-classification-using-bert","title":"Teamwork Dimensions Classification Using BERT","date":"2023-12-09","arxiv_id":"2312.05483","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-bert-for-point-cloud-pretraining","title":"Cross-BERT for Point Cloud Pretraining","date":"2023-12-08","arxiv_id":"2312.04891","n_code_links":0,"syntology":null},{"paper":null,"slug":"illicit-darkweb-classification-via-natural","title":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","date":"2023-12-08","arxiv_id":"2312.04944","n_code_links":0,"syntology":null},{"paper":"/paper/inspect-intrinsic-and-systematic-probing","slug":"inspect-intrinsic-and-systematic-probing","title":"INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers","date":"2023-12-08","arxiv_id":"2312.05092","n_code_links":1,"syntology":null},{"paper":null,"slug":"paperqa-retrieval-augmented-generative-agent","title":"PaperQA: Retrieval-Augmented Generative Agent for Scientific Research","date":"2023-12-08","arxiv_id":"2312.07559","n_code_links":0,"syntology":null},{"paper":"/paper/fortify-the-shortest-stave-in-attention","slug":"fortify-the-shortest-stave-in-attention","title":"Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use","date":"2023-12-07","arxiv_id":"2312.04455","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fiorina1212/attention-buckets"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["adrianbzg/tinyroberta-distillation-qa-es"],"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-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-transcription-of-handwritten-old","slug":"automatic-transcription-of-handwritten-old","title":"Automatic Transcription of Handwritten Old Occitan Language","date":"2023-12-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"corporate-bankruptcy-prediction-with-domain","title":"Corporate Bankruptcy Prediction with Domain-Adapted BERT","date":"2023-12-06","arxiv_id":"2312.03194","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-large-language-models-llms-succumb-to","slug":"not-all-large-language-models-llms-succumb-to","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","date":"2023-12-06","arxiv_id":"2312.03633","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-model-llm-security","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","date":"2023-12-04","arxiv_id":"2312.02003","n_code_links":0,"syntology":null},{"paper":null,"slug":"expand-bert-representation-with-visual","title":"Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment","date":"2023-12-04","arxiv_id":"2312.01592","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-disentangled-embeddings-for","slug":"prompting-disentangled-embeddings-for","title":"Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model","date":"2023-12-04","arxiv_id":"2312.01837","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai-powered-arabic-crossword-puzzle-generation","title":"ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications","date":"2023-12-03","arxiv_id":"2312.01339","n_code_links":0,"syntology":null},{"paper":"/paper/nlebench-norglm-a-comprehensive-empirical","slug":"nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["smartmedia-ai/norglm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"on-significance-of-subword-tokenization-for","title":"On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi","date":"2023-12-03","arxiv_id":"2312.01306","n_code_links":0,"syntology":null},{"paper":"/paper/a-ripple-in-time-a-discontinuity-in-american","slug":"a-ripple-in-time-a-discontinuity-in-american","title":"A ripple in time: a discontinuity in American history","date":"2023-12-02","arxiv_id":"2312.01185","n_code_links":1,"syntology":null},{"paper":null,"slug":"aspect-level-sentiment-analysis-based-on","title":"Knowledge Graph Enhanced Aspect-Level Sentiment Analysis","date":"2023-12-02","arxiv_id":"2312.10048","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-scoring-of-students-science-writing","title":"Automatic Scoring of Students' Science Writing Using Hybrid Neural Network","date":"2023-12-02","arxiv_id":"2312.03752","n_code_links":0,"syntology":null},{"paper":null,"slug":"iag-induction-augmented-generation-framework","title":"IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions","date":"2023-11-30","arxiv_id":"2311.18397","n_code_links":0,"syntology":null},{"paper":"/paper/llvms4protest-harnessing-the-power-of-large","slug":"llvms4protest-harnessing-the-power-of-large","title":"LLVMs4Protest: Harnessing the Power of Large Language and Vision Models for Deciphering Protests in the News","date":"2023-11-30","arxiv_id":"2311.18241","n_code_links":1,"syntology":null},{"paper":null,"slug":"transfer-learning-across-different-chemical","title":"Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data","date":"2023-11-30","arxiv_id":"2311.18377","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-natural-language-processing-based-approach","title":"A natural language processing-based approach: mapping human perception by understanding deep semantic features in street view images","date":"2023-11-29","arxiv_id":"2311.17354","n_code_links":0,"syntology":null},{"paper":"/paper/biomedical-knowledge-graph-enhanced-prompt","slug":"biomedical-knowledge-graph-enhanced-prompt","title":"Biomedical knowledge graph-optimized prompt generation for large language models","date":"2023-11-29","arxiv_id":"2311.17330","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["BaranziniLab/KG_RAG"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"enhancing-answer-selection-in-community","title":"Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models","date":"2023-11-29","arxiv_id":"2311.17502","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-the-robustness-of-transformer-based","title":"Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention","date":"2023-11-29","arxiv_id":"2311.17400","n_code_links":0,"syntology":null},{"paper":null,"slug":"rokepg-roberta-and-knowledge-enhancement-for","title":"RoKEPG: RoBERTa and Knowledge Enhancement for Prescription Generation of Traditional Chinese Medicine","date":"2023-11-29","arxiv_id":"2311.17307","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-template-transferable-backdoor-attack","title":"TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4","date":"2023-11-29","arxiv_id":"2311.17429","n_code_links":0,"syntology":null},{"paper":null,"slug":"timelygpt-recurrent-convolutional-transformer","title":"TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare","date":"2023-11-29","arxiv_id":"2312.00817","n_code_links":0,"syntology":null},{"paper":"/paper/turkishbertweet-fast-and-reliable-large","slug":"turkishbertweet-fast-and-reliable-large","title":"TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis","date":"2023-11-29","arxiv_id":"2311.18063","n_code_links":2,"syntology":null},{"paper":null,"slug":"natural-language-processing-through-transfer","title":"Natural Language Processing Through Transfer Learning: A Case Study on Sentiment Analysis","date":"2023-11-28","arxiv_id":"2311.16965","n_code_links":0,"syntology":null},{"paper":null,"slug":"syntax-informed-interactive-model-for","title":"Syntax-Informed Interactive Model for Comprehensive Aspect-Based Sentiment Analysis","date":"2023-11-28","arxiv_id":"2312.03739","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-social-aware-gaussian-pre-trained-model-for","title":"A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation","date":"2023-11-27","arxiv_id":"2311.15790","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-off-topic-investigating-the-domain","slug":"bert-goes-off-topic-investigating-the-domain","title":"BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification","date":"2023-11-27","arxiv_id":"2311.16083","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-deep-active-learning-to-identify","title":"Leveraging deep active learning to identify low-resource mobility functioning information in public clinical notes","date":"2023-11-27","arxiv_id":"2311.15946","n_code_links":0,"syntology":null},{"paper":"/paper/ssin-self-supervised-learning-for-rainfall","slug":"ssin-self-supervised-learning-for-rainfall","title":"SSIN: Self-Supervised Learning for Rainfall Spatial Interpolation","date":"2023-11-27","arxiv_id":"2311.15530","n_code_links":1,"syntology":null},{"paper":null,"slug":"uncertainty-aware-language-modeling-for","title":"Uncertainty-aware Language Modeling for Selective Question Answering","date":"2023-11-26","arxiv_id":"2311.15451","n_code_links":0,"syntology":null},{"paper":null,"slug":"swiftlearn-a-data-efficient-training-method","title":"SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling","date":"2023-11-25","arxiv_id":"2311.15134","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmed-gpt-prompt-tuning-for-entity-aware","title":"CMed-GPT: Prompt Tuning for Entity-Aware Chinese Medical Dialogue Generation","date":"2023-11-24","arxiv_id":"2311.14539","n_code_links":0,"syntology":null}],"record_sha256":"42bdc71686fad222fbfa9737b00628b67ff0c314b8dee8e00f2e0abe154a563f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}