{"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/wordpiece/papers/24","list_of":"/method/wordpiece","method":"WordPiece","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":24,"pages_in_order":71,"rows_per_page":100,"rows":[2301,2400],"of":7063,"counts":{"archive_papers_tagged":7063,"with_a_code_link":2910,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7063,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":529,"every_run_a_failure_of_syntologys_instrument":121,"listed_with_a_run_with_no_instrument_failure":529,"listed_every_run_a_failure_of_syntologys_instrument":121,"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/wordpiece","prev":"/method/wordpiece/papers/23","next":"/method/wordpiece/papers/25","papers":[{"paper":null,"slug":"dacbert-leveraging-dependency-agreement-for","title":"DACBERT: Leveraging Dependency Agreement for Cost-Efficient Bert Pretraining","date":"2023-11-08","arxiv_id":"2311.04799","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-brasil-at-absapt-2022","slug":"deep-learning-brasil-at-absapt-2022","title":"Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches","date":"2023-11-08","arxiv_id":"2311.05051","n_code_links":1,"syntology":null},{"paper":"/paper/deeplearningbrasil-lt-edi-2023-exploring-deep","slug":"deeplearningbrasil-lt-edi-2023-exploring-deep","title":"DeepLearningBrasil@LT-EDI-2023: Exploring Deep Learning Techniques for Detecting Depression in Social Media Text","date":"2023-11-08","arxiv_id":"2311.05047","n_code_links":1,"syntology":null},{"paper":"/paper/determination-of-toxic-comments-and","slug":"determination-of-toxic-comments-and","title":"Determination of toxic comments and unintended model bias minimization using Deep learning approach","date":"2023-11-08","arxiv_id":"2311.04789","n_code_links":1,"syntology":null},{"paper":null,"slug":"pre-training-llms-using-human-like","title":"Pre-training LLMs using human-like development data corpus","date":"2023-11-08","arxiv_id":"2311.04666","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-intelligence-with-arm-rag","title":"Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation","date":"2023-11-07","arxiv_id":"2311.04177","n_code_links":0,"syntology":null},{"paper":"/paper/modelling-sentiment-analysis-llms-and-data","slug":"modelling-sentiment-analysis-llms-and-data","title":"Modelling Sentiment Analysis: LLMs and data augmentation techniques","date":"2023-11-07","arxiv_id":"2311.04139","n_code_links":1,"syntology":null},{"paper":null,"slug":"personality-style-recognition-via-machine","title":"Personality Style Recognition via Machine Learning: Identifying Anaclitic and Introjective Personality Styles from Patients' Speech","date":"2023-11-07","arxiv_id":"2311.04088","n_code_links":0,"syntology":null},{"paper":"/paper/accumulating-word-representations-in-multi","slug":"accumulating-word-representations-in-multi","title":"Accumulating Word Representations in Multi-level Context Integration for ERC Task","date":"2023-11-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/language-models-are-super-mario-absorbing","slug":"language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","arxiv_id":"2311.03099","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yule-buaa/mergelm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/chata-towards-an-intelligent-question-answer","slug":"chata-towards-an-intelligent-question-answer","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","date":"2023-11-05","arxiv_id":"2311.02775","n_code_links":1,"syntology":null},{"paper":null,"slug":"you-only-forward-once-prediction-and","title":"You Only Forward Once: Prediction and Rationalization in A Single Forward Pass","date":"2023-11-04","arxiv_id":"2311.02344","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","n_code_links":0,"syntology":null},{"paper":"/paper/simplifying-transformer-blocks","slug":"simplifying-transformer-blocks","title":"Simplifying Transformer Blocks","date":"2023-11-03","arxiv_id":"2311.01906","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-five-accountable-talk-moves-to","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","date":"2023-11-02","arxiv_id":"2311.10749","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-improved-transformer-based-model-for","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","date":"2023-11-01","arxiv_id":"2311.04913","n_code_links":0,"syntology":null},{"paper":null,"slug":"entity-alignment-method-of-science-and","title":"Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion","date":"2023-11-01","arxiv_id":"2311.00300","n_code_links":0,"syntology":null},{"paper":"/paper/syntactic-inductive-bias-in-transformer","slug":"syntactic-inductive-bias-in-transformer","title":"Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?","date":"2023-11-01","arxiv_id":"2311.00268","n_code_links":1,"syntology":null},{"paper":null,"slug":"bertwich-extending-bert-s-capabilities-to","title":"BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text","date":"2023-10-31","arxiv_id":"2311.00116","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-token-barrier-chunking-and","title":"Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT","date":"2023-10-31","arxiv_id":"2310.20558","n_code_links":0,"syntology":null},{"paper":null,"slug":"eelbert-tiny-models-through-dynamic","title":"EELBERT: Tiny Models through Dynamic Embeddings","date":"2023-10-31","arxiv_id":"2310.20144","n_code_links":0,"syntology":null},{"paper":null,"slug":"fa-team-at-the-ntcir-17-ufo-task","title":"FA Team at the NTCIR-17 UFO Task","date":"2023-10-31","arxiv_id":"2310.20322","n_code_links":0,"syntology":null},{"paper":null,"slug":"gar-meets-rag-paradigm-for-zero-shot","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","date":"2023-10-31","arxiv_id":"2310.20158","n_code_links":0,"syntology":null},{"paper":"/paper/increasing-the-performance-of-cognitively","slug":"increasing-the-performance-of-cognitively","title":"Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building","date":"2023-10-31","arxiv_id":"2310.20589","n_code_links":1,"syntology":null},{"paper":"/paper/btrec-bert-based-trajectory-recommendation","slug":"btrec-bert-based-trajectory-recommendation","title":"BTRec: BERT-Based Trajectory Recommendation for Personalized Tours","date":"2023-10-30","arxiv_id":"2310.19886","n_code_links":1,"syntology":null},{"paper":"/paper/jina-embeddings-2-8192-token-general-purpose","slug":"jina-embeddings-2-8192-token-general-purpose","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","date":"2023-10-30","arxiv_id":"2310.19923","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"partial-tensorized-transformers-for-natural","title":"Partial Tensorized Transformers for Natural Language Processing","date":"2023-10-30","arxiv_id":"2310.20077","n_code_links":0,"syntology":null},{"paper":"/paper/split-ner-named-entity-recognition-via-two","slug":"split-ner-named-entity-recognition-via-two","title":"Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications","date":"2023-10-30","arxiv_id":"2310.19942","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["c3sr/split-ner"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"from-chatbots-to-phishbots-preventing","title":"From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude","date":"2023-10-29","arxiv_id":"2310.19181","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-and-transformer-based","title":"Prompt-Engineering and Transformer-based Question Generation and Evaluation","date":"2023-10-29","arxiv_id":"2310.18867","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrofitting-light-weight-language-models-for","title":"Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning","date":"2023-10-29","arxiv_id":"2310.18930","n_code_links":0,"syntology":null},{"paper":null,"slug":"style-description-based-text-to-speech-with","title":"Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN","date":"2023-10-27","arxiv_id":"2310.18169","n_code_links":0,"syntology":null},{"paper":null,"slug":"arabic-fine-grained-entity-recognition","title":"Arabic Fine-Grained Entity Recognition","date":"2023-10-26","arxiv_id":"2310.17333","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedpeat-convergence-of-federated-learning","title":"FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing","date":"2023-10-26","arxiv_id":"2310.17491","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-gpt-3-5-turbo-for-rhetorical-role","title":"Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases","date":"2023-10-26","arxiv_id":"2310.17413","n_code_links":0,"syntology":null},{"paper":"/paper/sliceformer-make-multi-head-attention-as","slug":"sliceformer-make-multi-head-attention-as","title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","date":"2023-10-26","arxiv_id":"2310.17683","n_code_links":1,"syntology":null},{"paper":"/paper/torchdistill-meets-hugging-face-libraries-for","slug":"torchdistill-meets-hugging-face-libraries-for","title":"torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP","date":"2023-10-26","arxiv_id":"2310.17644","n_code_links":1,"syntology":null},{"paper":null,"slug":"zeroquant-hero-hardware-enhanced-robust","title":"ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers","date":"2023-10-26","arxiv_id":"2310.17723","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-document-information-analysis-with","title":"Enhancing Document Information Analysis with Multi-Task Pre-training: A Robust Approach for Information Extraction in Visually-Rich Documents","date":"2023-10-25","arxiv_id":"2310.16527","n_code_links":0,"syntology":null},{"paper":"/paper/llm-fp4-4-bit-floating-point-quantized","slug":"llm-fp4-4-bit-floating-point-quantized","title":"LLM-FP4: 4-Bit Floating-Point Quantized Transformers","date":"2023-10-25","arxiv_id":"2310.16836","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["nbasyl/llm-fp4"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mathbb-vd-mathbb-gr-boosting-mathbb-v-isual","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","date":"2023-10-25","arxiv_id":"2310.16590","n_code_links":0,"syntology":null},{"paper":null,"slug":"url-bert-training-webpage-representations-via","title":"URL-BERT: Training Webpage Representations via Social Media Engagements","date":"2023-10-25","arxiv_id":"2310.16303","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-enhancing-backdoor-attacks-against","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","date":"2023-10-23","arxiv_id":"2310.14480","n_code_links":0,"syntology":null},{"paper":null,"slug":"health-disparities-through-generative-ai","title":"Health Disparities through Generative AI Models: A Comparison Study Using A Domain Specific large language model","date":"2023-10-23","arxiv_id":"2310.18355","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-potential-of-prompt","title":"Unleashing the potential of prompt engineering for large language models","date":"2023-10-23","arxiv_id":"2310.14735","n_code_links":0,"syntology":null},{"paper":null,"slug":"item-unsupervised-image-text-embedding","title":"ITEm: Unsupervised Image-Text Embedding Learning for eCommerce","date":"2023-10-22","arxiv_id":"2311.02084","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-harmful-erotic-content-detection","title":"Towards Harmful Erotic Content Detection through Coreference-Driven Contextual Analysis","date":"2023-10-22","arxiv_id":"2310.14325","n_code_links":0,"syntology":null},{"paper":null,"slug":"covidfakeexplainer-an-explainable-machine","title":"COVIDFakeExplainer: An Explainable Machine Learning based Web Application for Detecting COVID-19 Fake News","date":"2023-10-21","arxiv_id":"2310.13890","n_code_links":0,"syntology":null},{"paper":"/paper/llm-prop-predicting-physical-and-electronic","slug":"llm-prop-predicting-physical-and-electronic","title":"LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions","date":"2023-10-21","arxiv_id":"2310.14029","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["vertaix/llm-prop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"anomaly-detection-of-command-shell-sessions","title":"Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches","date":"2023-10-20","arxiv_id":"2310.13247","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-impact-of-corpus-diversity-on","slug":"exploring-the-impact-of-corpus-diversity-on","title":"Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models","date":"2023-10-20","arxiv_id":"2310.13312","n_code_links":1,"syntology":null},{"paper":null,"slug":"fabula-intelligence-report-generation-using","title":"FABULA: Intelligence Report Generation Using Retrieval-Augmented Narrative Construction","date":"2023-10-20","arxiv_id":"2310.13848","n_code_links":0,"syntology":null},{"paper":"/paper/multi-level-contrastive-learning-for-script","slug":"multi-level-contrastive-learning-for-script","title":"Multi-level Contrastive Learning for Script-based Character Understanding","date":"2023-10-20","arxiv_id":"2310.13231","n_code_links":1,"syntology":null},{"paper":null,"slug":"medai-dialog-corpus-medic-zero-shot","title":"MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations","date":"2023-10-19","arxiv_id":"2310.12489","n_code_links":0,"syntology":null},{"paper":"/paper/product-attribute-value-extraction-using","slug":"product-attribute-value-extraction-using","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","date":"2023-10-19","arxiv_id":"2310.12537","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-robust-pruning-an-adaptive-knowledge","title":"Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models","date":"2023-10-19","arxiv_id":"2310.13191","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-entity-legal-form","slug":"transformer-based-entity-legal-form","title":"Transformer-based Entity Legal Form Classification","date":"2023-10-19","arxiv_id":"2310.12766","n_code_links":1,"syntology":null},{"paper":null,"slug":"field-testing-items-using-artificial","title":"Field-testing items using artificial intelligence: Natural language processing with transformers","date":"2023-10-18","arxiv_id":"2310.11655","n_code_links":0,"syntology":null},{"paper":"/paper/improving-long-document-topic-segmentation","slug":"improving-long-document-topic-segmentation","title":"Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling","date":"2023-10-18","arxiv_id":"2310.11772","n_code_links":1,"syntology":null},{"paper":null,"slug":"disentangling-the-linguistic-competence-of","title":"Disentangling the Linguistic Competence of Privacy-Preserving BERT","date":"2023-10-17","arxiv_id":"2310.11363","n_code_links":0,"syntology":null},{"paper":"/paper/entity-matching-using-large-language-models","slug":"entity-matching-using-large-language-models","title":"Entity Matching using Large Language Models","date":"2023-10-17","arxiv_id":"2310.11244","n_code_links":1,"syntology":null},{"paper":null,"slug":"mason-nlp-at-erisk-2023-deep-learning-based","title":"MASON-NLP at eRisk 2023: Deep Learning-Based Detection of Depression Symptoms from Social Media Texts","date":"2023-10-17","arxiv_id":"2310.10941","n_code_links":0,"syntology":null},{"paper":"/paper/neural-attention-enhancing-qkv-calculation-in","slug":"neural-attention-enhancing-qkv-calculation-in","title":"Neural Attention: Enhancing QKV Calculation in Self-Attention Mechanism with Neural Networks","date":"2023-10-17","arxiv_id":"2310.11398","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-chatgpt-for-automatic-scoring","title":"Fine-tuning ChatGPT for Automatic Scoring","date":"2023-10-16","arxiv_id":"2310.10072","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-bias-in-multilingual-language","slug":"investigating-bias-in-multilingual-language","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","date":"2023-10-16","arxiv_id":"2310.10310","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-rank-context-for-named-entity","slug":"learning-to-rank-context-for-named-entity","title":"Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset","date":"2023-10-16","arxiv_id":"2310.10118","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalization-of-ctc-based-end-to-end","title":"Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization","date":"2023-10-16","arxiv_id":"2310.09988","n_code_links":0,"syntology":null},{"paper":"/paper/domain-specific-language-model-post-training","slug":"domain-specific-language-model-post-training","title":"Domain-Specific Language Model Post-Training for Indonesian Financial NLP","date":"2023-10-15","arxiv_id":"2310.09736","n_code_links":1,"syntology":null},{"paper":"/paper/dpzero-dimension-independent-and","slug":"dpzero-dimension-independent-and","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","date":"2023-10-14","arxiv_id":"2310.09639","n_code_links":1,"syntology":{"ran":8,"of":17,"n_ran_checked":6,"n_instrument":2,"unverified":9,"pointer_only":3,"phrase":"8 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; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["liang137/dpzero"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"leveraging-generative-ai-improving-software","title":"Leveraging Generative AI: Improving Software Metadata Classification with Generated Code-Comment Pairs","date":"2023-10-14","arxiv_id":"2311.03365","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-bert-based-visual-question","title":"Enhancing BERT-Based Visual Question Answering through Keyword-Driven Sentence Selection","date":"2023-10-13","arxiv_id":"2310.09432","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-textual-data-for-fatality","title":"Analyzing Textual Data for Fatality Classification in Afghanistan's Armed Conflicts: A BERT Approach","date":"2023-10-12","arxiv_id":"2310.08653","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-and-prediction-of-clopidogrel","title":"Detection and prediction of clopidogrel treatment failures using longitudinal structured electronic health records","date":"2023-10-12","arxiv_id":"2310.08757","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-effectiveness-of-capsule","slug":"evaluating-the-effectiveness-of-capsule","title":"Evaluating The Effectiveness of Capsule Neural Network in Toxic Comment Classification using Pre-trained BERT Embeddings","date":"2023-10-12","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/lemon-lossless-model-expansion","slug":"lemon-lossless-model-expansion","title":"LEMON: Lossless model expansion","date":"2023-10-12","arxiv_id":"2310.07999","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["YiteWang/lemon-pytorch"],"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":"llm-augmented-preference-learning-from","title":"LLM-augmented Preference Learning from Natural Language","date":"2023-10-12","arxiv_id":"2310.08523","n_code_links":0,"syntology":null},{"paper":"/paper/the-uncertainty-based-retrieval-framework-for-1","slug":"the-uncertainty-based-retrieval-framework-for-1","title":"The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS","date":"2023-10-12","arxiv_id":"2310.08496","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-electra-for-efficient-pre-training","title":"Fast-ELECTRA for Efficient Pre-training","date":"2023-10-11","arxiv_id":"2310.07347","n_code_links":0,"syntology":null},{"paper":null,"slug":"jaeger-a-concatenation-based-multi","title":"Jaeger: A Concatenation-Based Multi-Transformer VQA Model","date":"2023-10-11","arxiv_id":"2310.07091","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-the-bert-like-pretraining-for-dna","title":"Toward Understanding BERT-Like Pre-Training for DNA Foundation Models","date":"2023-10-11","arxiv_id":"2310.07644","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-transformer-based-1","title":"A Comparative Study of Transformer-based Neural Text Representation Techniques on Bug Triaging","date":"2023-10-10","arxiv_id":"2310.06913","n_code_links":0,"syntology":null},{"paper":"/paper/geollm-extracting-geospatial-knowledge-from","slug":"geollm-extracting-geospatial-knowledge-from","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","date":"2023-10-10","arxiv_id":"2310.06213","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rohinmanvi/GeoLLM"],"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":null,"slug":"gpt-4-as-an-agronomist-assistant-answering","title":"GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models","date":"2023-10-10","arxiv_id":"2310.06225","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","n_code_links":2,"syntology":null},{"paper":null,"slug":"auditing-gender-analyzers-on-text-data","title":"Auditing Gender Analyzers on Text Data","date":"2023-10-09","arxiv_id":"2310.06061","n_code_links":0,"syntology":null},{"paper":null,"slug":"cabbage-sweeter-than-cake-analysing-the","title":"Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces","date":"2023-10-09","arxiv_id":"2310.05481","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-models-meet-visualizations","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","date":"2023-10-09","arxiv_id":"2310.05771","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-fusion-with-optimal-transport","slug":"transformer-fusion-with-optimal-transport","title":"Transformer Fusion with Optimal Transport","date":"2023-10-09","arxiv_id":"2310.05719","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":0,"n_instrument":3,"unverified":7,"pointer_only":10,"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) · 7 unverified","official":{"repos":["graldij/transformer-fusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"breaking-down-word-semantics-from-pre-trained","title":"Breaking Down Word Semantics from Pre-trained Language Models through Layer-wise Dimension Selection","date":"2023-10-08","arxiv_id":"2310.05115","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pre-trained-language-models-with","title":"Enhancing Pre-Trained Language Models with Sentence Position Embeddings for Rhetorical Roles Recognition in Legal Opinions","date":"2023-10-08","arxiv_id":"2310.05276","n_code_links":0,"syntology":null},{"paper":"/paper/llm4vv-developing-llm-driven-testsuite-for","slug":"llm4vv-developing-llm-driven-testsuite-for","title":"LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation","date":"2023-10-08","arxiv_id":"2310.04963","n_code_links":1,"syntology":null},{"paper":null,"slug":"rac-bert-character-radical-enhanced-bert-for","title":"RAC-BERT: Character Radical Enhanced BERT for Ancient Chinese","date":"2023-10-08","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-process-for-topic-modelling-via-word","title":"A Process for Topic Modelling Via Word Embeddings","date":"2023-10-06","arxiv_id":"2312.03705","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-aspect-extraction-from-scientific","slug":"automatic-aspect-extraction-from-scientific","title":"Automatic Aspect Extraction from Scientific Texts","date":"2023-10-06","arxiv_id":"2310.04074","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantized-transformer-language-model","title":"Quantized Transformer Language Model Implementations on Edge Devices","date":"2023-10-06","arxiv_id":"2310.03971","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmented-harmonic-loss-handling-class","title":"Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models","date":"2023-10-06","arxiv_id":"2310.04595","n_code_links":0,"syntology":null},{"paper":null,"slug":"covid-19-south-african-vaccine-hesitancy","title":"COVID-19 South African Vaccine Hesitancy Models Show Boost in Performance Upon Fine-Tuning on M-pox Tweets","date":"2023-10-04","arxiv_id":"2310.04453","n_code_links":0,"syntology":null},{"paper":"/paper/memoria-hebbian-memory-architecture-for-human","slug":"memoria-hebbian-memory-architecture-for-human","title":"Memoria: Resolving Fateful Forgetting Problem through Human-Inspired Memory Architecture","date":"2023-10-04","arxiv_id":"2310.03052","n_code_links":1,"syntology":{"ran":1,"of":10,"n_ran_checked":0,"n_instrument":1,"unverified":9,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","official":{"repos":["cosmoquester/memoria"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-augmented-generation-to-improve","slug":"retrieval-augmented-generation-to-improve","title":"Retrieval-augmented Generation to Improve Math Question-Answering: Trade-offs Between Groundedness and Human Preference","date":"2023-10-04","arxiv_id":"2310.03184","n_code_links":2,"syntology":{"ran":12,"of":20,"n_ran_checked":12,"n_instrument":0,"unverified":8,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["digitalharborfoundation/rag-for-math-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"harnessing-pre-trained-sentence-transformers","title":"Harnessing Pre-Trained Sentence Transformers for Offensive Language Detection in Indian Languages","date":"2023-10-03","arxiv_id":"2310.02249","n_code_links":0,"syntology":null}],"record_sha256":"756bc54190c7ed1a776cccfe245fff356e1cca9f780bf2581e590c5d82efac00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}