{"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/24","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":24,"pages_in_order":71,"rows_per_page":100,"rows":[2301,2400],"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/23","next":"/method/linear-warmup-with-linear-decay/papers/25","papers":[{"paper":null,"slug":"a-multi-solution-study-on-gdpr-ai-enabled","title":"A Multi-solution Study on GDPR AI-enabled Completeness Checking of DPAs","date":"2023-11-23","arxiv_id":"2311.13881","n_code_links":0,"syntology":null},{"paper":"/paper/annotation-sensitivity-training-data","slug":"annotation-sensitivity-training-data","title":"Annotation Sensitivity: Training Data Collection Methods Affect Model Performance","date":"2023-11-23","arxiv_id":"2311.14212","n_code_links":1,"syntology":null},{"paper":null,"slug":"minimizing-factual-inconsistency-and","title":"Minimizing Factual Inconsistency and Hallucination in Large Language Models","date":"2023-11-23","arxiv_id":"2311.13878","n_code_links":0,"syntology":null},{"paper":null,"slug":"current-topological-and-machine-learning","title":"Current Topological and Machine Learning Applications for Bias Detection in Text","date":"2023-11-22","arxiv_id":"2311.13495","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-out-of-distribution-text-using","slug":"detecting-out-of-distribution-text-using","title":"Detecting out-of-distribution text using topological features of transformer-based language models","date":"2023-11-22","arxiv_id":"2311.13102","n_code_links":1,"syntology":null},{"paper":"/paper/white-box-transformers-via-sparse-rate-1","slug":"white-box-transformers-via-sparse-rate-1","title":"White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?","date":"2023-11-22","arxiv_id":"2311.13110","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/lowresource-at-blp-2023-task-2-leveraging","slug":"lowresource-at-blp-2023-task-2-leveraging","title":"LowResource at BLP-2023 Task 2: Leveraging BanglaBert for Low Resource Sentiment Analysis of Bangla Language","date":"2023-11-21","arxiv_id":"2311.12735","n_code_links":1,"syntology":null},{"paper":null,"slug":"utilizing-language-models-for-tour-itinerary","title":"Utilizing Language Models for Tour Itinerary Recommendation","date":"2023-11-21","arxiv_id":"2311.12355","n_code_links":0,"syntology":null},{"paper":"/paper/loglead-fast-and-integrated-log-loader","slug":"loglead-fast-and-integrated-log-loader","title":"LogLead -- Fast and Integrated Log Loader, Enhancer, and Anomaly Detector","date":"2023-11-20","arxiv_id":"2311.11809","n_code_links":1,"syntology":null},{"paper":"/paper/lq-lora-low-rank-plus-quantized-matrix","slug":"lq-lora-low-rank-plus-quantized-matrix","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","date":"2023-11-20","arxiv_id":"2311.12023","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hanguo97/lq-lora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/tensor-aware-energy-accounting","slug":"tensor-aware-energy-accounting","title":"Tensor-Aware Energy Accounting","date":"2023-11-19","arxiv_id":"2311.11424","n_code_links":1,"syntology":null},{"paper":null,"slug":"compositional-fusion-of-signals-in-data","title":"Compositional Fusion of Signals in Data Embedding","date":"2023-11-18","arxiv_id":"2311.11085","n_code_links":0,"syntology":null},{"paper":null,"slug":"bias-a-head-analyzing-bias-in-transformer","title":"Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads","date":"2023-11-17","arxiv_id":"2311.10395","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-periodontitis-diagnosis-in","title":"Extracting periodontitis diagnosis in clinical notes with RoBERTa and regular expression","date":"2023-11-17","arxiv_id":"2311.10809","n_code_links":0,"syntology":null},{"paper":"/paper/hashing-it-out-predicting-unhealthy","slug":"hashing-it-out-predicting-unhealthy","title":"Hashing it Out: Predicting Unhealthy Conversations on Twitter","date":"2023-11-17","arxiv_id":"2311.10596","n_code_links":1,"syntology":null},{"paper":null,"slug":"use-gpt-j-prompt-generation-with-roberta-for","title":"Use GPT-J Prompt Generation with RoBERTa for NER Models on Diagnosis Extraction of Periodontal Diagnosis from Electronic Dental Records","date":"2023-11-17","arxiv_id":"2311.10810","n_code_links":0,"syntology":null},{"paper":"/paper/ares-an-automated-evaluation-framework-for","slug":"ares-an-automated-evaluation-framework-for","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","date":"2023-11-16","arxiv_id":"2311.09476","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["stanford-futuredata/ares"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-ai-for-hate-speech-detection","title":"Generative AI for Hate Speech Detection: Evaluation and Findings","date":"2023-11-16","arxiv_id":"2311.09993","n_code_links":0,"syntology":null},{"paper":"/paper/lifetox-unveiling-implicit-toxicity-in-life","slug":"lifetox-unveiling-implicit-toxicity-in-life","title":"LifeTox: Unveiling Implicit Toxicity in Life Advice","date":"2023-11-16","arxiv_id":"2311.09585","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequencing-matters-a-generate-retrieve","title":"Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents","date":"2023-11-16","arxiv_id":"2311.09513","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-automatic-ai-agent-for-reaction","title":"Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis","date":"2023-11-16","arxiv_id":"2311.10776","n_code_links":0,"syntology":null},{"paper":"/paper/an-eye-on-clinical-bert-investigating","slug":"an-eye-on-clinical-bert-investigating","title":"An Eye on Clinical BERT: Investigating Language Model Generalization for Diabetic Eye Disease Phenotyping","date":"2023-11-15","arxiv_id":"2311.08687","n_code_links":1,"syntology":null},{"paper":"/paper/exponentially-faster-language-modelling","slug":"exponentially-faster-language-modelling","title":"Exponentially Faster Language Modelling","date":"2023-11-15","arxiv_id":"2311.10770","n_code_links":3,"syntology":null},{"paper":null,"slug":"german-finbert-a-german-pre-trained-language","title":"German FinBERT: A German Pre-trained Language Model","date":"2023-11-15","arxiv_id":"2311.08793","n_code_links":0,"syntology":null},{"paper":"/paper/we-demand-justice-towards-grounding-political","slug":"we-demand-justice-towards-grounding-political","title":"\"We Demand Justice!\": Towards Social Context Grounding of Political Texts","date":"2023-11-15","arxiv_id":"2311.09106","n_code_links":1,"syntology":null},{"paper":"/paper/xplainllm-a-qa-explanation-dataset-for","slug":"xplainllm-a-qa-explanation-dataset-for","title":"XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs","date":"2023-11-15","arxiv_id":"2311.08614","n_code_links":1,"syntology":null},{"paper":"/paper/artificial-text-boundary-detection-with","slug":"artificial-text-boundary-detection-with","title":"AI-generated text boundary detection with RoFT","date":"2023-11-14","arxiv_id":"2311.08349","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["silversolver/ai_boundary_detection"],"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/exploring-semi-supervised-hierarchical","slug":"exploring-semi-supervised-hierarchical","title":"Exploring Semi-supervised Hierarchical Stacked Encoder for Legal Judgement Prediction","date":"2023-11-14","arxiv_id":"2311.08103","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-the-encoding-of-words-in-bert-s","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","date":"2023-11-14","arxiv_id":"2311.08240","n_code_links":0,"syntology":null},{"paper":"/paper/memory-efficient-stochastic-methods-for","slug":"memory-efficient-stochastic-methods-for","title":"Memory-efficient Stochastic methods for Memory-based Transformers","date":"2023-11-14","arxiv_id":"2311.08123","n_code_links":1,"syntology":null},{"paper":null,"slug":"teach-me-with-a-whisper-enhancing-large","title":"Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings","date":"2023-11-13","arxiv_id":"2311.07014","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-and-generative-approaches-for-a","title":"Retrieval and Generative Approaches for a Pregnancy Chatbot in Nepali with Stemmed and Non-Stemmed Data : A Comparative Study","date":"2023-11-12","arxiv_id":"2311.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"argumentation-element-annotation-modeling","title":"Argumentation Element Annotation Modeling using XLNet","date":"2023-11-10","arxiv_id":"2311.06239","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishing-performance-baselines-in-fine","title":"Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM Users","date":"2023-11-10","arxiv_id":"2311.05903","n_code_links":0,"syntology":null},{"paper":"/paper/deep-natural-language-feature-learning-for","slug":"deep-natural-language-feature-learning-for","title":"Deep Natural Language Feature Learning for Interpretable Prediction","date":"2023-11-09","arxiv_id":"2311.05754","n_code_links":1,"syntology":null},{"paper":null,"slug":"logshield-a-transformer-based-apt-detection","title":"LogShield: A Transformer-based APT Detection System Leveraging Self-Attention","date":"2023-11-09","arxiv_id":"2311.05733","n_code_links":0,"syntology":null},{"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":"an-ensemble-method-based-on-the-combination","title":"An Ensemble Method Based on the Combination of Transformers with Convolutional Neural Networks to Detect Artificially Generated Text","date":"2023-10-26","arxiv_id":"2310.17312","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":"exploring-graph-neural-networks-for-indian","title":"Exploring Graph Neural Networks for Indian Legal Judgment Prediction","date":"2023-10-19","arxiv_id":"2310.12800","n_code_links":0,"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":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}],"record_sha256":"3acc719c0723e78db53b7359f76e9d9b6460c756f770b0c9d68a91cacc95a683","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}