{"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/weight-decay/papers/48","list_of":"/method/weight-decay","method":"Weight 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":48,"pages_in_order":108,"rows_per_page":100,"rows":[4701,4800],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/weight-decay","prev":"/method/weight-decay/papers/47","next":"/method/weight-decay/papers/49","papers":[{"paper":null,"slug":"convolutional-neural-networks-for-sentiment-2","title":"Convolutional Neural Networks for Sentiment Analysis on Weibo Data: A Natural Language Processing Approach","date":"2023-07-13","arxiv_id":"2307.06540","n_code_links":0,"syntology":null},{"paper":"/paper/negated-complementary-commonsense-using-large","slug":"negated-complementary-commonsense-using-large","title":"Negated Complementary Commonsense using Large Language Models","date":"2023-07-13","arxiv_id":"2307.06794","n_code_links":1,"syntology":null},{"paper":null,"slug":"securefalcon-the-next-cyber-reasoning-system","title":"SecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?","date":"2023-07-13","arxiv_id":"2307.06616","n_code_links":0,"syntology":null},{"paper":"/paper/tackling-fake-news-in-bengali-unraveling-the","slug":"tackling-fake-news-in-bengali-unraveling-the","title":"Tackling Fake News in Bengali: Unraveling the Impact of Summarization vs. Augmentation on Pre-trained Language Models","date":"2023-07-13","arxiv_id":"2307.06979","n_code_links":1,"syntology":null},{"paper":"/paper/towards-populating-generalizable-engineering","slug":"towards-populating-generalizable-engineering","title":"Retrieval Augmented Generation using Engineering Design Knowledge","date":"2023-07-13","arxiv_id":"2307.06985","n_code_links":2,"syntology":null},{"paper":"/paper/ashaar-automatic-analysis-and-generation-of","slug":"ashaar-automatic-analysis-and-generation-of","title":"Ashaar: Automatic Analysis and Generation of Arabic Poetry Using Deep Learning Approaches","date":"2023-07-12","arxiv_id":"2307.06218","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-the-presence-of-covid-19","title":"Detecting the Presence of COVID-19 Vaccination Hesitancy from South African Twitter Data Using Machine Learning","date":"2023-07-12","arxiv_id":"2307.15072","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-large-language-models-for","title":"Distilling Large Language Models for Biomedical Knowledge Extraction: A Case Study on Adverse Drug Events","date":"2023-07-12","arxiv_id":"2307.06439","n_code_links":0,"syntology":null},{"paper":"/paper/no-train-no-gain-revisiting-efficient","slug":"no-train-no-gain-revisiting-efficient","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","date":"2023-07-12","arxiv_id":"2307.06440","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 3 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jeankaddour/notrainnogain"],"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","unlocated"]}}},{"paper":null,"slug":"online-laplace-model-selection-revisited","title":"Online Laplace Model Selection Revisited","date":"2023-07-12","arxiv_id":"2307.06093","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-generate-train-pgt-a-framework-for-few","title":"Prompt Generate Train (PGT): Few-shot Domain Adaption of Retrieval Augmented Generation Models for Open Book Question-Answering","date":"2023-07-12","arxiv_id":"2307.05915","n_code_links":0,"syntology":null},{"paper":null,"slug":"argumentative-segmentation-enhancement-for","title":"Argumentative Segmentation Enhancement for Legal Summarization","date":"2023-07-11","arxiv_id":"2307.05081","n_code_links":0,"syntology":null},{"paper":null,"slug":"dnagpt-a-generalized-pretrained-tool-for","title":"DNAGPT: A Generalized Pre-trained Tool for Versatile DNA Sequence Analysis Tasks","date":"2023-07-11","arxiv_id":"2307.05628","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models","title":"Large Language Models","date":"2023-07-11","arxiv_id":"2307.05782","n_code_links":0,"syntology":null},{"paper":null,"slug":"named-entity-recognition-using-gpt-for","title":"Named entity recognition using GPT for identifying comparable companies","date":"2023-07-11","arxiv_id":"2307.07420","n_code_links":0,"syntology":null},{"paper":null,"slug":"safe-reinforcement-learning-for-strategic","title":"Safe Reinforcement Learning for Strategic Bidding of Virtual Power Plants in Day-Ahead Markets","date":"2023-07-11","arxiv_id":"2307.05812","n_code_links":0,"syntology":null},{"paper":"/paper/unleashing-cognitive-synergy-in-large","slug":"unleashing-cognitive-synergy-in-large","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","date":"2023-07-11","arxiv_id":"2307.05300","n_code_links":2,"syntology":null},{"paper":null,"slug":"vacaspati-a-diverse-corpus-of-bangla","title":"Vacaspati: A Diverse Corpus of Bangla Literature","date":"2023-07-11","arxiv_id":"2307.05083","n_code_links":0,"syntology":null},{"paper":"/paper/amadeusgpt-a-natural-language-interface-for-1","slug":"amadeusgpt-a-natural-language-interface-for-1","title":"AmadeusGPT: a natural language interface for interactive animal behavioral analysis","date":"2023-07-10","arxiv_id":"2307.04858","n_code_links":1,"syntology":null},{"paper":"/paper/chatgpt-for-digital-forensic-investigation","slug":"chatgpt-for-digital-forensic-investigation","title":"ChatGPT for Digital Forensic Investigation: The Good, The Bad, and The Unknown","date":"2023-07-10","arxiv_id":"2307.10195","n_code_links":1,"syntology":null},{"paper":null,"slug":"simplemtod-a-simple-language-model-for","title":"SimpleMTOD: A Simple Language Model for Multimodal Task-Oriented Dialogue with Symbolic Scene Representation","date":"2023-07-10","arxiv_id":"2307.04907","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-efficacy-of-large-language","title":"Assessing the efficacy of large language models in generating accurate teacher responses","date":"2023-07-09","arxiv_id":"2307.04274","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-stitch-in-time-saves-nine-detecting-and","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","date":"2023-07-08","arxiv_id":"2307.03987","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-chatgpt-a-good-personality-recognizer-a","title":"Is ChatGPT a Good Personality Recognizer? A Preliminary Study","date":"2023-07-08","arxiv_id":"2307.03952","n_code_links":0,"syntology":null},{"paper":"/paper/dwreco-at-checkthat-2023-enhancing","slug":"dwreco-at-checkthat-2023-enhancing","title":"DWReCO at CheckThat! 2023: Enhancing Subjectivity Detection through Style-based Data Sampling","date":"2023-07-07","arxiv_id":"2307.03550","n_code_links":1,"syntology":null},{"paper":null,"slug":"goal-conditioned-predictive-coding-as-an","title":"Goal-Conditioned Predictive Coding for Offline Reinforcement Learning","date":"2023-07-07","arxiv_id":"2307.03406","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-ai-chat-change-search-behaviors","title":"How does AI chat change search behaviors?","date":"2023-07-07","arxiv_id":"2307.03826","n_code_links":0,"syntology":null},{"paper":null,"slug":"radar-robust-ai-text-detection-via","title":"RADAR: Robust AI-Text Detection via Adversarial Learning","date":"2023-07-07","arxiv_id":"2307.03838","n_code_links":0,"syntology":null},{"paper":"/paper/trac-trustworthy-retrieval-augmented-chatbot","slug":"trac-trustworthy-retrieval-augmented-chatbot","title":"TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction","date":"2023-07-07","arxiv_id":"2307.04642","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-site-agnostic-multimodal-deep","title":"A Novel Site-Agnostic Multimodal Deep Learning Model to Identify Pro-Eating Disorder Content on Social Media","date":"2023-07-06","arxiv_id":"2307.06775","n_code_links":0,"syntology":null},{"paper":"/paper/can-chatgpt-s-responses-boost-traditional","slug":"can-chatgpt-s-responses-boost-traditional","title":"Can ChatGPT's Responses Boost Traditional Natural Language Processing?","date":"2023-07-06","arxiv_id":"2307.04648","n_code_links":1,"syntology":null},{"paper":"/paper/improving-retrieval-augmented-large-language","slug":"improving-retrieval-augmented-large-language","title":"Improving Retrieval-Augmented Large Language Models via Data Importance Learning","date":"2023-07-06","arxiv_id":"2307.03027","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["amsterdata/ragbooster"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-empowered-autonomous","title":"Large Language Models Empowered Autonomous Edge AI for Connected Intelligence","date":"2023-07-06","arxiv_id":"2307.02779","n_code_links":0,"syntology":null},{"paper":"/paper/text-alignment-is-an-efficient-unified-model","slug":"text-alignment-is-an-efficient-unified-model","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","date":"2023-07-06","arxiv_id":"2307.02729","n_code_links":1,"syntology":null},{"paper":null,"slug":"uit-saviors-at-medvqa-gi-2023-improving","title":"UIT-Saviors at MEDVQA-GI 2023: Improving Multimodal Learning with Image Enhancement for Gastrointestinal Visual Question Answering","date":"2023-07-06","arxiv_id":"2307.02783","n_code_links":0,"syntology":null},{"paper":"/paper/came-confidence-guided-adaptive-memory","slug":"came-confidence-guided-adaptive-memory","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","date":"2023-07-05","arxiv_id":"2307.02047","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["yangluo7/came","huawei-noah/Pretrained-Language-Model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/emoji-prediction-using-transformer-models","slug":"emoji-prediction-using-transformer-models","title":"Emoji Prediction in Tweets using BERT","date":"2023-07-05","arxiv_id":"2307.02054","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-effectiveness-of-large","title":"Evaluating the Effectiveness of Large Language Models in Representing Textual Descriptions of Geometry and Spatial Relations","date":"2023-07-05","arxiv_id":"2307.03678","n_code_links":0,"syntology":null},{"paper":"/paper/external-reasoning-towards-multi-large","slug":"external-reasoning-towards-multi-large","title":"External Reasoning: Towards Multi-Large-Language-Models Interchangeable Assistance with Human Feedback","date":"2023-07-05","arxiv_id":"2307.12057","n_code_links":1,"syntology":null},{"paper":"/paper/hoodwinked-deception-and-cooperation-in-a","slug":"hoodwinked-deception-and-cooperation-in-a","title":"Hoodwinked: Deception and Cooperation in a Text-Based Game for Language Models","date":"2023-07-05","arxiv_id":"2308.01404","n_code_links":1,"syntology":null},{"paper":"/paper/multilingual-controllable-transformer-based","slug":"multilingual-controllable-transformer-based","title":"Multilingual Controllable Transformer-Based Lexical Simplification","date":"2023-07-05","arxiv_id":"2307.02120","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-inclusion-in-abstractive-text-1","title":"Named Entity Inclusion in Abstractive Text Summarization","date":"2023-07-05","arxiv_id":"2307.02570","n_code_links":0,"syntology":null},{"paper":null,"slug":"open-source-large-language-models-outperform","title":"Open-Source LLMs for Text Annotation: A Practical Guide for Model Setting and Fine-Tuning","date":"2023-07-05","arxiv_id":"2307.02179","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-formai-dataset-generative-ai-in-software","title":"The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification","date":"2023-07-05","arxiv_id":"2307.02192","n_code_links":0,"syntology":null},{"paper":"/paper/embodied-task-planning-with-large-language","slug":"embodied-task-planning-with-large-language","title":"Embodied Task Planning with Large Language Models","date":"2023-07-04","arxiv_id":"2307.01848","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":["Gary3410/TaPA"],"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":"/paper/kdstm-neural-semi-supervised-topic-modeling","slug":"kdstm-neural-semi-supervised-topic-modeling","title":"KDSTM: Neural Semi-supervised Topic Modeling with Knowledge Distillation","date":"2023-07-04","arxiv_id":"2307.01878","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"nonparametric-classification-on-low","title":"Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks","date":"2023-07-04","arxiv_id":"2307.01649","n_code_links":0,"syntology":null},{"paper":null,"slug":"alberti-a-multilingual-domain-specific","title":"ALBERTI, a Multilingual Domain Specific Language Model for Poetry Analysis","date":"2023-07-03","arxiv_id":"2307.01387","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-plasticity-via-pretraining","slug":"improving-language-plasticity-via-pretraining","title":"Improving Language Plasticity via Pretraining with Active Forgetting","date":"2023-07-03","arxiv_id":"2307.01163","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretability-and-transparency-driven","title":"Interpretability and Transparency-Driven Detection and Transformation of Textual Adversarial Examples (IT-DT)","date":"2023-07-03","arxiv_id":"2307.01225","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-zero-shot-llm-prompting-for","title":"Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction","date":"2023-07-03","arxiv_id":"2307.01128","n_code_links":0,"syntology":null},{"paper":null,"slug":"tensorgpt-efficient-compression-of-the","title":"TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition","date":"2023-07-02","arxiv_id":"2307.00526","n_code_links":0,"syntology":null},{"paper":"/paper/how-far-is-language-model-from-100-few-shot","slug":"how-far-is-language-model-from-100-few-shot","title":"How far is Language Model from 100% Few-shot Named Entity Recognition in Medical Domain","date":"2023-07-01","arxiv_id":"2307.00186","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-for-automating","title":"Large Language Models (GPT) for automating feedback on programming assignments","date":"2023-06-30","arxiv_id":"2307.00150","n_code_links":0,"syntology":null},{"paper":"/paper/meta-reasoning-semantics-symbol","slug":"meta-reasoning-semantics-symbol","title":"Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models","date":"2023-06-30","arxiv_id":"2306.17820","n_code_links":1,"syntology":null},{"paper":null,"slug":"spae-semantic-pyramid-autoencoder-for","title":"SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs","date":"2023-06-30","arxiv_id":"2306.17842","n_code_links":0,"syntology":null},{"paper":"/paper/stay-on-topic-with-classifier-free-guidance","slug":"stay-on-topic-with-classifier-free-guidance","title":"Stay on topic with Classifier-Free Guidance","date":"2023-06-30","arxiv_id":"2306.17806","n_code_links":0,"syntology":null},{"paper":null,"slug":"ticket-bert-labeling-incident-management","title":"Ticket-BERT: Labeling Incident Management Tickets with Language Models","date":"2023-06-30","arxiv_id":"2307.00108","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-negation-detection-assessment-of-gpts","title":"A negation detection assessment of GPTs: analysis with the xNot360 dataset","date":"2023-06-29","arxiv_id":"2306.16638","n_code_links":0,"syntology":null},{"paper":null,"slug":"benchmarking-large-language-model","title":"Benchmarking Large Language Model Capabilities for Conditional Generation","date":"2023-06-29","arxiv_id":"2306.16793","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-crime-types-using-judgment","title":"Classifying Crime Types using Judgment Documents from Social Media","date":"2023-06-29","arxiv_id":"2306.17020","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-for-programming-education","title":"Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors","date":"2023-06-29","arxiv_id":"2306.17156","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-hugging-face","title":"Harnessing the Power of Hugging Face Transformers for Predicting Mental Health Disorders in Social Networks","date":"2023-06-29","arxiv_id":"2306.16891","n_code_links":0,"syntology":null},{"paper":null,"slug":"safety-aware-task-composition-for-discrete","title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning","date":"2023-06-29","arxiv_id":"2306.17033","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-model-soups-a-recipe-for-improved","slug":"sparse-model-soups-a-recipe-for-improved","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","date":"2023-06-29","arxiv_id":"2306.16788","n_code_links":1,"syntology":null},{"paper":null,"slug":"spectral-batch-normalization-normalization-in","title":"Spectral Batch Normalization: Normalization in the Frequency Domain","date":"2023-06-29","arxiv_id":"2306.16999","n_code_links":0,"syntology":null},{"paper":null,"slug":"action-and-trajectory-planning-for-urban","title":"Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning","date":"2023-06-28","arxiv_id":"2306.15968","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-sparse-inference-software","slug":"an-efficient-sparse-inference-software","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","date":"2023-06-28","arxiv_id":"2306.16601","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-calibration-and-error-correction","title":"Pareto Optimal Learning for Estimating Large Language Model Errors","date":"2023-06-28","arxiv_id":"2306.16564","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-the-hype-assessing-the-performance","title":"Beyond the Hype: Assessing the Performance, Trustworthiness, and Clinical Suitability of GPT3.5","date":"2023-06-28","arxiv_id":"2306.15887","n_code_links":0,"syntology":null},{"paper":null,"slug":"inferring-the-goals-of-communicating-agents","title":"Inferring the Goals of Communicating Agents from Actions and Instructions","date":"2023-06-28","arxiv_id":"2306.16207","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-biomedical-expert-exploring-the","slug":"is-chatgpt-a-biomedical-expert-exploring-the","title":"Is ChatGPT a Biomedical Expert? -- Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2023-06-28","arxiv_id":"2306.16108","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-site-clinical-federated-learning-using","title":"Multi-Site Clinical Federated Learning using Recursive and Attentive Models and NVFlare","date":"2023-06-28","arxiv_id":"2306.16367","n_code_links":0,"syntology":null},{"paper":"/paper/taqyim-evaluating-arabic-nlp-tasks-using","slug":"taqyim-evaluating-arabic-nlp-tasks-using","title":"Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models","date":"2023-06-28","arxiv_id":"2306.16322","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-gpt-3-5-and-gpt-4-on-grammatical","title":"Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese","date":"2023-06-27","arxiv_id":"2306.15788","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-in-bert-measuring-and-analysing-1","title":"Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task","date":"2023-06-27","arxiv_id":"2306.15298","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-cross-domain-behaviors-of-bert","title":"Investigating Cross-Domain Behaviors of BERT in Review Understanding","date":"2023-06-27","arxiv_id":"2306.15123","n_code_links":0,"syntology":null},{"paper":null,"slug":"mat-mixed-strategy-game-of-adversarial","title":"MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning","date":"2023-06-27","arxiv_id":"2306.15826","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparseoptimizer-sparsify-language-models","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","date":"2023-06-27","arxiv_id":"2306.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-power-of-user-reviews","title":"Unleashing the Power of User Reviews: Exploring Airline Choices at Catania Airport, Italy","date":"2023-06-27","arxiv_id":"2306.15541","n_code_links":0,"syntology":null},{"paper":"/paper/constraint-aware-and-ranking-distilled-token","slug":"constraint-aware-and-ranking-distilled-token","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","date":"2023-06-26","arxiv_id":"2306.14393","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-robustness-of-large-language","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","date":"2023-06-26","arxiv_id":"2306.14583","n_code_links":0,"syntology":null},{"paper":"/paper/longcoder-a-long-range-pre-trained-language","slug":"longcoder-a-long-range-pre-trained-language","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","date":"2023-06-26","arxiv_id":"2306.14893","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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) · 0 unverified","official":{"repos":["microsoft/CodeBERT"],"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":"addressing-cold-start-problem-for-end-to-end","title":"Addressing Cold Start Problem for End-to-end Automatic Speech Scoring","date":"2023-06-25","arxiv_id":"2306.14310","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-design-by-integrating-a-large-pre","title":"Interactive Design by Integrating a Large Pre-Trained Language Model and Building Information Modeling","date":"2023-06-25","arxiv_id":"2306.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"let-s-do-a-thought-experiment-using","title":"Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning","date":"2023-06-25","arxiv_id":"2306.14308","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-cyber-threat-detection-with","title":"Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices","date":"2023-06-25","arxiv_id":"2306.14263","n_code_links":0,"syntology":null},{"paper":null,"slug":"switch-bert-learning-to-model-multimodal","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","date":"2023-06-25","arxiv_id":"2306.14182","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-pre-trained-language-models-for","title":"Comparison of Pre-trained Language Models for Turkish Address Parsing","date":"2023-06-24","arxiv_id":"2306.13947","n_code_links":0,"syntology":null},{"paper":null,"slug":"ierl-interpretable-ensemble-representation","title":"IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations","date":"2023-06-24","arxiv_id":"2306.13865","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-pre-training-truly-better-than-meta","title":"Is Pre-training Truly Better Than Meta-Learning?","date":"2023-06-24","arxiv_id":"2306.13841","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahasent-md-a-multi-domain-marathi","slug":"l3cube-mahasent-md-a-multi-domain-marathi","title":"L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models","date":"2023-06-24","arxiv_id":"2306.13888","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-as-sous-chefs-revising","slug":"large-language-models-as-sous-chefs-revising","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","date":"2023-06-24","arxiv_id":"2306.13986","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-sequence-models-for-sequential-decision","title":"Large Sequence Models for Sequential Decision-Making: A Survey","date":"2023-06-24","arxiv_id":"2306.13945","n_code_links":0,"syntology":null},{"paper":"/paper/math-word-problem-solving-by-generating","slug":"math-word-problem-solving-by-generating","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","date":"2023-06-24","arxiv_id":"2306.13899","n_code_links":1,"syntology":null},{"paper":"/paper/my-boli-code-mixed-marathi-english-corpora","slug":"my-boli-code-mixed-marathi-english-corpora","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","date":"2023-06-24","arxiv_id":"2306.14030","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-uses-of-large-language-models-to","title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","date":"2023-06-24","arxiv_id":"2306.14062","n_code_links":0,"syntology":null},{"paper":null,"slug":"partitioning-guided-k-means-extreme-empty","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","date":"2023-06-24","arxiv_id":"2306.14031","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-assisted-content-analysis-using-large","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","date":"2023-06-23","arxiv_id":"2306.14924","n_code_links":0,"syntology":null},{"paper":null,"slug":"resume-information-extraction-via-post-ocr","title":"Resume Information Extraction via Post-OCR Text Processing","date":"2023-06-23","arxiv_id":"2306.13775","n_code_links":0,"syntology":null}],"record_sha256":"cb16b676d7abe602c42a1ae17e35cd53eaa37fbc8d941a0f820a74b5f7f15ee3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}