{"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/55","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":55,"pages_in_order":108,"rows_per_page":100,"rows":[5401,5500],"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/54","next":"/method/weight-decay/papers/56","papers":[{"paper":"/paper/autoad-movie-description-in-context","slug":"autoad-movie-description-in-context","title":"AutoAD: Movie Description in Context","date":"2023-03-29","arxiv_id":"2303.16899","n_code_links":1,"syntology":{"ran":5,"of":13,"n_ran_checked":3,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["Soldelli/MAD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/bert4eth-a-pre-trained-transformer-for","slug":"bert4eth-a-pre-trained-transformer-for","title":"BERT4ETH: A Pre-trained Transformer for Ethereum Fraud Detection","date":"2023-03-29","arxiv_id":"2303.18138","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-gpt-3-5-and-gpt-4-models-on","slug":"evaluating-gpt-3-5-and-gpt-4-models-on","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","date":"2023-03-29","arxiv_id":"2303.17003","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":6,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["piresramon/gpt-4-enem"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-do-decoding-algorithms-distribute","title":"How do decoding algorithms distribute information in dialogue responses?","date":"2023-03-29","arxiv_id":"2303.17006","n_code_links":0,"syntology":null},{"paper":"/paper/larger-probes-tell-a-different-story","slug":"larger-probes-tell-a-different-story","title":"Larger Probes Tell a Different Story: Extending Psycholinguistic Datasets Via In-Context Learning","date":"2023-03-29","arxiv_id":"2303.16445","n_code_links":1,"syntology":null},{"paper":"/paper/ten-quick-tips-for-harnessing-the-power-of","slug":"ten-quick-tips-for-harnessing-the-power-of","title":"Ten Quick Tips for Harnessing the Power of ChatGPT/GPT-4 in Computational Biology","date":"2023-03-29","arxiv_id":"2303.16429","n_code_links":1,"syntology":null},{"paper":"/paper/viewrefer-grasp-the-multi-view-knowledge-for","slug":"viewrefer-grasp-the-multi-view-knowledge-for","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","date":"2023-03-29","arxiv_id":"2303.16894","n_code_links":7,"syntology":{"ran":8,"of":12,"n_ran_checked":6,"n_instrument":2,"unverified":4,"pointer_only":12,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ivan-tang-3d/viewrefer3d","ziyuguo99/viewrefer3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/zero-shot-clinical-entity-recognition-using","slug":"zero-shot-clinical-entity-recognition-using","title":"Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering","date":"2023-03-29","arxiv_id":"2303.16416","n_code_links":1,"syntology":null},{"paper":"/paper/explicit-planning-helps-language-models-in","slug":"explicit-planning-helps-language-models-in","title":"Explicit Planning Helps Language Models in Logical Reasoning","date":"2023-03-28","arxiv_id":"2303.15714","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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["cindermond/explicit-planning-for-reasoning","cindermond/leap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-codex-prompt-engineering-for-ocl","title":"On Codex Prompt Engineering for OCL Generation: An Empirical Study","date":"2023-03-28","arxiv_id":"2303.16244","n_code_links":0,"syntology":null},{"paper":"/paper/zero-shot-generalizable-end-to-end-task","slug":"zero-shot-generalizable-end-to-end-task","title":"Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema","date":"2023-03-28","arxiv_id":"2303.16252","n_code_links":1,"syntology":null},{"paper":"/paper/kpeval-towards-fine-grained-semantic-based","slug":"kpeval-towards-fine-grained-semantic-based","title":"KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation","date":"2023-03-27","arxiv_id":"2303.15422","n_code_links":1,"syntology":null},{"paper":null,"slug":"textmi-textualize-multimodal-information-for","title":"TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models","date":"2023-03-27","arxiv_id":"2303.15430","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-multimodal-sentiment-analysis-via","title":"Exploring Multimodal Sentiment Analysis via CBAM Attention and Double-layer BiLSTM Architecture","date":"2023-03-26","arxiv_id":"2303.14708","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-gpt-3-s-performance-in","title":"Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction","date":"2023-03-25","arxiv_id":"2303.14342","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-models-assist-in-hazard","title":"Can Large Language Models assist in Hazard Analysis?","date":"2023-03-25","arxiv_id":"2303.15473","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-is-becoming-a-turing-machine-here-are","title":"GPT is becoming a Turing machine: Here are some ways to program it","date":"2023-03-25","arxiv_id":"2303.14310","n_code_links":0,"syntology":null},{"paper":"/paper/indonesian-text-to-image-synthesis-with","slug":"indonesian-text-to-image-synthesis-with","title":"Indonesian Text-to-Image Synthesis with Sentence-BERT and FastGAN","date":"2023-03-25","arxiv_id":"2303.14517","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatio-temporal-driven-attention-graph-neural","title":"Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA)","date":"2023-03-25","arxiv_id":"2303.14322","n_code_links":0,"syntology":null},{"paper":null,"slug":"depression-detection-in-social-media-posts","title":"Depression detection in social media posts using affective and social norm features","date":"2023-03-24","arxiv_id":"2303.14279","n_code_links":0,"syntology":null},{"paper":"/paper/get-ready-for-a-party-exploring-smarter-smart","slug":"get-ready-for-a-party-exploring-smarter-smart","title":"\"Get ready for a party\": Exploring smarter smart spaces with help from large language models","date":"2023-03-24","arxiv_id":"2303.14143","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalizing-task-oriented-dialog-systems","title":"Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function","date":"2023-03-24","arxiv_id":"2303.13797","n_code_links":0,"syntology":null},{"paper":null,"slug":"seal-semantic-frame-execution-and","title":"SEAL: Semantic Frame Execution And Localization for Perceiving Afforded Robot Actions","date":"2023-03-24","arxiv_id":"2303.14067","n_code_links":0,"syntology":null},{"paper":"/paper/sigmorphon-2023-shared-task-of-interlinear","slug":"sigmorphon-2023-shared-task-of-interlinear","title":"SIGMORPHON 2023 Shared Task of Interlinear Glossing: Baseline Model","date":"2023-03-24","arxiv_id":"2303.14234","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-open-domain-slot-filling-via-self","title":"Toward Open-domain Slot Filling via Self-supervised Co-training","date":"2023-03-24","arxiv_id":"2303.13801","n_code_links":0,"syntology":null},{"paper":"/paper/where-to-go-next-for-recommender-systems-id","slug":"where-to-go-next-for-recommender-systems-id","title":"Where to Go Next for Recommender Systems? ID- vs. Modality-based Recommender Models Revisited","date":"2023-03-24","arxiv_id":"2303.13835","n_code_links":1,"syntology":null},{"paper":"/paper/a-novel-patent-similarity-measurement","slug":"a-novel-patent-similarity-measurement","title":"A Novel Patent Similarity Measurement Methodology: Semantic Distance and Technological Distance","date":"2023-03-23","arxiv_id":"2303.16767","n_code_links":1,"syntology":null},{"paper":null,"slug":"gesgpt-speech-gesture-synthesis-with-text","title":"GesGPT: Speech Gesture Synthesis With Text Parsing from ChatGPT","date":"2023-03-23","arxiv_id":"2303.13013","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-classification-with","slug":"retrieval-augmented-classification-with","title":"Retrieval-Augmented Classification with Decoupled Representation","date":"2023-03-23","arxiv_id":"2303.13065","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-the-generalizability-of-deep","title":"Analyzing the Generalizability of Deep Contextualized Language Representations For Text Classification","date":"2023-03-22","arxiv_id":"2303.12936","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-labeled-training-data-using-prompt","title":"Generate labeled training data using Prompt Programming and GPT-3. An example of Big Five Personality Classification","date":"2023-03-22","arxiv_id":"2303.12279","n_code_links":0,"syntology":null},{"paper":null,"slug":"tron-transformer-neural-network-acceleration","title":"TRON: Transformer Neural Network Acceleration with Non-Coherent Silicon Photonics","date":"2023-03-22","arxiv_id":"2303.12914","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-complete-survey-on-generative-ai-aigc-is","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","date":"2023-03-21","arxiv_id":"2303.11717","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-and-a-new-academic-reality-ai-written","title":"ChatGPT and a New Academic Reality: Artificial Intelligence-Written Research Papers and the Ethics of the Large Language Models in Scholarly Publishing","date":"2023-03-21","arxiv_id":"2303.13367","n_code_links":0,"syntology":null},{"paper":"/paper/ctbl-augmenting-large-language-models-for","slug":"ctbl-augmenting-large-language-models-for","title":"cTBLS: Augmenting Large Language Models with Conversational Tables","date":"2023-03-21","arxiv_id":"2303.12024","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-climatebert-transformer-with","title":"Fine-tuning ClimateBert transformer with ClimaText for the disclosure analysis of climate-related financial risks","date":"2023-03-21","arxiv_id":"2303.13373","n_code_links":0,"syntology":null},{"paper":"/paper/is-bert-blind-exploring-the-effect-of-vision","slug":"is-bert-blind-exploring-the-effect-of-vision","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","date":"2023-03-21","arxiv_id":"2303.12513","n_code_links":1,"syntology":null},{"paper":"/paper/learning-a-sparse-transformer-network-for","slug":"learning-a-sparse-transformer-network-for","title":"Learning A Sparse Transformer Network for Effective Image Deraining","date":"2023-03-21","arxiv_id":"2303.11950","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 8 samples that ran constructed an object rather than computing a result","official":{"repos":["cschenxiang/drsformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multimodal-pre-training-framework-for","title":"Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning","date":"2023-03-21","arxiv_id":"2303.11879","n_code_links":0,"syntology":null},{"paper":"/paper/sift-sparse-iso-flop-transformations-for","slug":"sift-sparse-iso-flop-transformations-for","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","date":"2023-03-21","arxiv_id":"2303.11525","n_code_links":2,"syntology":{"ran":21,"of":24,"n_ran_checked":20,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cerebrasresearch/sift","cerebrasresearch/sparse-ift"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/capabilities-of-gpt-4-on-medical-challenge","slug":"capabilities-of-gpt-4-on-medical-challenge","title":"Capabilities of GPT-4 on Medical Challenge Problems","date":"2023-03-20","arxiv_id":"2303.13375","n_code_links":1,"syntology":null},{"paper":"/paper/character-word-or-both-revisiting-the","slug":"character-word-or-both-revisiting-the","title":"Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models","date":"2023-03-20","arxiv_id":"2303.10893","n_code_links":1,"syntology":null},{"paper":null,"slug":"mind-meets-machine-unravelling-gpt-4-s","title":"Mind meets machine: Unravelling GPT-4's cognitive psychology","date":"2023-03-20","arxiv_id":"2303.11436","n_code_links":0,"syntology":null},{"paper":"/paper/ctran-cnn-transformer-based-network-for","slug":"ctran-cnn-transformer-based-network-for","title":"CTRAN: CNN-Transformer-based Network for Natural Language Understanding","date":"2023-03-19","arxiv_id":"2303.10606","n_code_links":1,"syntology":null},{"paper":null,"slug":"paco-provocation-involving-action-culture-and","title":"PACO: Provocation Involving Action, Culture, and Oppression","date":"2023-03-19","arxiv_id":"2303.12808","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-capability-analysis-of-gpt-3","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","date":"2023-03-18","arxiv_id":"2303.10420","n_code_links":0,"syntology":null},{"paper":"/paper/an-empirical-study-of-pre-trained-language","slug":"an-empirical-study-of-pre-trained-language","title":"An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering","date":"2023-03-18","arxiv_id":"2303.10368","n_code_links":1,"syntology":null},{"paper":null,"slug":"noisyhate-benchmarking-content-moderation","title":"NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Models","date":"2023-03-18","arxiv_id":"2303.10430","n_code_links":0,"syntology":null},{"paper":null,"slug":"spdf-sparse-pre-training-and-dense-fine","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","date":"2023-03-18","arxiv_id":"2303.10464","n_code_links":0,"syntology":null},{"paper":"/paper/gadformer-an-attention-based-model-for-group","slug":"gadformer-an-attention-based-model-for-group","title":"GADformer: A Transparent Transformer Model for Group Anomaly Detection on Trajectories","date":"2023-03-17","arxiv_id":"2303.09841","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpts-are-gpts-an-early-look-at-the-labor","title":"GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models","date":"2023-03-17","arxiv_id":"2303.10130","n_code_links":0,"syntology":null},{"paper":"/paper/trained-on-100-million-words-and-still-in","slug":"trained-on-100-million-words-and-still-in","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","date":"2023-03-17","arxiv_id":"2303.09859","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["ltgoslo/ltg-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"block-wise-bit-compression-of-transformer","title":"Block-wise Bit-Compression of Transformer-based Models","date":"2023-03-16","arxiv_id":"2303.09184","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-generative-pre-trained-transformers-gpt","title":"Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?","date":"2023-03-16","arxiv_id":"2303.09325","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-management-of-multi-mode-plug-in","title":"Energy Management of Multi-mode Plug-in Hybrid Electric Vehicle using Multi-agent Deep Reinforcement Learning","date":"2023-03-16","arxiv_id":"2303.09658","n_code_links":0,"syntology":null},{"paper":"/paper/jump-to-conclusions-short-cutting","slug":"jump-to-conclusions-short-cutting","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","date":"2023-03-16","arxiv_id":"2303.09435","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sashayd/mat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"measuring-improvement-of-f-1-scores-in","title":"Measuring Improvement of F$_1$-Scores in Detection of Self-Admitted Technical Debt","date":"2023-03-16","arxiv_id":"2303.09617","n_code_links":0,"syntology":null},{"paper":"/paper/smartbert-a-promotion-of-dynamic-early","slug":"smartbert-a-promotion-of-dynamic-early","title":"SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference","date":"2023-03-16","arxiv_id":"2303.09266","n_code_links":0,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"towards-the-scalable-evaluation-of","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","date":"2023-03-16","arxiv_id":"2303.13360","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-interactive-domain-specific","title":"Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs","date":"2023-03-15","arxiv_id":"2303.08941","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-uncertainty-estimation-with","title":"Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response Retrieval","date":"2023-03-15","arxiv_id":"2303.08599","n_code_links":0,"syntology":null},{"paper":null,"slug":"gcre-gpt-a-generative-model-for-comparative","title":"GCRE-GPT: A Generative Model for Comparative Relation Extraction","date":"2023-03-15","arxiv_id":"2303.08601","n_code_links":0,"syntology":null},{"paper":"/paper/selfcheckgpt-zero-resource-black-box","slug":"selfcheckgpt-zero-resource-black-box","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","date":"2023-03-15","arxiv_id":"2303.08896","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":3,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["potsawee/selfcheckgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"do-transformers-parse-while-predicting-the","title":"Do Transformers Parse while Predicting the Masked Word?","date":"2023-03-14","arxiv_id":"2303.08117","n_code_links":0,"syntology":null},{"paper":"/paper/evaluation-of-chatgpt-as-a-question-answering","slug":"evaluation-of-chatgpt-as-a-question-answering","title":"Can ChatGPT Replace Traditional KBQA Models? An In-depth Analysis of the Question Answering Performance of the GPT LLM Family","date":"2023-03-14","arxiv_id":"2303.07992","n_code_links":2,"syntology":null},{"paper":null,"slug":"features-matching-using-natural-language","title":"Features matching using natural language processing","date":"2023-03-14","arxiv_id":"2303.12804","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-the-needle-in-a-haystack-unsupervised","title":"Finding the Needle in a Haystack: Unsupervised Rationale Extraction from Long Text Classifiers","date":"2023-03-14","arxiv_id":"2303.07991","n_code_links":0,"syntology":null},{"paper":null,"slug":"medbert-de-a-comprehensive-german-bert-model","title":"MEDBERT.de: A Comprehensive German BERT Model for the Medical Domain","date":"2023-03-14","arxiv_id":"2303.08179","n_code_links":0,"syntology":null},{"paper":"/paper/neuro-symbolic-commonsense-social-reasoning","slug":"neuro-symbolic-commonsense-social-reasoning","title":"Neuro-symbolic Commonsense Social Reasoning","date":"2023-03-14","arxiv_id":"2303.08264","n_code_links":3,"syntology":null},{"paper":null,"slug":"re-move-an-adaptive-policy-design-approach","title":"RE-MOVE: An Adaptive Policy Design for Robotic Navigation Tasks in Dynamic Environments via Language-Based Feedback","date":"2023-03-14","arxiv_id":"2303.07622","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-approach-for-classifying-the","title":"Deep Learning Approach for Classifying the Aggressive Comments on Social Media: Machine Translated Data Vs Real Life Data","date":"2023-03-13","arxiv_id":"2303.07484","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-the-workplace-a-case","title":"Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification","date":"2023-03-13","arxiv_id":"2303.07142","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-approaches-to-sentiment","title":"Transformer-based approaches to Sentiment Detection","date":"2023-03-13","arxiv_id":"2303.07292","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-know-your-contextual","slug":"large-language-models-know-your-contextual","title":"Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search","date":"2023-03-12","arxiv_id":"2303.06573","n_code_links":2,"syntology":null},{"paper":"/paper/luke-graph-a-transformer-based-approach-with","slug":"luke-graph-a-transformer-based-approach-with","title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","date":"2023-03-12","arxiv_id":"2303.06675","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-combinatorial-prompts-for-universal","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","date":"2023-03-11","arxiv_id":"2303.06338","n_code_links":0,"syntology":null},{"paper":null,"slug":"algorithmic-ghost-in-the-research-shell-large","title":"Algorithmic Ghost in the Research Shell: Large Language Models and Academic Knowledge Creation in Management Research","date":"2023-03-10","arxiv_id":"2303.07304","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-in-hospital-meta-information-useful-for","title":"Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?","date":"2023-03-10","arxiv_id":"2303.06002","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-cpi-prediction-based-on-natural","title":"Research on CPI Prediction Based on Natural Language Processing","date":"2023-03-10","arxiv_id":"2303.05666","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-may-pass-the-bar-exam-soon-but-has-a","slug":"chatgpt-may-pass-the-bar-exam-soon-but-has-a","title":"ChatGPT may Pass the Bar Exam soon, but has a Long Way to Go for the LexGLUE benchmark","date":"2023-03-09","arxiv_id":"2304.12202","n_code_links":1,"syntology":null},{"paper":"/paper/icl-d3ie-in-context-learning-with-diverse","slug":"icl-d3ie-in-context-learning-with-diverse","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","date":"2023-03-09","arxiv_id":"2303.05063","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-gpt-struggle-to-answer","title":"Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code","date":"2023-03-09","arxiv_id":"2303.08033","n_code_links":0,"syntology":null},{"paper":"/paper/chatgpt-participates-in-a-computer-science","slug":"chatgpt-participates-in-a-computer-science","title":"ChatGPT Participates in a Computer Science Exam","date":"2023-03-08","arxiv_id":"2303.09461","n_code_links":1,"syntology":null},{"paper":"/paper/cost-effective-hyperparameter-optimization","slug":"cost-effective-hyperparameter-optimization","title":"Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference","date":"2023-03-08","arxiv_id":"2303.04673","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/FLAML"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/on-the-risks-of-stealing-the-decoding","slug":"on-the-risks-of-stealing-the-decoding","title":"Stealing the Decoding Algorithms of Language Models","date":"2023-03-08","arxiv_id":"2303.04729","n_code_links":1,"syntology":null},{"paper":"/paper/a-comprehensive-survey-of-ai-generated","slug":"a-comprehensive-survey-of-ai-generated","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","date":"2023-03-07","arxiv_id":"2303.04226","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-strategy-oriented-bayesian-soft-actor","title":"A Strategy-Oriented Bayesian Soft Actor-Critic Model","date":"2023-03-07","arxiv_id":"2303.04193","n_code_links":0,"syntology":null},{"paper":null,"slug":"adelt-transpilation-between-deep-learning","title":"ADELT: Transpilation Between Deep Learning Frameworks","date":"2023-03-07","arxiv_id":"2303.03593","n_code_links":0,"syntology":null},{"paper":null,"slug":"classifying-text-based-conspiracy-tweets","title":"Classifying Text-Based Conspiracy Tweets related to COVID-19 using Contextualized Word Embeddings","date":"2023-03-07","arxiv_id":"2303.03706","n_code_links":0,"syntology":null},{"paper":null,"slug":"german-bert-model-for-legal-named-entity","title":"German BERT Model for Legal Named Entity Recognition","date":"2023-03-07","arxiv_id":"2303.05388","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-free-structured-pruning-with","title":"Gradient-Free Structured Pruning with Unlabeled Data","date":"2023-03-07","arxiv_id":"2303.04185","n_code_links":0,"syntology":null},{"paper":null,"slug":"globally-optimal-training-of-neural-networks","title":"Globally Optimal Training of Neural Networks with Threshold Activation Functions","date":"2023-03-06","arxiv_id":"2303.03382","n_code_links":0,"syntology":null},{"paper":"/paper/towards-zero-shot-functional-compositionality","slug":"towards-zero-shot-functional-compositionality","title":"Towards Zero-Shot Functional Compositionality of Language Models","date":"2023-03-06","arxiv_id":"2303.03103","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-question-answering-using-clip-guided","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","date":"2023-03-06","arxiv_id":"2303.03131","n_code_links":0,"syntology":null},{"paper":null,"slug":"fqp-2-0-industry-trend-analysis-via","title":"Industry Risk Assessment via Hierarchical Financial Data Using Stock Market Sentiment Indicators","date":"2023-03-05","arxiv_id":"2303.02707","n_code_links":0,"syntology":null},{"paper":"/paper/robust-affine-feature-matching-via-quadratic","slug":"robust-affine-feature-matching-via-quadratic","title":"Robust affine point matching via quadratic assignment on Grassmannians","date":"2023-03-05","arxiv_id":"2303.02698","n_code_links":3,"syntology":null},{"paper":null,"slug":"early-warning-signals-of-social-instabilities","title":"Early Warning Signals of Social Instabilities in Twitter Data","date":"2023-03-03","arxiv_id":"2303.05401","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-data-augmentation-methods-on-social","title":"Exploring Data Augmentation Methods on Social Media Corpora","date":"2023-03-03","arxiv_id":"2303.02198","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-label-classification-of-artificial","title":"Multi label classification of Artificial Intelligence related patents using Modified D2SBERT and Sentence Attention mechanism","date":"2023-03-03","arxiv_id":"2303.03165","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-model-representations-and-their","title":"Pre-trained Model Representations and their Robustness against Noise for Speech Emotion Analysis","date":"2023-03-03","arxiv_id":"2303.03177","n_code_links":0,"syntology":null}],"record_sha256":"73da455cc657466520861e5b8c6f135ce8acbf3ba4a97761d433c72499ed9020","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}