{"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/53","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":53,"pages_in_order":108,"rows_per_page":100,"rows":[5201,5300],"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/52","next":"/method/weight-decay/papers/54","papers":[{"paper":null,"slug":"on-the-usage-of-continual-learning-for-out-of","title":"On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code","date":"2023-05-06","arxiv_id":"2305.04106","n_code_links":0,"syntology":null},{"paper":"/paper/plan-and-solve-prompting-improving-zero-shot","slug":"plan-and-solve-prompting-improving-zero-shot","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","date":"2023-05-06","arxiv_id":"2305.04091","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["agi-edgerunners/plan-and-solve-prompting"],"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":"pre-training-language-model-as-a-multi","title":"Pre-training Language Model as a Multi-perspective Course Learner","date":"2023-05-06","arxiv_id":"2305.03981","n_code_links":0,"syntology":null},{"paper":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","n_code_links":1,"syntology":null},{"paper":null,"slug":"rhetorical-role-labeling-of-legal-documents","title":"Rhetorical Role Labeling of Legal Documents using Transformers and Graph Neural Networks","date":"2023-05-06","arxiv_id":"2305.04100","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-transformer-language-models-for","title":"Adapting Transformer Language Models for Predictive Typing in Brain-Computer Interfaces","date":"2023-05-05","arxiv_id":"2305.03819","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-the-label-and-noise-an-n-gram-masked","title":"Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking","date":"2023-05-05","arxiv_id":"2305.03314","n_code_links":0,"syntology":null},{"paper":null,"slug":"clac-at-semeval-2023-task-2-comparing-span","title":"CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NER","date":"2023-05-05","arxiv_id":"2305.03845","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-bert-in-the-turkish","title":"Harnessing the Power of BERT in the Turkish Clinical Domain: Pretraining Approaches for Limited Data Scenarios","date":"2023-05-05","arxiv_id":"2305.03788","n_code_links":0,"syntology":null},{"paper":"/paper/otter-a-multi-modal-model-with-in-context","slug":"otter-a-multi-modal-model-with-in-context","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","date":"2023-05-05","arxiv_id":"2305.03726","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-covid-19-and-pneumonia","title":"Predicting COVID-19 and pneumonia complications from admission texts","date":"2023-05-05","arxiv_id":"2305.03661","n_code_links":0,"syntology":null},{"paper":null,"slug":"simulating-h-p-lovecraft-horror-literature","title":"Simulating H.P. Lovecraft horror literature with the ChatGPT large language model","date":"2023-05-05","arxiv_id":"2305.03429","n_code_links":0,"syntology":null},{"paper":"/paper/using-chatgpt-for-entity-matching","slug":"using-chatgpt-for-entity-matching","title":"Using ChatGPT for Entity Matching","date":"2023-05-05","arxiv_id":"2305.03423","n_code_links":1,"syntology":null},{"paper":"/paper/verify-and-edit-a-knowledge-enhanced-chain-of","slug":"verify-and-edit-a-knowledge-enhanced-chain-of","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","date":"2023-05-05","arxiv_id":"2305.03268","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-automatically-discovered-chain-of-thought","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","date":"2023-05-04","arxiv_id":"2305.02897","n_code_links":0,"syntology":null},{"paper":null,"slug":"automl-gpt-automatic-machine-learning-with","title":"AutoML-GPT: Automatic Machine Learning with GPT","date":"2023-05-04","arxiv_id":"2305.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pashto-text-classification-using","title":"Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis","date":"2023-05-04","arxiv_id":"2305.03201","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-a-review-on-advancements-and","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","date":"2023-05-04","arxiv_id":"2305.03195","n_code_links":0,"syntology":null},{"paper":"/paper/improving-code-example-recommendations-on","slug":"improving-code-example-recommendations-on","title":"Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study","date":"2023-05-04","arxiv_id":"2305.03017","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-time-preferences-and-consumer","title":"Can LLMs Capture Human Preferences?","date":"2023-05-04","arxiv_id":"2305.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"late-binding-scholarship-in-the-age-of-ai","title":"Late-Binding Scholarship in the Age of AI: Navigating Legal and Normative Challenges of a New Form of Knowledge Production","date":"2023-05-04","arxiv_id":"2305.11058","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-bert-language-model-for-arabic","title":"Leveraging BERT Language Model for Arabic Long Document Classification","date":"2023-05-04","arxiv_id":"2305.03519","n_code_links":0,"syntology":null},{"paper":"/paper/personallm-investigating-the-ability-of-gpt-3","slug":"personallm-investigating-the-ability-of-gpt-3","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","date":"2023-05-04","arxiv_id":"2305.02547","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hjian42/personallm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/simple-noisy-environment-augmentation-for","slug":"simple-noisy-environment-augmentation-for","title":"Simple Noisy Environment Augmentation for Reinforcement Learning","date":"2023-05-04","arxiv_id":"2305.02882","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-plagiarism-detection-approach","title":"A Novel Plagiarism Detection Approach Combining BERT-based Word Embedding, Attention-based LSTMs and an Improved Differential Evolution Algorithm","date":"2023-05-03","arxiv_id":"2305.02374","n_code_links":0,"syntology":null},{"paper":"/paper/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-bert-and-parsbert-for-analyzing","title":"evaluating bert and parsbert for analyzing persian advertisement data","date":"2023-05-03","arxiv_id":"2305.02426","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-bert-based-scientific-relation","title":"Evaluating BERT-based Scientific Relation Classifiers for Scholarly Knowledge Graph Construction on Digital Library Collections","date":"2023-05-03","arxiv_id":"2305.02291","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-linguistic-properties-of","title":"Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages","date":"2023-05-03","arxiv_id":"2305.02215","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-re-in-context-learning-for-relation","slug":"gpt-re-in-context-learning-for-relation","title":"GPT-RE: In-context Learning for Relation Extraction using Large Language Models","date":"2023-05-03","arxiv_id":"2305.02105","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancer-hallmark-classification-using","title":"Improving Cancer Hallmark Classification with BERT-based Deep Learning Approach","date":"2023-05-02","arxiv_id":"2305.03501","n_code_links":0,"syntology":null},{"paper":"/paper/discern-and-answer-mitigating-the-impact-of","slug":"discern-and-answer-mitigating-the-impact-of","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","date":"2023-05-02","arxiv_id":"2305.01579","n_code_links":1,"syntology":null},{"paper":null,"slug":"freelm-fine-tuning-free-language-model","title":"FreeLM: Fine-Tuning-Free Language Model","date":"2023-05-02","arxiv_id":"2305.01616","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-unleash-the-power-of-large-language","slug":"how-to-unleash-the-power-of-large-language","title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","date":"2023-05-02","arxiv_id":"2305.01555","n_code_links":2,"syntology":null},{"paper":null,"slug":"new-trends-in-machine-translation-using-large","title":"A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models","date":"2023-05-02","arxiv_id":"2305.01181","n_code_links":0,"syntology":null},{"paper":"/paper/unlimiformer-long-range-transformers-with","slug":"unlimiformer-long-range-transformers-with","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","date":"2023-05-02","arxiv_id":"2305.01625","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["abertsch72/unlimiformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-meets-definitions-unsupervised-visual","slug":"vision-meets-definitions-unsupervised-visual","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","date":"2023-05-02","arxiv_id":"2305.01788","n_code_links":1,"syntology":null},{"paper":"/paper/autoencoders-for-discovering-manifold","slug":"autoencoders-for-discovering-manifold","title":"Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systems","date":"2023-05-01","arxiv_id":"2305.01090","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-paper-screening-for-clinical","title":"Automated Paper Screening for Clinical Reviews Using Large Language Models","date":"2023-05-01","arxiv_id":"2305.00844","n_code_links":0,"syntology":null},{"paper":null,"slug":"logion-machine-learning-for-greek-philology","title":"Logion: Machine Learning for Greek Philology","date":"2023-05-01","arxiv_id":"2305.01099","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieving-comparative-arguments-using","title":"Retrieving Comparative Arguments using Ensemble Methods and Neural Information Retrieval","date":"2023-05-01","arxiv_id":"2305.01513","n_code_links":0,"syntology":null},{"paper":"/paper/safewebuh-at-semeval-2023-task-11-learning","slug":"safewebuh-at-semeval-2023-task-11-learning","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","date":"2023-05-01","arxiv_id":"2305.01050","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-classification-financial-reasoning-in","slug":"beyond-classification-financial-reasoning-in","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","date":"2023-04-30","arxiv_id":"2305.01505","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-effectiveness-of-large-language","slug":"exploring-the-effectiveness-of-large-language","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","date":"2023-04-30","arxiv_id":"2305.00418","n_code_links":1,"syntology":null},{"paper":"/paper/how-does-gpt-2-compute-greater-than-1","slug":"how-does-gpt-2-compute-greater-than-1","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","date":"2023-04-30","arxiv_id":"2305.00586","n_code_links":3,"syntology":null},{"paper":"/paper/are-the-best-multilingual-document-embeddings","slug":"are-the-best-multilingual-document-embeddings","title":"Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?","date":"2023-04-28","arxiv_id":"2304.14796","n_code_links":1,"syntology":null},{"paper":"/paper/causal-reasoning-and-large-language-models","slug":"causal-reasoning-and-large-language-models","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","date":"2023-04-28","arxiv_id":"2305.00050","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["py-why/pywhy-llm"],"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/flowtransformer-a-transformer-framework-for","slug":"flowtransformer-a-transformer-framework-for","title":"FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems","date":"2023-04-28","arxiv_id":"2304.14746","n_code_links":1,"syntology":null},{"paper":"/paper/towards-automated-circuit-discovery-for-1","slug":"towards-automated-circuit-discovery-for-1","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","date":"2023-04-28","arxiv_id":"2304.14997","n_code_links":4,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["arthurconmy/automatic-circuit-discovery","neelnanda-io/transformerlens"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-better-domain-adaptation-for-self","slug":"towards-better-domain-adaptation-for-self","title":"Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR","date":"2023-04-28","arxiv_id":"2305.00115","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-mining-and-technical-analyses","title":"Assessing Text Mining and Technical Analyses on Forecasting Financial Time Series","date":"2023-04-27","arxiv_id":"2304.14544","n_code_links":0,"syntology":null},{"paper":null,"slug":"framing-the-news-from-human-perception-to","title":"Framing the News:From Human Perception to Large Language Model Inferences","date":"2023-04-27","arxiv_id":"2304.14456","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-state-of-the-art-1","slug":"large-language-models-are-state-of-the-art-1","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","date":"2023-04-27","arxiv_id":"2304.14317","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["terryyz/llm-code-eval","terryyz/ice-score"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"origin-tracing-and-detecting-of-llms","title":"Origin Tracing and Detecting of LLMs","date":"2023-04-27","arxiv_id":"2304.14072","n_code_links":0,"syntology":null},{"paper":"/paper/pybibx-a-python-library-for-bibliometric-and","slug":"pybibx-a-python-library-for-bibliometric-and","title":"pyBibX -- A Python Library for Bibliometric and Scientometric Analysis Powered with Artificial Intelligence Tools","date":"2023-04-27","arxiv_id":"2304.14516","n_code_links":1,"syntology":null},{"paper":"/paper/swectrl-mini-a-data-transparent-transformer","slug":"swectrl-mini-a-data-transparent-transformer","title":"SweCTRL-Mini: a data-transparent Transformer-based large language model for controllable text generation in Swedish","date":"2023-04-27","arxiv_id":"2304.13994","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-based-reasoning-framework-for-adaptive","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","date":"2023-04-26","arxiv_id":"2304.13301","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-5-and-gpt-4-for","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","date":"2023-04-26","arxiv_id":"2304.13714","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-curious-case-of-code-prompts","slug":"exploring-the-curious-case-of-code-prompts","title":"Exploring the Curious Case of Code Prompts","date":"2023-04-26","arxiv_id":"2304.13250","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":["zharry29/codex_vs_gpt3"],"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":"extracting-structured-seed-mediated-gold","title":"Extracting Structured Seed-Mediated Gold Nanorod Growth Procedures from Literature with GPT-3","date":"2023-04-26","arxiv_id":"2304.13846","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-with-abnormal-examples","title":"Fine Tuning with Abnormal Examples","date":"2023-04-26","arxiv_id":"2304.13783","n_code_links":0,"syntology":null},{"paper":"/paper/hausanlp-at-semeval-2023-task-12-leveraging","slug":"hausanlp-at-semeval-2023-task-12-leveraging","title":"HausaNLP at SemEval-2023 Task 12: Leveraging African Low Resource TweetData for Sentiment Analysis","date":"2023-04-26","arxiv_id":"2304.13634","n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-multi-modal-dbmss-for-seamless","title":"Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables","date":"2023-04-26","arxiv_id":"2304.13559","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-deep-reinforcement-learning-for-thz","title":"Federated Deep Reinforcement Learning for THz-Beam Search with Limited CSI","date":"2023-04-25","arxiv_id":"2304.13109","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-massive-multitask-chinese","slug":"measuring-massive-multitask-chinese","title":"Measuring Massive Multitask Chinese Understanding","date":"2023-04-25","arxiv_id":"2304.12986","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Felixgithub2017/MMCU"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"nlp-ltu-at-semeval-2023-task-10-the-impact-of","title":"NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset","date":"2023-04-25","arxiv_id":"2304.12847","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-compression-with-large-language","title":"Semantic Compression With Large Language Models","date":"2023-04-25","arxiv_id":"2304.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-potential-of-visual-chatgpt-for-remote","title":"The Potential of Visual ChatGPT For Remote Sensing","date":"2023-04-25","arxiv_id":"2304.13009","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-learn-about-prosody","title":"What does BERT learn about prosody?","date":"2023-04-25","arxiv_id":"2304.12706","n_code_links":0,"syntology":null},{"paper":"/paper/generation-driven-contrastive-self-training","slug":"generation-driven-contrastive-self-training","title":"Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM","date":"2023-04-24","arxiv_id":"2304.11872","n_code_links":1,"syntology":null},{"paper":"/paper/paragraph2graph-a-gnn-based-framework-for","slug":"paragraph2graph-a-gnn-based-framework-for","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","date":"2023-04-24","arxiv_id":"2304.11810","n_code_links":1,"syntology":null},{"paper":"/paper/pre-trained-embeddings-for-entity-resolution","slug":"pre-trained-embeddings-for-entity-resolution","title":"Pre-trained Embeddings for Entity Resolution: An Experimental Analysis [Experiment, Analysis & Benchmark]","date":"2023-04-24","arxiv_id":"2304.12329","n_code_links":1,"syntology":null},{"paper":"/paper/socialdial-a-benchmark-for-socially-aware","slug":"socialdial-a-benchmark-for-socially-aware","title":"SocialDial: A Benchmark for Socially-Aware Dialogue Systems","date":"2023-04-24","arxiv_id":"2304.12026","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-challenges-of-deploying-bert-based","slug":"exploring-challenges-of-deploying-bert-based","title":"Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?","date":"2023-04-23","arxiv_id":"2304.11520","n_code_links":2,"syntology":null},{"paper":"/paper/boosting-theory-of-mind-performance-in-large","slug":"boosting-theory-of-mind-performance-in-large","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","date":"2023-04-22","arxiv_id":"2304.11490","n_code_links":1,"syntology":null},{"paper":null,"slug":"l3cube-indicsbert-a-simple-approach-for","title":"L3Cube-IndicSBERT: A simple approach for learning cross-lingual sentence representations using multilingual BERT","date":"2023-04-22","arxiv_id":"2304.11434","n_code_links":0,"syntology":null},{"paper":"/paper/a-group-specific-approach-to-nlp-for-hate","slug":"a-group-specific-approach-to-nlp-for-hate","title":"A Group-Specific Approach to NLP for Hate Speech Detection","date":"2023-04-21","arxiv_id":"2304.11223","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-based-clinical-knowledge-extraction-for","title":"BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis","date":"2023-04-21","arxiv_id":"2304.10996","n_code_links":0,"syntology":null},{"paper":"/paper/building-multimodal-ai-chatbots","slug":"building-multimodal-ai-chatbots","title":"Building Multimodal AI Chatbots","date":"2023-04-21","arxiv_id":"2305.03512","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-transformer-language-models-on-1","slug":"evaluating-transformer-language-models-on-1","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","date":"2023-04-21","arxiv_id":"2304.10977","n_code_links":1,"syntology":null},{"paper":null,"slug":"inducing-anxiety-in-large-language-models","title":"Inducing anxiety in large language models can induce bias","date":"2023-04-21","arxiv_id":"2304.11111","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-deep-learning-for-credit-rating","slug":"multi-modal-deep-learning-for-credit-rating","title":"Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams","date":"2023-04-21","arxiv_id":"2304.10740","n_code_links":1,"syntology":null},{"paper":null,"slug":"text2time-transformer-based-article-time","title":"Text2Time: Transformer-based Article Time Period Prediction","date":"2023-04-21","arxiv_id":"2304.10859","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-dark-side-of-chatgpt-legal-and-ethical","title":"The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination","date":"2023-04-21","arxiv_id":"2304.14347","n_code_links":0,"syntology":null},{"paper":null,"slug":"who-s-the-best-detective-llms-vs-mls-in","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","date":"2023-04-21","arxiv_id":"2304.11257","n_code_links":0,"syntology":null},{"paper":null,"slug":"domain-specific-continued-pretraining-of","title":"Domain-specific Continued Pretraining of Language Models for Capturing Long Context in Mental Health","date":"2023-04-20","arxiv_id":"2304.10447","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-cross-modal-information-retrieval-possible","title":"Is Cross-modal Information Retrieval Possible without Training?","date":"2023-04-20","arxiv_id":"2304.11095","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-semantics-towards-better-natural","title":"Meta Semantics: Towards better natural language understanding and reasoning","date":"2023-04-20","arxiv_id":"2304.10663","n_code_links":0,"syntology":null},{"paper":null,"slug":"movie-box-office-prediction-with-self","title":"Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining","date":"2023-04-20","arxiv_id":"2304.10311","n_code_links":0,"syntology":null},{"paper":"/paper/safety-assessment-of-chinese-large-language","slug":"safety-assessment-of-chinese-large-language","title":"Safety Assessment of Chinese Large Language Models","date":"2023-04-20","arxiv_id":"2304.10436","n_code_links":2,"syntology":null},{"paper":null,"slug":"sinc-spatial-composition-of-3d-human-motions","title":"SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation","date":"2023-04-20","arxiv_id":"2304.10417","n_code_links":0,"syntology":null},{"paper":null,"slug":"word-sense-induction-with-knowledge-1","title":"Word Sense Induction with Knowledge Distillation from BERT","date":"2023-04-20","arxiv_id":"2304.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"catch-me-if-you-can-identifying-fraudulent","title":"Catch Me If You Can: Identifying Fraudulent Physician Reviews with Large Language Models Using Generative Pre-Trained Transformers","date":"2023-04-19","arxiv_id":"2304.09948","n_code_links":0,"syntology":null},{"paper":"/paper/genegpt-teaching-large-language-models-to-use","slug":"genegpt-teaching-large-language-models-to-use","title":"GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information","date":"2023-04-19","arxiv_id":"2304.09667","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":["ncbi/GeneGPT"],"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":"how-to-do-things-with-deep-learning-code","title":"How to Do Things with Deep Learning Code","date":"2023-04-19","arxiv_id":"2304.09406","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-transformer-to-1m-tokens-and-beyond","slug":"scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","date":"2023-04-19","arxiv_id":"2304.11062","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["booydar/t5-experiments"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"supporting-human-ai-collaboration-in-auditing","title":"Supporting Human-AI Collaboration in Auditing LLMs with LLMs","date":"2023-04-19","arxiv_id":"2304.09991","n_code_links":0,"syntology":null},{"paper":"/paper/surgicalgpt-end-to-end-language-vision-gpt","slug":"surgicalgpt-end-to-end-language-vision-gpt","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","date":"2023-04-19","arxiv_id":"2304.09974","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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lalithjets/surgicalgpt"],"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/tiefake-title-text-similarity-and-emotion","slug":"tiefake-title-text-similarity-and-emotion","title":"TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection","date":"2023-04-19","arxiv_id":"2304.09421","n_code_links":2,"syntology":null}],"record_sha256":"4953e8de11b634e5e871239e218fe3a72db83fb76b318c7a565be047f20db553","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}