{"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/54","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":54,"pages_in_order":108,"rows_per_page":100,"rows":[5301,5400],"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/53","next":"/method/weight-decay/papers/55","papers":[{"paper":null,"slug":"bim-gpt-a-prompt-based-virtual-assistant","title":"BIM-GPT: a Prompt-Based Virtual Assistant Framework for BIM Information Retrieval","date":"2023-04-18","arxiv_id":"2304.09333","n_code_links":0,"syntology":null},{"paper":null,"slug":"cancergpt-few-shot-drug-pair-synergy","title":"CancerGPT: Few-shot Drug Pair Synergy Prediction using Large Pre-trained Language Models","date":"2023-04-18","arxiv_id":"2304.10946","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-interaction-for-content-generation","title":"LLM-based Interaction for Content Generation: A Case Study on the Perception of Employees in an IT department","date":"2023-04-18","arxiv_id":"2304.09064","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-suppression-accurate-quantization-of","slug":"outlier-suppression-accurate-quantization-of","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","date":"2023-04-18","arxiv_id":"2304.09145","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["modeltc/outlier_suppression_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-empirical-study-of-multitask-learning-to","slug":"an-empirical-study-of-multitask-learning-to","title":"An Empirical Study of Multitask Learning to Improve Open Domain Dialogue Systems","date":"2023-04-17","arxiv_id":"2304.08115","n_code_links":1,"syntology":null},{"paper":"/paper/context-dependent-embedding-utterance","slug":"context-dependent-embedding-utterance","title":"Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations","date":"2023-04-17","arxiv_id":"2304.08216","n_code_links":1,"syntology":null},{"paper":"/paper/from-zero-to-hero-examining-the-power-of","slug":"from-zero-to-hero-examining-the-power-of","title":"From Zero to Hero: Examining the Power of Symbolic Tasks in Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.07995","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/symbolic-instruction-tuning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructuie-multi-task-instruction-tuning-for","slug":"instructuie-multi-task-instruction-tuning-for","title":"InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction","date":"2023-04-17","arxiv_id":"2304.08085","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-short-video-rumor-detection-system","title":"Multimodal Short Video Rumor Detection System Based on Contrastive Learning","date":"2023-04-17","arxiv_id":"2304.08401","n_code_links":0,"syntology":null},{"paper":null,"slug":"new-product-development-npd-through-social","title":"New Product Development (NPD) through Social Media-based Analysis by Comparing Word2Vec and BERT Word Embeddings","date":"2023-04-17","arxiv_id":"2304.08369","n_code_links":0,"syntology":null},{"paper":null,"slug":"supporting-qualitative-analysis-with-large","title":"Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding","date":"2023-04-17","arxiv_id":"2304.10548","n_code_links":0,"syntology":null},{"paper":"/paper/the-minipile-challenge-for-data-efficient","slug":"the-minipile-challenge-for-data-efficient","title":"The MiniPile Challenge for Data-Efficient Language Models","date":"2023-04-17","arxiv_id":"2304.08442","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-virtual-simulation-pilot-agent-for-training","title":"A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers","date":"2023-04-16","arxiv_id":"2304.07842","n_code_links":0,"syntology":null},{"paper":"/paper/argugpt-evaluating-understanding-and","slug":"argugpt-evaluating-understanding-and","title":"ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models","date":"2023-04-16","arxiv_id":"2304.07666","n_code_links":2,"syntology":null},{"paper":null,"slug":"automated-program-repair-based-on-code-review","title":"Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering","date":"2023-04-16","arxiv_id":"2304.07840","n_code_links":0,"syntology":null},{"paper":null,"slug":"sabia-portuguese-large-language-models","title":"Sabiá: Portuguese Large Language Models","date":"2023-04-16","arxiv_id":"2304.07880","n_code_links":0,"syntology":null},{"paper":"/paper/sikugpt-a-generative-pre-trained-model-for","slug":"sikugpt-a-generative-pre-trained-model-for","title":"SikuGPT: A Generative Pre-trained Model for Intelligent Information Processing of Ancient Texts from the Perspective of Digital Humanities","date":"2023-04-16","arxiv_id":"2304.07778","n_code_links":1,"syntology":null},{"paper":"/paper/towards-better-instruction-following-language","slug":"towards-better-instruction-following-language","title":"Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation","date":"2023-04-16","arxiv_id":"2304.07854","n_code_links":2,"syntology":null},{"paper":null,"slug":"can-chatgpt-forecast-stock-price-movements","title":"Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models","date":"2023-04-15","arxiv_id":"2304.07619","n_code_links":0,"syntology":null},{"paper":"/paper/api-bank-a-benchmark-for-tool-augmented-llms","slug":"api-bank-a-benchmark-for-tool-augmented-llms","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","date":"2023-04-14","arxiv_id":"2304.08244","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"chatgpt-applications-opportunities-and","title":"ChatGPT: Applications, Opportunities, and Threats","date":"2023-04-14","arxiv_id":"2304.09103","n_code_links":0,"syntology":null},{"paper":"/paper/medalpaca-an-open-source-collection-of","slug":"medalpaca-an-open-source-collection-of","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","date":"2023-04-14","arxiv_id":"2304.08247","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/simplex-a-lexical-text-simplification","slug":"simplex-a-lexical-text-simplification","title":"SimpLex: a lexical text simplification architecture","date":"2023-04-14","arxiv_id":"2304.07002","n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-code-generation","title":"Stochastic Code Generation","date":"2023-04-14","arxiv_id":"2304.08243","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-mapping-of-cve-vulnerability","title":"Automated Mapping of CVE Vulnerability Records to MITRE CWE Weaknesses","date":"2023-04-13","arxiv_id":"2304.11130","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-cites-the-most-cited-articles-and","title":"ChatGPT cites the most-cited articles and journals, relying solely on Google Scholar's citation counts. As a result, AI may amplify the Matthew Effect in environmental science","date":"2023-04-13","arxiv_id":"2304.06794","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-social-biases-in-recent-large","title":"Evaluation of Social Biases in Recent Large Pre-Trained Models","date":"2023-04-13","arxiv_id":"2304.06861","n_code_links":0,"syntology":null},{"paper":"/paper/pgtask-introducing-the-task-of-profile","slug":"pgtask-introducing-the-task-of-profile","title":"PGTask: Introducing the Task of Profile Generation from Dialogues","date":"2023-04-13","arxiv_id":"2304.06634","n_code_links":1,"syntology":null},{"paper":"/paper/shall-we-pretrain-autoregressive-language","slug":"shall-we-pretrain-autoregressive-language","title":"Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study","date":"2023-04-13","arxiv_id":"2304.06762","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-does-clip-know-about-a-red-circle-visual","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","date":"2023-04-13","arxiv_id":"2304.06712","n_code_links":0,"syntology":null},{"paper":"/paper/detection-of-fake-generated-scientific","slug":"detection-of-fake-generated-scientific","title":"Detection of Fake Generated Scientific Abstracts","date":"2023-04-12","arxiv_id":"2304.06148","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluation-of-chatgpt-model-for-vulnerability","title":"Evaluation of ChatGPT Model for Vulnerability Detection","date":"2023-04-12","arxiv_id":"2304.07232","n_code_links":0,"syntology":null},{"paper":"/paper/localizing-model-behavior-with-path-patching","slug":"localizing-model-behavior-with-path-patching","title":"Localizing Model Behavior with Path Patching","date":"2023-04-12","arxiv_id":"2304.05969","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["redwoodresearch/rust_circuit_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"active-ris-aided-eh-noma-networks-a-deep","title":"Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach","date":"2023-04-11","arxiv_id":"2304.12184","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximating-human-evaluation-of-social","title":"Approximating Online Human Evaluation of Social Chatbots with Prompting","date":"2023-04-11","arxiv_id":"2304.05253","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-optimization-of-catalysts-with-in","slug":"bayesian-optimization-of-catalysts-with-in","title":"Bayesian Optimization of Catalysis With In-Context Learning","date":"2023-04-11","arxiv_id":"2304.05341","n_code_links":2,"syntology":null},{"paper":null,"slug":"distinguishing-chatgpt-3-5-4-generated-and","title":"Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis","date":"2023-04-11","arxiv_id":"2304.05534","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-use-of-foundation-models-for","title":"Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages","date":"2023-04-11","arxiv_id":"2304.05336","n_code_links":0,"syntology":null},{"paper":"/paper/multi-step-jailbreaking-privacy-attacks-on","slug":"multi-step-jailbreaking-privacy-attacks-on","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","date":"2023-04-11","arxiv_id":"2304.05197","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":0,"n_instrument":5,"unverified":1,"pointer_only":0,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hkust-knowcomp/llm-multistep-jailbreak"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-preserving-word-order-importance","slug":"towards-preserving-word-order-importance","title":"Towards preserving word order importance through Forced Invalidation","date":"2023-04-11","arxiv_id":"2304.05221","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-large-language-models-efficiently","title":"Training Large Language Models Efficiently with Sparsity and Dataflow","date":"2023-04-11","arxiv_id":"2304.05511","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-reading-passage-generation-with","title":"Automated Reading Passage Generation with OpenAI's Large Language Model","date":"2023-04-10","arxiv_id":"2304.04616","n_code_links":0,"syntology":null},{"paper":null,"slug":"incorporating-structured-sentences-with-time","title":"Incorporating Structured Sentences with Time-enhanced BERT for Fully-inductive Temporal Relation Prediction","date":"2023-04-10","arxiv_id":"2304.04717","n_code_links":0,"syntology":null},{"paper":"/paper/is-chatgpt-a-good-sentiment-analyzer-a","slug":"is-chatgpt-a-good-sentiment-analyzer-a","title":"Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study","date":"2023-04-10","arxiv_id":"2304.04339","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["nustm/chatgpt-sentiment-evaluation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"on-the-possibilities-of-ai-generated-text","title":"On the Possibilities of AI-Generated Text Detection","date":"2023-04-10","arxiv_id":"2304.04736","n_code_links":0,"syntology":null},{"paper":"/paper/are-large-language-models-ready-for","slug":"are-large-language-models-ready-for","title":"Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding","date":"2023-04-09","arxiv_id":"2304.05368","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-tokenize-for-generative-retrieval","slug":"learning-to-tokenize-for-generative-retrieval","title":"Learning to Tokenize for Generative Retrieval","date":"2023-04-09","arxiv_id":"2304.04171","n_code_links":1,"syntology":null},{"paper":"/paper/factify-2-a-multimodal-fake-news-and-satire","slug":"factify-2-a-multimodal-fake-news-and-satire","title":"Factify 2: A Multimodal Fake News and Satire News Dataset","date":"2023-04-08","arxiv_id":"2304.03897","n_code_links":1,"syntology":null},{"paper":null,"slug":"flexmoe-scaling-large-scale-sparse-pre","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","date":"2023-04-08","arxiv_id":"2304.03946","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt4rec-a-generative-framework-for","title":"GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation","date":"2023-04-08","arxiv_id":"2304.03879","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-multi-labeled-bengali-toxic","slug":"interpretable-multi-labeled-bengali-toxic","title":"Interpretable Multi Labeled Bengali Toxic Comments Classification using Deep Learning","date":"2023-04-08","arxiv_id":"2304.04087","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-class-categorization-of-reasons-behind","title":"Multi-class Categorization of Reasons behind Mental Disturbance in Long Texts","date":"2023-04-08","arxiv_id":"2304.04118","n_code_links":0,"syntology":null},{"paper":"/paper/tmn-at-semeval-2023-task-9-multilingual-tweet","slug":"tmn-at-semeval-2023-task-9-multilingual-tweet","title":"tmn at SemEval-2023 Task 9: Multilingual Tweet Intimacy Detection using XLM-T, Google Translate, and Ensemble Learning","date":"2023-04-08","arxiv_id":"2304.04054","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-logical-reasoning-ability-of","slug":"evaluating-the-logical-reasoning-ability-of","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","date":"2023-04-07","arxiv_id":"2304.03439","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-evaluation-protocols-of-visual","title":"Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning","date":"2023-04-07","arxiv_id":"2304.03456","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-crawler-find-out-if-chatgpt-really","title":"ChatGPT-Crawler: Find out if ChatGPT really knows what it's talking about","date":"2023-04-06","arxiv_id":"2304.03325","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-opinion-mining-and-topic","title":"Deep Learning for Opinion Mining and Topic Classification of Course Reviews","date":"2023-04-06","arxiv_id":"2304.03394","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-detectors-are-biased-against-non-native","slug":"gpt-detectors-are-biased-against-non-native","title":"GPT detectors are biased against non-native English writers","date":"2023-04-06","arxiv_id":"2304.02819","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":["weixin-liang/chatgpt-detector-bias"],"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/making-ai-less-thirsty-uncovering-and","slug":"making-ai-less-thirsty-uncovering-and","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","date":"2023-04-06","arxiv_id":"2304.03271","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ren-research/making-ai-less-thirsty"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/micron-bert-bert-based-facial-micro","slug":"micron-bert-bert-based-facial-micro","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","date":"2023-04-06","arxiv_id":"2304.03195","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 2 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","official":{"repos":["uark-cviu/micron-bert"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-label-classification-of-open-ended","title":"Multi-label classification of open-ended questions with BERT","date":"2023-04-06","arxiv_id":"2304.02945","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-evaluations-of-chatgpt-and-emotion","slug":"on-the-evaluations-of-chatgpt-and-emotion","title":"Towards Interpretable Mental Health Analysis with Large Language Models","date":"2023-04-06","arxiv_id":"2304.03347","n_code_links":2,"syntology":null},{"paper":"/paper/zero-shot-next-item-recommendation-using","slug":"zero-shot-next-item-recommendation-using","title":"Zero-Shot Next-Item Recommendation using Large Pretrained Language Models","date":"2023-04-06","arxiv_id":"2304.03153","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":null}},{"paper":null,"slug":"behavioral-estimates-of-conceptual-structure","title":"Conceptual structure coheres in human cognition but not in large language models","date":"2023-04-05","arxiv_id":"2304.02754","n_code_links":0,"syntology":null},{"paper":null,"slug":"bengali-fake-review-detection-using-semi","title":"Bengali Fake Review Detection using Semi-supervised Generative Adversarial Networks","date":"2023-04-05","arxiv_id":"2304.02739","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-aware-classification-of-legal","title":"Context-Aware Classification of Legal Document Pages","date":"2023-04-05","arxiv_id":"2304.02787","n_code_links":0,"syntology":null},{"paper":"/paper/document-level-machine-translation-with-large","slug":"document-level-machine-translation-with-large","title":"Document-Level Machine Translation with Large Language Models","date":"2023-04-05","arxiv_id":"2304.02210","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-master-key-unlocking","title":"Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT","date":"2023-04-05","arxiv_id":"2304.02213","n_code_links":0,"syntology":null},{"paper":null,"slug":"blockwise-compression-of-transformer-based","title":"Blockwise Compression of Transformer-based Models without Retraining","date":"2023-04-04","arxiv_id":"2304.01483","n_code_links":0,"syntology":null},{"paper":null,"slug":"geotechnical-parrot-tales-gpt-overcoming-gpt","title":"Geotechnical Parrot Tales (GPT): Harnessing Large Language Models in geotechnical engineering","date":"2023-04-04","arxiv_id":"2304.02138","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-to-gpt-3-5-hold-my-scalpel-a-look-at","title":"GPT-4 to GPT-3.5: 'Hold My Scalpel' -- A Look at the Competency of OpenAI's GPT on the Plastic Surgery In-Service Training Exam","date":"2023-04-04","arxiv_id":"2304.01503","n_code_links":0,"syntology":null},{"paper":"/paper/improved-visual-fine-tuning-with-natural","slug":"improved-visual-fine-tuning-with-natural","title":"Improved Visual Fine-tuning with Natural Language Supervision","date":"2023-04-04","arxiv_id":"2304.01489","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":["idstcv/tes"],"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":"is-chatgpt-a-highly-fluent-grammatical-error","title":"Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation","date":"2023-04-04","arxiv_id":"2304.01746","n_code_links":0,"syntology":null},{"paper":"/paper/llm-adapters-an-adapter-family-for-parameter","slug":"llm-adapters-an-adapter-family-for-parameter","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01933","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agi-edgerunners/llm-adapters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/refiner-reasoning-feedback-on-intermediate","slug":"refiner-reasoning-feedback-on-intermediate","title":"REFINER: Reasoning Feedback on Intermediate Representations","date":"2023-04-04","arxiv_id":"2304.01904","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["debjitpaul/refiner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"san-bert-extractive-summarization-for","title":"San-BERT: Extractive Summarization for Sanskrit Documents using BERT and it's variants","date":"2023-04-04","arxiv_id":"2304.01894","n_code_links":0,"syntology":null},{"paper":null,"slug":"summary-of-chatgpt-gpt-4-research-and","title":"Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01852","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-homophobia-transphobia-in","title":"Detection of Homophobia & Transphobia in Dravidian Languages: Exploring Deep Learning Methods","date":"2023-04-03","arxiv_id":"2304.01241","n_code_links":0,"syntology":null},{"paper":"/paper/greekbart-the-first-pretrained-greek-sequence","slug":"greekbart-the-first-pretrained-greek-sequence","title":"GreekBART: The First Pretrained Greek Sequence-to-Sequence Model","date":"2023-04-03","arxiv_id":"2304.00869","n_code_links":2,"syntology":null},{"paper":"/paper/hate-speech-targets-detection-in-parler-using","slug":"hate-speech-targets-detection-in-parler-using","title":"Hate Speech Targets Detection in Parler using BERT","date":"2023-04-03","arxiv_id":"2304.01179","n_code_links":1,"syntology":null},{"paper":"/paper/minirbt-a-two-stage-distilled-small-chinese","slug":"minirbt-a-two-stage-distilled-small-chinese","title":"MiniRBT: A Two-stage Distilled Small Chinese Pre-trained Model","date":"2023-04-03","arxiv_id":"2304.00717","n_code_links":1,"syntology":null},{"paper":"/paper/safety-analysis-in-the-era-of-large-language","slug":"safety-analysis-in-the-era-of-large-language","title":"Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT","date":"2023-04-03","arxiv_id":"2304.01246","n_code_links":2,"syntology":null},{"paper":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","n_code_links":2,"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":["huashen218/llm-deepfake-human-study"],"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":"classifying-covid-19-related-tweets-for-fake","title":"Classifying COVID-19 Related Tweets for Fake News Detection and Sentiment Analysis with BERT-based Models","date":"2023-04-02","arxiv_id":"2304.00636","n_code_links":0,"syntology":null},{"paper":"/paper/llmmaps-a-visual-metaphor-for-stratified","slug":"llmmaps-a-visual-metaphor-for-stratified","title":"LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models","date":"2023-04-02","arxiv_id":"2304.00457","n_code_links":1,"syntology":null},{"paper":"/paper/the-other-side-of-compression-measuring-bias","slug":"the-other-side-of-compression-measuring-bias","title":"The Other Side of Compression: Measuring Bias in Pruned Transformers","date":"2023-04-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/bertino-an-italian-distilbert-model","slug":"bertino-an-italian-distilbert-model","title":"BERTino: an Italian DistilBERT model","date":"2023-03-31","arxiv_id":"2303.18121","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-gpt-4-and-chatgpt-on-japanese","slug":"evaluating-gpt-4-and-chatgpt-on-japanese","title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations","date":"2023-03-31","arxiv_id":"2303.18027","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-potential-of-large-language","title":"GPT-4 can pass the Korean National Licensing Examination for Korean Medicine Doctors","date":"2023-03-31","arxiv_id":"2303.17807","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-thyroid-nodules-characteristics","title":"Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods","date":"2023-03-31","arxiv_id":"2304.00115","n_code_links":0,"syntology":null},{"paper":null,"slug":"jobham-place-with-smart-recommend-job-options","title":"JobHam-place with smart recommend job options and candidate filtering options","date":"2023-03-31","arxiv_id":"2303.17930","n_code_links":0,"syntology":null},{"paper":null,"slug":"quick-dense-retrievers-consume-kale-post","title":"Quick Dense Retrievers Consume KALE: Post Training Kullback Leibler Alignment of Embeddings for Asymmetrical dual encoders","date":"2023-03-31","arxiv_id":"2304.01016","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-a-medium-size-gpt-model-in-english","title":"Aligning a medium-size GPT model in English to a small closed domain in Spanish","date":"2023-03-30","arxiv_id":"2303.17649","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-and-bert-based-models-on","title":"Evaluation of GPT and BERT-based models on identifying protein-protein interactions in biomedical text","date":"2023-03-30","arxiv_id":"2303.17728","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-bert-with-character-level-noise","title":"Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages","date":"2023-03-30","arxiv_id":"2303.17683","n_code_links":0,"syntology":null},{"paper":null,"slug":"humans-in-humans-out-on-gpt-converging-toward","title":"Humans in Humans Out: On GPT Converging Toward Common Sense in both Success and Failure","date":"2023-03-30","arxiv_id":"2303.17276","n_code_links":0,"syntology":null},{"paper":null,"slug":"oberta-improving-sparse-transfer-learning-via","title":"oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes","date":"2023-03-30","arxiv_id":"2303.17612","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthesis-of-mathematical-programs-from","title":"Synthesis of Mathematical programs from Natural Language Specifications","date":"2023-03-30","arxiv_id":"2304.03287","n_code_links":0,"syntology":null},{"paper":null,"slug":"advances-in-apparent-conceptual-physics","title":"Advances in apparent conceptual physics reasoning in GPT-4","date":"2023-03-29","arxiv_id":"2303.17012","n_code_links":0,"syntology":null},{"paper":"/paper/annollm-making-large-language-models-to-be","slug":"annollm-making-large-language-models-to-be","title":"AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators","date":"2023-03-29","arxiv_id":"2303.16854","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nlpcode/annollm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"6ccd5bcb9bcaca8ee0c1a4ed8619667b49a8d845c7fe7b1155336f461a701092","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}