{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-warmup-with-cosine-annealing/papers/28","list_of":"/method/linear-warmup-with-cosine-annealing","method":"Linear Warmup With Cosine Annealing","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":28,"pages_in_order":38,"rows_per_page":100,"rows":[2701,2800],"of":3797,"counts":{"archive_papers_tagged":3797,"with_a_code_link":1655,"where_syntology_ran_a_sample":602,"not_listed_spam_title":0,"listed":3797,"listed_where_code_ran":602,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":490,"every_run_a_failure_of_syntologys_instrument":112,"listed_with_a_run_with_no_instrument_failure":490,"listed_every_run_a_failure_of_syntologys_instrument":112,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-warmup-with-cosine-annealing","prev":"/method/linear-warmup-with-cosine-annealing/papers/27","next":"/method/linear-warmup-with-cosine-annealing/papers/29","papers":[{"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":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/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":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":"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":"/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":"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":"/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":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":"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":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":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":"/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/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":"/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":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":"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":"/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/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":"/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/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":"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":"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":"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"]}}},{"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/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/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":"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/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":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":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":"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":"/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":"/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":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":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":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":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":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":"/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":"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":"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":"/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":"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":"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":"/paper/transformer-based-world-models-are-happy-with","slug":"transformer-based-world-models-are-happy-with","title":"Transformer-based World Models Are Happy With 100k Interactions","date":"2023-03-13","arxiv_id":"2303.07109","n_code_links":1,"syntology":{"ran":16,"of":25,"n_ran_checked":8,"n_instrument":8,"unverified":9,"pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified","official":{"repos":["jrobine/twm"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":9,"ran_from_kinds":["official"]}}},{"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":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":"/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}],"record_sha256":"49298f188267a557388b8a8084bad286bb1f8d210b17f45b20a33f1f2b4764db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}