{"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/27","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":27,"pages_in_order":38,"rows_per_page":100,"rows":[2601,2700],"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/26","next":"/method/linear-warmup-with-cosine-annealing/papers/28","papers":[{"paper":"/paper/m3ke-a-massive-multi-level-multi-subject","slug":"m3ke-a-massive-multi-level-multi-subject","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","date":"2023-05-17","arxiv_id":"2305.10263","n_code_links":1,"syntology":null},{"paper":"/paper/smaller-language-models-are-better-black-box","slug":"smaller-language-models-are-better-black-box","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","date":"2023-05-17","arxiv_id":"2305.09859","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-gradient-descent-meets-derivative-free","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","date":"2023-05-17","arxiv_id":"2305.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-preliminary-analysis-on-the-code-generation","title":"A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions","date":"2023-05-16","arxiv_id":"2305.09402","n_code_links":0,"syntology":null},{"paper":"/paper/keras-gpt-copilot-integrating-the-power-of","slug":"keras-gpt-copilot-integrating-the-power-of","title":"Keras GPT Copilot: Integrating the Power of Large Language Models in Deep Learning Model Development","date":"2023-05-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-rumination-for-pre-trained-language","slug":"knowledge-rumination-for-pre-trained-language","title":"Knowledge Rumination for Pre-trained Language Models","date":"2023-05-15","arxiv_id":"2305.08732","n_code_links":1,"syntology":null},{"paper":"/paper/rl4f-generating-natural-language-feedback","slug":"rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","arxiv_id":"2305.08844","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feyzaakyurek/rl4f"],"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":["found_in_text","official"]}}},{"paper":"/paper/schema-adaptable-knowledge-graph-construction","slug":"schema-adaptable-knowledge-graph-construction","title":"Schema-adaptable Knowledge Graph Construction","date":"2023-05-15","arxiv_id":"2305.08703","n_code_links":1,"syntology":null},{"paper":"/paper/similarity-weighted-construction-of","slug":"similarity-weighted-construction-of","title":"Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks","date":"2023-05-15","arxiv_id":"2305.08495","n_code_links":1,"syntology":null},{"paper":"/paper/small-models-are-valuable-plug-ins-for-large","slug":"small-models-are-valuable-plug-ins-for-large","title":"Small Models are Valuable Plug-ins for Large Language Models","date":"2023-05-15","arxiv_id":"2305.08848","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":["JetRunner/SuperICL"],"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/text-classification-via-large-language-models","slug":"text-classification-via-large-language-models","title":"Text Classification via Large Language Models","date":"2023-05-15","arxiv_id":"2305.08377","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["shannonai/gpt-cls-carp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"using-llm-assisted-annotation-for-corpus","title":"Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology","date":"2023-05-15","arxiv_id":"2305.08339","n_code_links":0,"syntology":null},{"paper":"/paper/mobile-env-a-universal-platform-for-training","slug":"mobile-env-a-universal-platform-for-training","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","date":"2023-05-14","arxiv_id":"2305.08144","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":11,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opendfm/mobile-env-expe","x-lance/mobile-env"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-history-with-ai-a-comparative","title":"Bridging History with AI A Comparative Evaluation of GPT 3.5, GPT4, and GoogleBARD in Predictive Accuracy and Fact Checking","date":"2023-05-13","arxiv_id":"2305.07868","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-emergent-goal-like-behaviour-in","slug":"investigating-emergent-goal-like-behaviour-in","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","date":"2023-05-13","arxiv_id":"2305.07970","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["phelps-sg/llm-cooperation","gitlab.com/sphelps/llm-cooperation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"learning-to-reason-over-scene-graphs-a-case","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","date":"2023-05-12","arxiv_id":"2305.07716","n_code_links":0,"syntology":null},{"paper":"/paper/tinystories-how-small-can-language-models-be","slug":"tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","arxiv_id":"2305.07759","n_code_links":8,"syntology":{"ran":10,"of":18,"n_ran_checked":8,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":null,"slug":"when-giant-language-brains-just-aren-t-enough","title":"When Giant Language Brains Just Aren't Enough! Domain Pizzazz with Knowledge Sparkle Dust","date":"2023-05-12","arxiv_id":"2305.07230","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-a","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","date":"2023-05-11","arxiv_id":"2305.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-can-be-used-to","title":"Spear Phishing With Large Language Models","date":"2023-05-11","arxiv_id":"2305.06972","n_code_links":0,"syntology":null},{"paper":null,"slug":"overinformative-question-answering-by-humans","title":"Overinformative Question Answering by Humans and Machines","date":"2023-05-11","arxiv_id":"2305.07151","n_code_links":0,"syntology":null},{"paper":null,"slug":"recommendation-as-instruction-following-a","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","date":"2023-05-11","arxiv_id":"2305.07001","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-for-ct-reconstruction-from","title":"Transformers for CT Reconstruction From Monoplanar and Biplanar Radiographs","date":"2023-05-11","arxiv_id":"2305.06965","n_code_links":0,"syntology":null},{"paper":null,"slug":"bits-of-grass-does-gpt-already-know-how-to","title":"Bits of Grass: Does GPT already know how to write like Whitman?","date":"2023-05-10","arxiv_id":"2305.11064","n_code_links":0,"syntology":null},{"paper":null,"slug":"davinci-the-dualist-the-mind-body-divide-in","title":"Davinci the Dualist: the mind-body divide in large language models and in human learners","date":"2023-05-10","arxiv_id":"2305.07667","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-medically-accurate-summaries-of","title":"Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models","date":"2023-05-10","arxiv_id":"2305.05982","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-in-biomedical-natural","slug":"large-language-models-in-biomedical-natural","title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","date":"2023-05-10","arxiv_id":"2305.16326","n_code_links":1,"syntology":null},{"paper":"/paper/summarizing-simplifying-and-synthesizing","slug":"summarizing-simplifying-and-synthesizing","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","date":"2023-05-10","arxiv_id":"2305.06299","n_code_links":1,"syntology":null},{"paper":"/paper/codeie-large-code-generation-models-are","slug":"codeie-large-code-generation-models-are","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","date":"2023-05-09","arxiv_id":"2305.05711","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":["dasepli/codeie"],"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":"gpt-agents-in-game-theory-experiments","title":"GPT in Game Theory Experiments","date":"2023-05-09","arxiv_id":"2305.05516","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-nas-neural-architecture-search-with-the","title":"GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model","date":"2023-05-09","arxiv_id":"2305.05351","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effect-of-sub-word","title":"Effects of sub-word segmentation on performance of transformer language models","date":"2023-05-09","arxiv_id":"2305.05480","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-automatic-optimisation-model","title":"Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer","date":"2023-05-09","arxiv_id":"2305.05811","n_code_links":0,"syntology":null},{"paper":null,"slug":"coherent-wave-dynamics-and-language","title":"Coherent Wave Dynamics and Language Generation of a Generative Pre-trained Transformer","date":"2023-05-08","arxiv_id":"2305.05061","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-show-decision","title":"Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5","date":"2023-05-08","arxiv_id":"2305.04400","n_code_links":0,"syntology":null},{"paper":"/paper/explanation-based-finetuning-makes-models","slug":"explanation-based-finetuning-makes-models","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","date":"2023-05-08","arxiv_id":"2305.04990","n_code_links":1,"syntology":null},{"paper":null,"slug":"gersteinlab-at-mediqa-chat-2023-clinical-note","title":"GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning","date":"2023-05-08","arxiv_id":"2305.05001","n_code_links":0,"syntology":null},{"paper":"/paper/neurocomparatives-neuro-symbolic-distillation","slug":"neurocomparatives-neuro-symbolic-distillation","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","date":"2023-05-08","arxiv_id":"2305.04978","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-relation-extraction-in-the-era-of","title":"Revisiting Relation Extraction in the era of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05003","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-practical-applications-in-legal","title":"Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts","date":"2023-05-08","arxiv_id":"2305.04417","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-don-t-always-say-what-they-1","slug":"language-models-don-t-always-say-what-they-1","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","date":"2023-05-07","arxiv_id":"2305.04388","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["milesaturpin/cot-unfaithfulness"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"professional-certification-benchmark-dataset","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","date":"2023-05-07","arxiv_id":"2305.05377","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-neuropsychology-are-large-language","title":"Artificial Neuropsychology: Are Large Language Models Developing Executive Functions?","date":"2023-05-06","arxiv_id":"2305.04134","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":"/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":"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":"/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":"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":"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":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":"/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/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":"/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":"/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/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":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":"/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/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":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/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":"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":"/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":"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":"/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/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":"/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":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":"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":"/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":"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":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":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/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}],"record_sha256":"dbcee346b6de011a58313afea73fb8c93354b6614a56e25824a0d038b56321f1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}