{"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/15","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":15,"pages_in_order":38,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/method/linear-warmup-with-cosine-annealing/papers/16","papers":[{"paper":null,"slug":"gpt-4-as-evaluator-evaluating-large-language","title":"GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture","date":"2024-03-18","arxiv_id":"2403.11858","n_code_links":0,"syntology":null},{"paper":"/paper/hatecot-an-explanation-enhanced-dataset-for","slug":"hatecot-an-explanation-enhanced-dataset-for","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","date":"2024-03-18","arxiv_id":"2403.11456","n_code_links":1,"syntology":null},{"paper":"/paper/how-far-are-we-on-the-decision-making-of-llms","slug":"how-far-are-we-on-the-decision-making-of-llms","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","date":"2024-03-18","arxiv_id":"2403.11807","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cuhk-arise/gamabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-prompting-for-automating-zero-shot","slug":"meta-prompting-for-automating-zero-shot","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","date":"2024-03-18","arxiv_id":"2403.11755","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jmiemirza/meta-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metaphor-understanding-challenge-dataset-for","title":"Metaphor Understanding Challenge Dataset for LLMs","date":"2024-03-18","arxiv_id":"2403.11810","n_code_links":0,"syntology":null},{"paper":null,"slug":"shifting-the-lens-detecting-malware-in-npm","title":"Leveraging Large Language Models to Detect npm Malicious Packages","date":"2024-03-18","arxiv_id":"2403.12196","n_code_links":0,"syntology":null},{"paper":"/paper/data-is-all-you-need-finetuning-llms-for-chip","slug":"data-is-all-you-need-finetuning-llms-for-chip","title":"Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework","date":"2024-03-17","arxiv_id":"2403.11202","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 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) · 1 unverified","official":{"repos":["aichipdesign/chipgptft"],"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":"forging-the-forger-an-attempt-to-improve","title":"Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation","date":"2024-03-17","arxiv_id":"2403.11265","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-understand-medical","title":"Can Large Language Models abstract Medical Coded Language?","date":"2024-03-16","arxiv_id":"2403.10822","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-melting-pots-to-misrepresentations","title":"From Melting Pots to Misrepresentations: Exploring Harms in Generative AI","date":"2024-03-16","arxiv_id":"2403.10776","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-powered-chatbots-for","title":"Large language model-powered chatbots for internationalizing student support in higher education","date":"2024-03-16","arxiv_id":"2403.14702","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-gpt-language-models-for","title":"Application of GPT Language Models for Innovation in Activities in University Teaching","date":"2024-03-15","arxiv_id":"2403.14694","n_code_links":0,"syntology":null},{"paper":null,"slug":"exegpt-constraint-aware-resource-scheduling","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","date":"2024-03-15","arxiv_id":"2404.07947","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-condensation-and-reasoning-for","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","date":"2024-03-15","arxiv_id":"2403.10037","n_code_links":0,"syntology":null},{"paper":null,"slug":"vitcn-vision-transformer-contrastive-network","title":"ViTCN: Vision Transformer Contrastive Network For Reasoning","date":"2024-03-15","arxiv_id":"2403.09962","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-on-ai-exploring-the-utility-of-gpt-as-an","title":"AI on AI: Exploring the Utility of GPT as an Expert Annotator of AI Publications","date":"2024-03-14","arxiv_id":"2403.09097","n_code_links":0,"syntology":null},{"paper":"/paper/codeultrafeedback-an-llm-as-a-judge-dataset","slug":"codeultrafeedback-an-llm-as-a-judge-dataset","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","date":"2024-03-14","arxiv_id":"2403.09032","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":["martin-wey/codeultrafeedback"],"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":"evaluating-llms-for-gender-disparities-in","title":"Evaluating LLMs for Gender Disparities in Notable Persons","date":"2024-03-14","arxiv_id":"2403.09148","n_code_links":0,"syntology":null},{"paper":null,"slug":"komodo-a-linguistic-expedition-into-indonesia","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","date":"2024-03-14","arxiv_id":"2403.09362","n_code_links":0,"syntology":null},{"paper":null,"slug":"leap-molecular-synthesisability-scoring-with","title":"Leap: molecular synthesisability scoring with intermediates","date":"2024-03-14","arxiv_id":"2403.13005","n_code_links":0,"syntology":null},{"paper":"/paper/optimistic-verifiable-training-by-controlling","slug":"optimistic-verifiable-training-by-controlling","title":"Optimistic Verifiable Training by Controlling Hardware Nondeterminism","date":"2024-03-14","arxiv_id":"2403.09603","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":4,"n_instrument":5,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["meghabyte/verifiable-training"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/rectifying-demonstration-shortcut-in-in","slug":"rectifying-demonstration-shortcut-in-in","title":"Rectifying Demonstration Shortcut in In-Context Learning","date":"2024-03-14","arxiv_id":"2403.09488","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":1,"n_instrument":2,"unverified":6,"pointer_only":9,"phrase":"3 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; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["lainshower/in-context-calibration"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"sabia-2-a-new-generation-of-portuguese-large","title":"Sabiá-2: A New Generation of Portuguese Large Language Models","date":"2024-03-14","arxiv_id":"2403.09887","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-care-about-text-quality","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","date":"2024-03-13","arxiv_id":"2403.08693","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","n_code_links":2,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/gpt-generated-text-detection-benchmark","slug":"gpt-generated-text-detection-benchmark","title":"GPT-generated Text Detection: Benchmark Dataset and Tensor-based Detection Method","date":"2024-03-12","arxiv_id":"2403.07321","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["madlab-ucr/grid"],"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":"rethinking-aste-a-minimalist-tagging-scheme","title":"Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning","date":"2024-03-12","arxiv_id":"2403.07342","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-generative-large-language-model","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","date":"2024-03-12","arxiv_id":"2403.07872","n_code_links":0,"syntology":null},{"paper":null,"slug":"sifid-reassess-summary-factual-inconsistency","title":"SIFiD: Reassess Summary Factual Inconsistency Detection with LLM","date":"2024-03-12","arxiv_id":"2403.07557","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-future-of-document-indexing-gpt-and-donut","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","date":"2024-03-12","arxiv_id":"2403.07553","n_code_links":0,"syntology":null},{"paper":null,"slug":"development-of-a-reliable-and-accessible","title":"Development of a Reliable and Accessible Caregiving Language Model (CaLM)","date":"2024-03-11","arxiv_id":"2403.06857","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-human-llm-corpus-construction-and-llm","title":"Hybrid Human-LLM Corpus Construction and LLM Evaluation for Rare Linguistic Phenomena","date":"2024-03-11","arxiv_id":"2403.06965","n_code_links":0,"syntology":null},{"paper":null,"slug":"narrating-causal-graphs-with-large-language","title":"Narrating Causal Graphs with Large Language Models","date":"2024-03-11","arxiv_id":"2403.07118","n_code_links":0,"syntology":null},{"paper":null,"slug":"segmentation-guided-sparse-transformer-for","title":"Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration","date":"2024-03-09","arxiv_id":"2403.05906","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-nuanced-conversation-evaluation","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","date":"2024-03-08","arxiv_id":"2403.09705","n_code_links":0,"syntology":null},{"paper":"/paper/bias-augmented-consistency-training-reduces","slug":"bias-augmented-consistency-training-reduces","title":"Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought","date":"2024-03-08","arxiv_id":"2403.05518","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["raybears/cot-transparency"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rat-retrieval-augmented-thoughts-elicit","slug":"rat-retrieval-augmented-thoughts-elicit","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","date":"2024-03-08","arxiv_id":"2403.05313","n_code_links":1,"syntology":null},{"paper":"/paper/federated-recommendation-via-hybrid-retrieval","slug":"federated-recommendation-via-hybrid-retrieval","title":"Federated Recommendation via Hybrid Retrieval Augmented Generation","date":"2024-03-07","arxiv_id":"2403.04256","n_code_links":1,"syntology":null},{"paper":null,"slug":"feedback-generation-for-programming-exercises","title":"Feedback-Generation for Programming Exercises With GPT-4","date":"2024-03-07","arxiv_id":"2403.04449","n_code_links":0,"syntology":null},{"paper":null,"slug":"telecom-language-models-must-they-be-large","title":"Telecom Language Models: Must They Be Large?","date":"2024-03-07","arxiv_id":"2403.04666","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-hallucination-in-large-language","slug":"benchmarking-hallucination-in-large-language","title":"Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem","date":"2024-03-06","arxiv_id":"2403.03558","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-do-analytical","title":"Can Large Language Models do Analytical Reasoning?","date":"2024-03-06","arxiv_id":"2403.04031","n_code_links":0,"syntology":null},{"paper":null,"slug":"general2specialized-llms-translation-for-e","title":"General2Specialized LLMs Translation for E-commerce","date":"2024-03-06","arxiv_id":"2403.03689","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-enumerative-program-synthesis-with","title":"Guiding Enumerative Program Synthesis with Large Language Models","date":"2024-03-06","arxiv_id":"2403.03997","n_code_links":0,"syntology":null},{"paper":null,"slug":"japanese-english-sentence-translation","title":"Japanese-English Sentence Translation Exercises Dataset for Automatic Grading","date":"2024-03-06","arxiv_id":"2403.03396","n_code_links":0,"syntology":null},{"paper":"/paper/rapidly-developing-high-quality-instruction","slug":"rapidly-developing-high-quality-instruction","title":"Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese","date":"2024-03-06","arxiv_id":"2403.03690","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-and-optimizing-educational-content","slug":"evaluating-and-optimizing-educational-content","title":"Evaluating and Optimizing Educational Content with Large Language Model Judgments","date":"2024-03-05","arxiv_id":"2403.02795","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":["StanfordAI4HI/ed-expert-simulator"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/exploring-naive-approaches-to-tell-apart-llms","slug":"exploring-naive-approaches-to-tell-apart-llms","title":"Exploring Naive Approaches to Tell Apart LLMs Productions from Human-written Text","date":"2024-03-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-event-definition-following-for-zero","title":"Improving Event Definition Following For Zero-Shot Event Detection","date":"2024-03-05","arxiv_id":"2403.02586","n_code_links":0,"syntology":null},{"paper":"/paper/jmi-at-semeval-2024-task-3-two-step-approach","slug":"jmi-at-semeval-2024-task-3-two-step-approach","title":"JMI at SemEval 2024 Task 3: Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models","date":"2024-03-05","arxiv_id":"2403.04798","n_code_links":1,"syntology":{"ran":5,"of":12,"n_ran_checked":5,"n_instrument":0,"unverified":7,"pointer_only":12,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["cmooncs/semeval-2024_multimodal_ecpe"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"knowledge-graphs-as-context-sources-for-llm","title":"Knowledge Graphs as Context Sources for LLM-Based Explanations of Learning Recommendations","date":"2024-03-05","arxiv_id":"2403.03008","n_code_links":0,"syntology":null},{"paper":"/paper/mathscale-scaling-instruction-tuning-for","slug":"mathscale-scaling-instruction-tuning-for","title":"MathScale: Scaling Instruction Tuning for Mathematical Reasoning","date":"2024-03-05","arxiv_id":"2403.02884","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-aware-semantic-cache-for-large","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","date":"2024-03-05","arxiv_id":"2403.02694","n_code_links":0,"syntology":null},{"paper":"/paper/towards-democratized-flood-risk-management-an","slug":"towards-democratized-flood-risk-management-an","title":"Towards Democratized Flood Risk Management: An Advanced AI Assistant Enabled by GPT-4 for Enhanced Interpretability and Public Engagement","date":"2024-03-05","arxiv_id":"2403.03188","n_code_links":2,"syntology":null},{"paper":null,"slug":"zero-shot-cross-lingual-document-level-event","title":"Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning","date":"2024-03-05","arxiv_id":"2403.02893","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-generation-of-multiple-choice-cloze","title":"Automated Generation of Multiple-Choice Cloze Questions for Assessing English Vocabulary Using GPT-turbo 3.5","date":"2024-03-04","arxiv_id":"2403.02078","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-generate-architectural-design","title":"Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study","date":"2024-03-04","arxiv_id":"2403.01709","n_code_links":0,"syntology":null},{"paper":"/paper/differentially-private-synthetic-data-via-1","slug":"differentially-private-synthetic-data-via-1","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","date":"2024-03-04","arxiv_id":"2403.01749","n_code_links":2,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ai-secure/aug-pe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hypertext-entity-extraction-in-webpage","title":"Hypertext Entity Extraction in Webpage","date":"2024-03-04","arxiv_id":"2403.01698","n_code_links":0,"syntology":null},{"paper":null,"slug":"phantom-personality-has-an-effect-on-theory","title":"PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models","date":"2024-03-04","arxiv_id":"2403.02246","n_code_links":0,"syntology":null},{"paper":"/paper/protrix-building-models-for-planning-and","slug":"protrix-building-models-for-planning-and","title":"ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context","date":"2024-03-04","arxiv_id":"2403.02177","n_code_links":1,"syntology":null},{"paper":"/paper/sciassess-benchmarking-llm-proficiency-in","slug":"sciassess-benchmarking-llm-proficiency-in","title":"SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis","date":"2024-03-04","arxiv_id":"2403.01976","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["sci-assess/sciassess"],"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/using-llms-for-the-extraction-and","slug":"using-llms-for-the-extraction-and","title":"Using LLMs for the Extraction and Normalization of Product Attribute Values","date":"2024-03-04","arxiv_id":"2403.02130","n_code_links":1,"syntology":null},{"paper":"/paper/serval-synergy-learning-between-vertical","slug":"serval-synergy-learning-between-vertical","title":"SERVAL: Synergy Learning between Vertical Models and LLMs towards Oracle-Level Zero-shot Medical Prediction","date":"2024-03-03","arxiv_id":"2403.01570","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"transformers-for-supervised-online-continual","title":"Transformers for Supervised Online Continual Learning","date":"2024-03-03","arxiv_id":"2403.01554","n_code_links":0,"syntology":null},{"paper":"/paper/autodefense-multi-agent-llm-defense-against","slug":"autodefense-multi-agent-llm-defense-against","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","date":"2024-03-02","arxiv_id":"2403.04783","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":["xhmy/autodefense"],"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":null,"slug":"lm4opt-unveiling-the-potential-of-large","title":"LM4OPT: Unveiling the Potential of Large Language Models in Formulating Mathematical Optimization Problems","date":"2024-03-02","arxiv_id":"2403.01342","n_code_links":0,"syntology":null},{"paper":null,"slug":"gender-bias-in-large-language-models-across","title":"Gender Bias in Large Language Models across Multiple Languages","date":"2024-03-01","arxiv_id":"2403.00277","n_code_links":0,"syntology":null},{"paper":"/paper/softtiger-a-clinical-foundation-model-for","slug":"softtiger-a-clinical-foundation-model-for","title":"SoftTiger: A Clinical Foundation Model for Healthcare Workflows","date":"2024-03-01","arxiv_id":"2403.00868","n_code_links":1,"syntology":null},{"paper":"/paper/artist-automated-text-simplification-for-task","slug":"artist-automated-text-simplification-for-task","title":"ARTiST: Automated Text Simplification for Task Guidance in Augmented Reality","date":"2024-02-29","arxiv_id":"2402.18797","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-ensemble-optimal-large-language-model","title":"LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction","date":"2024-02-29","arxiv_id":"2403.00863","n_code_links":0,"syntology":null},{"paper":null,"slug":"proc2pddl-open-domain-planning","title":"PROC2PDDL: Open-Domain Planning Representations from Texts","date":"2024-02-29","arxiv_id":"2403.00092","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-chatgpt-for-translation-a","title":"Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts","date":"2024-02-29","arxiv_id":"2403.00127","n_code_links":0,"syntology":null},{"paper":null,"slug":"rl-gpt-integrating-reinforcement-learning-and","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy","date":"2024-02-29","arxiv_id":"2402.19299","n_code_links":0,"syntology":null},{"paper":null,"slug":"vixen-visual-text-comparison-network-for","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","date":"2024-02-29","arxiv_id":"2402.19119","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-gpt-improve-the-state-of-prior","title":"Can GPT Improve the State of Prior Authorization via Guideline Based Automated Question Answering?","date":"2024-02-28","arxiv_id":"2402.18419","n_code_links":0,"syntology":null},{"paper":"/paper/clustering-and-ranking-diversity-preserved","slug":"clustering-and-ranking-diversity-preserved","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","date":"2024-02-28","arxiv_id":"2402.18191","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ironbeliever/car"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"decomposed-prompting-unveiling-multilingual","title":"Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models","date":"2024-02-28","arxiv_id":"2402.18397","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-free-adaptive-global-pruning-for-pre","slug":"gradient-free-adaptive-global-pruning-for-pre","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","date":"2024-02-28","arxiv_id":"2402.17946","n_code_links":2,"syntology":{"ran":3,"of":9,"n_ran_checked":2,"n_instrument":1,"unverified":6,"pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","official":{"repos":["baithebest/adagp","baithebest/sparsellm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/keeping-llms-aligned-after-fine-tuning-the","slug":"keeping-llms-aligned-after-fine-tuning-the","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","date":"2024-02-28","arxiv_id":"2402.18540","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":5,"n_instrument":1,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vfleaking/ptst"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-language-model-based-framework-for-new","slug":"a-language-model-based-framework-for-new","title":"A Language Model based Framework for New Concept Placement in Ontologies","date":"2024-02-27","arxiv_id":"2402.17897","n_code_links":1,"syntology":null},{"paper":null,"slug":"cocoa-cbt-based-conversational-counseling","title":"COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt","date":"2024-02-27","arxiv_id":"2402.17546","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-detection-method-for-large","title":"Deep Learning Detection Method for Large Language Models-Generated Scientific Content","date":"2024-02-27","arxiv_id":"2403.00828","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-vision-language-stem-skills-of","slug":"measuring-vision-language-stem-skills-of","title":"Measuring Vision-Language STEM Skills of Neural Models","date":"2024-02-27","arxiv_id":"2402.17205","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":["stemdataset/STEM"],"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/variational-learning-is-effective-for-large","slug":"variational-learning-is-effective-for-large","title":"Variational Learning is Effective for Large Deep Networks","date":"2024-02-27","arxiv_id":"2402.17641","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["team-approx-bayes/ivon"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-integrated-data-processing-framework-for","slug":"an-integrated-data-processing-framework-for","title":"An Integrated Data Processing Framework for Pretraining Foundation Models","date":"2024-02-26","arxiv_id":"2402.16358","n_code_links":2,"syntology":null},{"paper":"/paper/chatmusician-understanding-and-generating","slug":"chatmusician-understanding-and-generating","title":"ChatMusician: Understanding and Generating Music Intrinsically with LLM","date":"2024-02-25","arxiv_id":"2402.16153","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["hf-lin/ChatMusician"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-learning-approaches-for-improving","title":"Deep Learning Approaches for Improving Question Answering Systems in Hepatocellular Carcinoma Research","date":"2024-02-25","arxiv_id":"2402.16038","n_code_links":0,"syntology":null},{"paper":"/paper/fusechat-knowledge-fusion-of-chat-models","slug":"fusechat-knowledge-fusion-of-chat-models","title":"Knowledge Fusion of Chat LLMs: A Preliminary Technical Report","date":"2024-02-25","arxiv_id":"2402.16107","n_code_links":2,"syntology":null},{"paper":null,"slug":"llms-can-defend-themselves-against","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper","date":"2024-02-24","arxiv_id":"2402.15727","n_code_links":0,"syntology":null},{"paper":null,"slug":"look-before-you-leap-problem-elaboration","title":"Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models","date":"2024-02-24","arxiv_id":"2402.15764","n_code_links":0,"syntology":null},{"paper":null,"slug":"prp-propagating-universal-perturbations-to","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","date":"2024-02-24","arxiv_id":"2402.15911","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-first-look-at-gpt-apps-landscape-and","title":"A First Look at GPT Apps: Landscape and Vulnerability","date":"2024-02-23","arxiv_id":"2402.15105","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-parameter-efficiency-in-fine-tuning","slug":"advancing-parameter-efficiency-in-fine-tuning","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","date":"2024-02-23","arxiv_id":"2402.15179","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"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":{"repos":["mlwu22/red"],"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":["listed","official"]}}},{"paper":"/paper/attributionbench-how-hard-is-automatic","slug":"attributionbench-how-hard-is-automatic","title":"AttributionBench: How Hard is Automatic Attribution Evaluation?","date":"2024-02-23","arxiv_id":"2402.15089","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-large-language-models-for-domain","title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","date":"2024-02-23","arxiv_id":"2402.15061","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-llms-to-compose-meta-review-drafts","slug":"prompting-llms-to-compose-meta-review-drafts","title":"LLMs as Meta-Reviewers' Assistants: A Case Study","date":"2024-02-23","arxiv_id":"2402.15589","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-detect","title":"Can Large Language Models Detect Misinformation in Scientific News Reporting?","date":"2024-02-22","arxiv_id":"2402.14268","n_code_links":0,"syntology":null},{"paper":null,"slug":"copilot-evaluation-harness-evaluating-llm","title":"Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming","date":"2024-02-22","arxiv_id":"2402.14261","n_code_links":0,"syntology":null},{"paper":"/paper/hint-before-solving-prompting-guiding-llms-to","slug":"hint-before-solving-prompting-guiding-llms-to","title":"Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded Knowledge","date":"2024-02-22","arxiv_id":"2402.14310","n_code_links":1,"syntology":null}],"record_sha256":"aa2762260f81af3b4cce099d022cfa3afd431c33350dafed293ec1dfe3bd84c4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}