{"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":"/task/prompt-engineering/papers/2","list_of":"/task/prompt-engineering","task":"Prompt Engineering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":13,"rows_per_page":100,"rows":[101,200],"of":1236,"counts":{"archive_papers_tagged":1236,"with_a_code_link":454,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1236,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":118,"every_run_a_failure_of_syntologys_instrument":25,"listed_with_a_run_with_no_instrument_failure":118,"listed_every_run_a_failure_of_syntologys_instrument":25,"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":"/task/prompt-engineering","prev":"/task/prompt-engineering","next":"/task/prompt-engineering/papers/3","papers":[{"url":"/paper/sugar-coated-poison-benign-generation-unlocks","slug":"sugar-coated-poison-benign-generation-unlocks","title":"Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking","date":"2025-04-08","arxiv_id":"2504.05652","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-the-next-token-towards-prompt-robust","slug":"beyond-the-next-token-towards-prompt-robust","title":"Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction","date":"2025-04-04","arxiv_id":"2504.03159","repositories_listed":1,"syntology":null},{"url":"/paper/deepresearcher-scaling-deep-research-via","slug":"deepresearcher-scaling-deep-research-via","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","date":"2025-04-04","arxiv_id":"2504.03160","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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","sample_list":"/paper/deepresearcher-scaling-deep-research-via#ran","syntology_url":"https://syntology.ai/paper/2504.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03160"}},"official":{"repos":["gair-nlp/deepresearcher"],"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"]}}},{"url":"/paper/large-vision-language-models-are-unsupervised","slug":"large-vision-language-models-are-unsupervised","title":"Large (Vision) Language Models are Unsupervised In-Context Learners","date":"2025-04-03","arxiv_id":"2504.02349","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/large-vision-language-models-are-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2504.02349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02349"}},"official":{"repos":["mlbio-epfl/joint-inference"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompting-vision-language-model-for-nuclei","slug":"prompting-vision-language-model-for-nuclei","title":"Prompting Vision-Language Model for Nuclei Instance Segmentation and Classification","date":"2025-03-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-efficient-long-to-short-llm","slug":"unlocking-efficient-long-to-short-llm","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","date":"2025-03-26","arxiv_id":"2503.20641","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-photonic-structures-with-large","slug":"optimizing-photonic-structures-with-large","title":"Optimizing Photonic Structures with Large Language Model Driven Algorithm Discovery","date":"2025-03-25","arxiv_id":"2503.19742","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-mathematical-reasoning-and","slug":"a-survey-on-mathematical-reasoning-and","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","date":"2025-03-22","arxiv_id":"2503.17726","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-the-optimization-of-large","slug":"a-survey-on-the-optimization-of-large","title":"A Survey on the Optimization of Large Language Model-based Agents","date":"2025-03-16","arxiv_id":"2503.12434","repositories_listed":1,"syntology":null},{"url":"/paper/molex-mixture-of-layer-experts-for-finetuning","slug":"molex-mixture-of-layer-experts-for-finetuning","title":"MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling","date":"2025-03-14","arxiv_id":"2503.11144","repositories_listed":1,"syntology":null},{"url":"/paper/lend-a-hand-semi-training-free-cued-speech","slug":"lend-a-hand-semi-training-free-cued-speech","title":"Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free Communication","date":"2025-03-11","arxiv_id":"2503.21785","repositories_listed":1,"syntology":null},{"url":"/paper/mmrl-multi-modal-representation-learning-for","slug":"mmrl-multi-modal-representation-learning-for","title":"MMRL: Multi-Modal Representation Learning for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08497","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mmrl-multi-modal-representation-learning-for#ran","syntology_url":"https://syntology.ai/paper/2503.08497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08497"}},"official":{"repos":["yunncheng/MMRL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/modeling-variants-of-prompts-for-vision","slug":"modeling-variants-of-prompts-for-vision","title":"Modeling Variants of Prompts for Vision-Language Models","date":"2025-03-11","arxiv_id":"2503.08229","repositories_listed":1,"syntology":null},{"url":"/paper/limtopic-llm-based-topic-modeling-and-text","slug":"limtopic-llm-based-topic-modeling-and-text","title":"LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations","date":"2025-03-08","arxiv_id":"2503.10658","repositories_listed":1,"syntology":null},{"url":"/paper/can-frontier-llms-replace-annotators-in","slug":"can-frontier-llms-replace-annotators-in","title":"Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions","date":"2025-03-05","arxiv_id":"2503.03261","repositories_listed":1,"syntology":null},{"url":"/paper/2503-01163","slug":"2503-01163","title":"Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers","date":"2025-03-03","arxiv_id":"2503.01163","repositories_listed":1,"syntology":null},{"url":"/paper/nutrigen-personalized-meal-plan-generator","slug":"nutrigen-personalized-meal-plan-generator","title":"NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence","date":"2025-02-28","arxiv_id":"2502.20601","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-fine-tuning-on-scaled-survey","slug":"language-model-fine-tuning-on-scaled-survey","title":"Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions","date":"2025-02-24","arxiv_id":"2502.16761","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/language-model-fine-tuning-on-scaled-survey#ran","syntology_url":"https://syntology.ai/paper/2502.16761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16761"}},"official":{"repos":["josephjeesungsuh/subpop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/code-summarization-beyond-function-level","slug":"code-summarization-beyond-function-level","title":"Code Summarization Beyond Function Level","date":"2025-02-23","arxiv_id":"2502.16704","repositories_listed":1,"syntology":null},{"url":"/paper/control-illusion-the-failure-of-instruction","slug":"control-illusion-the-failure-of-instruction","title":"Control Illusion: The Failure of Instruction Hierarchies in Large Language Models","date":"2025-02-21","arxiv_id":"2502.15851","repositories_listed":1,"syntology":null},{"url":"/paper/can-llms-predict-citation-intent-an","slug":"can-llms-predict-citation-intent-an","title":"Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs","date":"2025-02-20","arxiv_id":"2502.14561","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-prefix-tree-in-structured-output","slug":"exploiting-prefix-tree-in-structured-output","title":"Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking","date":"2025-02-19","arxiv_id":"2502.13527","repositories_listed":1,"syntology":null},{"url":"/paper/testing-prompt-engineering-methods-for","slug":"testing-prompt-engineering-methods-for","title":"Testing Prompt Engineering Methods for Knowledge Extraction from Text","date":"2025-02-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-improvements-on-using-large","slug":"evaluating-improvements-on-using-large","title":"Evaluating improvements on using Large Language Models (LLMs) for property extraction in the Open Research Knowledge Graph (ORKG)","date":"2025-02-15","arxiv_id":"2502.10768","repositories_listed":1,"syntology":null},{"url":"/paper/the-ann-arbor-architecture-for-agent-oriented","slug":"the-ann-arbor-architecture-for-agent-oriented","title":"The Ann Arbor Architecture for Agent-Oriented Programming","date":"2025-02-14","arxiv_id":"2502.09903","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-reasoning-to-adapt-large-language","slug":"enhancing-reasoning-to-adapt-large-language","title":"Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications","date":"2025-02-05","arxiv_id":"2502.04384","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 2 unverified","sample_list":"/paper/enhancing-reasoning-to-adapt-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.04384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04384"}},"official":{"repos":["wenboown/generative-ai-for-semiconductor-physical-design"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/picbench-benchmarking-llms-for-photonic","slug":"picbench-benchmarking-llms-for-photonic","title":"PICBench: Benchmarking LLMs for Photonic Integrated Circuits Design","date":"2025-02-05","arxiv_id":"2502.03159","repositories_listed":1,"syntology":null},{"url":"/paper/llm-ta-an-llm-enhanced-thematic-analysis","slug":"llm-ta-an-llm-enhanced-thematic-analysis","title":"LLM-TA: An LLM-Enhanced Thematic Analysis Pipeline for Transcripts from Parents of Children with Congenital Heart Disease","date":"2025-02-03","arxiv_id":"2502.01620","repositories_listed":1,"syntology":null},{"url":"/paper/logits-are-all-we-need-to-adapt-closed-models","slug":"logits-are-all-we-need-to-adapt-closed-models","title":"Logits are All We Need to Adapt Closed Models","date":"2025-02-03","arxiv_id":"2502.06806","repositories_listed":1,"syntology":null},{"url":"/paper/auto-differentiating-any-llm-workflow-a","slug":"auto-differentiating-any-llm-workflow-a","title":"LLM-AutoDiff: Auto-Differentiate Any LLM Workflow","date":"2025-01-28","arxiv_id":"2501.16673","repositories_listed":1,"syntology":null},{"url":"/paper/a-zero-shot-llm-framework-for-automatic","slug":"a-zero-shot-llm-framework-for-automatic","title":"A Zero-Shot LLM Framework for Automatic Assignment Grading in Higher Education","date":"2025-01-24","arxiv_id":"2501.14305","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-gpt-s-ability-as-a-judge-in-music","slug":"exploring-gpt-s-ability-as-a-judge-in-music","title":"Exploring GPT's Ability as a Judge in Music Understanding","date":"2025-01-22","arxiv_id":"2501.13261","repositories_listed":1,"syntology":null},{"url":"/paper/network-informed-prompt-engineering-against","slug":"network-informed-prompt-engineering-against","title":"Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance","date":"2025-01-21","arxiv_id":"2501.11849","repositories_listed":1,"syntology":null},{"url":"/paper/mygo-multiplex-cot-a-method-for-self","slug":"mygo-multiplex-cot-a-method-for-self","title":"MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking","date":"2025-01-20","arxiv_id":"2501.13117","repositories_listed":1,"syntology":null},{"url":"/paper/medfilip-medical-fine-grained-language-image","slug":"medfilip-medical-fine-grained-language-image","title":"MedFILIP: Medical Fine-grained Language-Image Pre-training","date":"2025-01-18","arxiv_id":"2501.10775","repositories_listed":1,"syntology":null},{"url":"/paper/pixels-progressive-image-xemplar-based","slug":"pixels-progressive-image-xemplar-based","title":"PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery","date":"2025-01-16","arxiv_id":"2501.09826","repositories_listed":1,"syntology":null},{"url":"/paper/can-large-language-models-predict-the-outcome","slug":"can-large-language-models-predict-the-outcome","title":"Can Large Language Models Predict the Outcome of Judicial Decisions?","date":"2025-01-15","arxiv_id":"2501.09768","repositories_listed":1,"syntology":null},{"url":"/paper/tapo-task-referenced-adaptation-for-prompt","slug":"tapo-task-referenced-adaptation-for-prompt","title":"TAPO: Task-Referenced Adaptation for Prompt Optimization","date":"2025-01-12","arxiv_id":"2501.06689","repositories_listed":1,"syntology":null},{"url":"/paper/labels-generated-by-large-language-model","slug":"labels-generated-by-large-language-model","title":"Labels Generated by Large Language Model Helps Measuring People's Empathy in Vitro","date":"2025-01-01","arxiv_id":"2501.00691","repositories_listed":1,"syntology":null},{"url":"/paper/the-impact-of-prompt-programming-on-function","slug":"the-impact-of-prompt-programming-on-function","title":"The Impact of Prompt Programming on Function-Level Code Generation","date":"2024-12-29","arxiv_id":"2412.20545","repositories_listed":1,"syntology":null},{"url":"/paper/agreemate-teaching-llms-to-haggle","slug":"agreemate-teaching-llms-to-haggle","title":"AgreeMate: Teaching LLMs to Haggle","date":"2024-12-24","arxiv_id":"2412.18690","repositories_listed":1,"syntology":null},{"url":"/paper/cof-coarse-to-fine-grained-image","slug":"cof-coarse-to-fine-grained-image","title":"CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models","date":"2024-12-22","arxiv_id":"2412.16869","repositories_listed":1,"syntology":null},{"url":"/paper/adaptations-of-ai-models-for-querying-the","slug":"adaptations-of-ai-models-for-querying-the","title":"Adaptations of AI models for querying the LandMatrix database in natural language","date":"2024-12-17","arxiv_id":"2412.12961","repositories_listed":1,"syntology":null},{"url":"/paper/combining-large-language-models-with-tutoring","slug":"combining-large-language-models-with-tutoring","title":"Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework Support","date":"2024-12-16","arxiv_id":"2412.11995","repositories_listed":1,"syntology":null},{"url":"/paper/rag-playground-a-framework-for-systematic","slug":"rag-playground-a-framework-for-systematic","title":"RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems","date":"2024-12-16","arxiv_id":"2412.12322","repositories_listed":1,"syntology":null},{"url":"/paper/dual-traits-in-probabilistic-reasoning-of","slug":"dual-traits-in-probabilistic-reasoning-of","title":"Dual Traits in Probabilistic Reasoning of Large Language Models","date":"2024-12-15","arxiv_id":"2412.11009","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-the-reasoning-capabilities-of-small","slug":"enhancing-the-reasoning-capabilities-of-small","title":"Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning","date":"2024-12-13","arxiv_id":"2412.09906","repositories_listed":1,"syntology":null},{"url":"/paper/greater-gradients-over-reasoning-makes","slug":"greater-gradients-over-reasoning-makes","title":"GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers","date":"2024-12-12","arxiv_id":"2412.09722","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/greater-gradients-over-reasoning-makes#ran","syntology_url":"https://syntology.ai/paper/2412.09722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09722"}},"official":{"repos":["psunlpgroup/greater"],"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"]}}},{"url":"/paper/kajal-extracting-grammar-of-a-source-code","slug":"kajal-extracting-grammar-of-a-source-code","title":"Kajal: Extracting Grammar of a Source Code Using Large Language Models","date":"2024-12-12","arxiv_id":"2412.08842","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-for-scholarly-ontology","slug":"large-language-models-for-scholarly-ontology","title":"Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field","date":"2024-12-11","arxiv_id":"2412.08258","repositories_listed":1,"syntology":null},{"url":"/paper/3d-part-segmentation-via-geometric","slug":"3d-part-segmentation-via-geometric","title":"3D Part Segmentation via Geometric Aggregation of 2D Visual Features","date":"2024-12-05","arxiv_id":"2412.04247","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/3d-part-segmentation-via-geometric#ran","syntology_url":"https://syntology.ai/paper/2412.04247","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04247"}},"official":{"repos":["marco-garosi/COPS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revolve-optimizing-ai-systems-by-tracking","slug":"revolve-optimizing-ai-systems-by-tracking","title":"Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization","date":"2024-12-04","arxiv_id":"2412.03092","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/revolve-optimizing-ai-systems-by-tracking#ran","syntology_url":"https://syntology.ai/paper/2412.03092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03092"}},"official":{"repos":["peiyance/revolve"],"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"]}}},{"url":"/paper/can-we-afford-the-perfect-prompt-balancing","slug":"can-we-afford-the-perfect-prompt-balancing","title":"Can We Afford The Perfect Prompt? Balancing Cost and Accuracy with the Economical Prompting Index","date":"2024-12-02","arxiv_id":"2412.01690","repositories_listed":1,"syntology":null},{"url":"/paper/llms4life-large-language-models-for-ontology","slug":"llms4life-large-language-models-for-ontology","title":"LLMs4Life: Large Language Models for Ontology Learning in Life Sciences","date":"2024-12-02","arxiv_id":"2412.02035","repositories_listed":1,"syntology":null},{"url":"/paper/quallm-health-an-adaptation-of-an-llm-based","slug":"quallm-health-an-adaptation-of-an-llm-based","title":"QuaLLM-Health: An Adaptation of an LLM-Based Framework for Quantitative Data Extraction from Online Health Discussions","date":"2024-11-27","arxiv_id":"2411.17967","repositories_listed":1,"syntology":null},{"url":"/paper/don-t-command-cultivate-an-exploratory-study","slug":"don-t-command-cultivate-an-exploratory-study","title":"Don't Command, Cultivate: An Exploratory Study of System-2 Alignment","date":"2024-11-26","arxiv_id":"2411.17075","repositories_listed":1,"syntology":null},{"url":"/paper/assertify-utilizing-large-language-models-to","slug":"assertify-utilizing-large-language-models-to","title":"ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code","date":"2024-11-25","arxiv_id":"2411.16927","repositories_listed":1,"syntology":null},{"url":"/paper/med-persam-one-shot-visual-prompt-tuning-for","slug":"med-persam-one-shot-visual-prompt-tuning-for","title":"Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain","date":"2024-11-25","arxiv_id":"2411.16123","repositories_listed":1,"syntology":null},{"url":"/paper/instruct-or-interact-exploring-and-eliciting","slug":"instruct-or-interact-exploring-and-eliciting","title":"Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt Engineering","date":"2024-11-23","arxiv_id":"2411.15501","repositories_listed":1,"syntology":null},{"url":"/paper/biomedcoop-learning-to-prompt-for-biomedical","slug":"biomedcoop-learning-to-prompt-for-biomedical","title":"BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models","date":"2024-11-21","arxiv_id":"2411.15232","repositories_listed":1,"syntology":null},{"url":"/paper/robust-planning-with-compound-llm","slug":"robust-planning-with-compound-llm","title":"Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach","date":"2024-11-20","arxiv_id":"2411.14484","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-pose-to-image-improving","slug":"from-text-to-pose-to-image-improving","title":"From Text to Pose to Image: Improving Diffusion Model Control and Quality","date":"2024-11-19","arxiv_id":"2411.12872","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-text-to-pose-to-image-improving#ran","syntology_url":"https://syntology.ai/paper/2411.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12872"}},"official":{"repos":["clement-bonnet/text-to-pose"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/empowering-meta-analysis-leveraging-large","slug":"empowering-meta-analysis-leveraging-large","title":"Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis","date":"2024-11-16","arxiv_id":"2411.10878","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-chatgpt-3-5-efficiency-in-solving","slug":"evaluating-chatgpt-3-5-efficiency-in-solving","title":"Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis","date":"2024-11-12","arxiv_id":"2411.07529","repositories_listed":1,"syntology":null},{"url":"/paper/likelihood-as-a-performance-gauge-for","slug":"likelihood-as-a-performance-gauge-for","title":"Likelihood as a Performance Gauge for Retrieval-Augmented Generation","date":"2024-11-12","arxiv_id":"2411.07773","repositories_listed":1,"syntology":null},{"url":"/paper/tipo-text-to-image-with-text-presampling-for","slug":"tipo-text-to-image-with-text-presampling-for","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","date":"2024-11-12","arxiv_id":"2411.08127","repositories_listed":1,"syntology":null},{"url":"/paper/llms-as-method-actors-a-model-for-prompt","slug":"llms-as-method-actors-a-model-for-prompt","title":"LLMs as Method Actors: A Model for Prompt Engineering and Architecture","date":"2024-11-08","arxiv_id":"2411.05778","repositories_listed":1,"syntology":null},{"url":"/paper/web-archives-metadata-generation-with-gpt-4o","slug":"web-archives-metadata-generation-with-gpt-4o","title":"Web Archives Metadata Generation with GPT-4o: Challenges and Insights","date":"2024-11-08","arxiv_id":"2411.05409","repositories_listed":1,"syntology":null},{"url":"/paper/ask-and-it-shall-be-given-turing-completeness","slug":"ask-and-it-shall-be-given-turing-completeness","title":"Ask, and it shall be given: On the Turing completeness of prompting","date":"2024-11-04","arxiv_id":"2411.01992","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-vision-language-action-models-on","slug":"benchmarking-vision-language-action-models-on","title":"Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks","date":"2024-11-04","arxiv_id":"2411.05821","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-code","slug":"leveraging-large-language-models-for-code","title":"Leveraging Large Language Models for Code Translation and Software Development in Scientific Computing","date":"2024-10-31","arxiv_id":"2410.24119","repositories_listed":1,"syntology":null},{"url":"/paper/sg-bench-evaluating-llm-safety-generalization","slug":"sg-bench-evaluating-llm-safety-generalization","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","date":"2024-10-29","arxiv_id":"2410.21965","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/sg-bench-evaluating-llm-safety-generalization#ran","syntology_url":"https://syntology.ai/paper/2410.21965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21965"}},"official":{"repos":["MurrayTom/SG-Bench"],"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"]}}},{"url":"/paper/provable-optimal-transport-with-transformers","slug":"provable-optimal-transport-with-transformers","title":"Provable optimal transport with transformers: The essence of depth and prompt engineering","date":"2024-10-25","arxiv_id":"2410.19931","repositories_listed":1,"syntology":null},{"url":"/paper/demystifying-large-language-models-for","slug":"demystifying-large-language-models-for","title":"Demystifying Large Language Models for Medicine: A Primer","date":"2024-10-24","arxiv_id":"2410.18856","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-foundation-models-on-exceptional","slug":"benchmarking-foundation-models-on-exceptional","title":"Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation","date":"2024-10-23","arxiv_id":"2410.18001","repositories_listed":1,"syntology":null},{"url":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","repositories_listed":1,"syntology":null},{"url":"/paper/comparative-study-of-multilingual-idioms-and","slug":"comparative-study-of-multilingual-idioms-and","title":"Comparative Study of Multilingual Idioms and Similes in Large Language Models","date":"2024-10-21","arxiv_id":"2410.16461","repositories_listed":1,"syntology":null},{"url":"/paper/causality-for-large-language-models","slug":"causality-for-large-language-models","title":"Causality for Large Language Models","date":"2024-10-20","arxiv_id":"2410.15319","repositories_listed":1,"syntology":null},{"url":"/paper/do-llms-know-internally-when-they-follow","slug":"do-llms-know-internally-when-they-follow","title":"Do LLMs \"know\" internally when they follow instructions?","date":"2024-10-18","arxiv_id":"2410.14516","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"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) · 5 unverified","sample_list":"/paper/do-llms-know-internally-when-they-follow#ran","syntology_url":"https://syntology.ai/paper/2410.14516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14516"}},"official":{"repos":["apple/ml-internal-llms-instruction-following"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mcqg-srefine-multiple-choice-question","slug":"mcqg-srefine-multiple-choice-question","title":"MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback","date":"2024-10-17","arxiv_id":"2410.13191","repositories_listed":1,"syntology":null},{"url":"/paper/samreg-sam-enabled-image-registration-with","slug":"samreg-sam-enabled-image-registration-with","title":"SAMReg: SAM-enabled Image Registration with ROI-based Correspondence","date":"2024-10-17","arxiv_id":"2410.14083","repositories_listed":1,"syntology":null},{"url":"/paper/self-pluralising-culture-alignment-for-large","slug":"self-pluralising-culture-alignment-for-large","title":"Self-Pluralising Culture Alignment for Large Language Models","date":"2024-10-16","arxiv_id":"2410.12971","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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","sample_list":"/paper/self-pluralising-culture-alignment-for-large#ran","syntology_url":"https://syntology.ai/paper/2410.12971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12971"}},"official":{"repos":["shaoyangxu/culturespa"],"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"]}}},{"url":"/paper/generalizing-segmentation-foundation-model","slug":"generalizing-segmentation-foundation-model","title":"Generalizing Segmentation Foundation Model Under Sim-to-real Domain-shift for Guidewire Segmentation in X-ray Fluoroscopy","date":"2024-10-09","arxiv_id":"2410.07460","repositories_listed":1,"syntology":null},{"url":"/paper/towards-world-simulator-crafting-physical","slug":"towards-world-simulator-crafting-physical","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","date":"2024-10-07","arxiv_id":"2410.05363","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-world-simulator-crafting-physical#ran","syntology_url":"https://syntology.ai/paper/2410.05363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05363"}},"official":{"repos":["opengvlab/phygenbench"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enriching-ontologies-with-disjointness-axioms","slug":"enriching-ontologies-with-disjointness-axioms","title":"Enriching Ontologies with Disjointness Axioms using Large Language Models","date":"2024-10-04","arxiv_id":"2410.03235","repositories_listed":1,"syntology":null},{"url":"/paper/can-llms-reliably-simulate-human-learner","slug":"can-llms-reliably-simulate-human-learner","title":"Can LLMs Reliably Simulate Human Learner Actions? A Simulation Authoring Framework for Open-Ended Learning Environments","date":"2024-10-03","arxiv_id":"2410.02110","repositories_listed":1,"syntology":null},{"url":"/paper/crispo-multi-aspect-critique-suggestion","slug":"crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","arxiv_id":"2410.02748","repositories_listed":1,"syntology":null},{"url":"/paper/a-versatile-machine-learning-workflow-for","slug":"a-versatile-machine-learning-workflow-for","title":"A versatile machine learning workflow for high-throughput analysis of supported metal catalyst particles","date":"2024-10-02","arxiv_id":"2410.01213","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-deductive-coding-in-discourse","slug":"automatic-deductive-coding-in-discourse","title":"Automatic deductive coding in discourse analysis: an application of large language models in learning analytics","date":"2024-10-02","arxiv_id":"2410.01240","repositories_listed":1,"syntology":null},{"url":"/paper/rgd-multi-llm-based-agent-debugger-via","slug":"rgd-multi-llm-based-agent-debugger-via","title":"RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidance","date":"2024-10-02","arxiv_id":"2410.01242","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-scores-a-modular-rag-based-system-for","slug":"beyond-scores-a-modular-rag-based-system-for","title":"Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback","date":"2024-09-30","arxiv_id":"2409.20042","repositories_listed":1,"syntology":null},{"url":"/paper/beats-optimizing-llm-mathematical","slug":"beats-optimizing-llm-mathematical","title":"BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search","date":"2024-09-26","arxiv_id":"2409.17972","repositories_listed":1,"syntology":null},{"url":"/paper/retrospective-comparative-analysis-of","slug":"retrospective-comparative-analysis-of","title":"Retrospective Comparative Analysis of Prostate Cancer In-Basket Messages: Responses from Closed-Domain LLM vs. Clinical Teams","date":"2024-09-26","arxiv_id":"2409.18290","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-token-generation-in-large","slug":"counterfactual-token-generation-in-large","title":"Counterfactual Token Generation in Large Language Models","date":"2024-09-25","arxiv_id":"2409.17027","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counterfactual-token-generation-in-large#ran","syntology_url":"https://syntology.ai/paper/2409.17027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17027"}},"official":{"repos":["networks-learning/counterfactual-llms"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revise-reason-and-recognize-llm-based-emotion","slug":"revise-reason-and-recognize-llm-based-emotion","title":"Revise, Reason, and Recognize: LLM-Based Emotion Recognition via Emotion-Specific Prompts and ASR Error Correction","date":"2024-09-23","arxiv_id":"2409.15551","repositories_listed":1,"syntology":null},{"url":"/paper/tsclip-robust-clip-fine-tuning-for-worldwide","slug":"tsclip-robust-clip-fine-tuning-for-worldwide","title":"TSCLIP: Robust CLIP Fine-Tuning for Worldwide Cross-Regional Traffic Sign Recognition","date":"2024-09-23","arxiv_id":"2409.15077","repositories_listed":1,"syntology":null},{"url":"/paper/2409-14175","slug":"2409-14175","title":"QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling","date":"2024-09-21","arxiv_id":"2409.14175","repositories_listed":1,"syntology":null},{"url":"/paper/minstrel-structural-prompt-generation-with","slug":"minstrel-structural-prompt-generation-with","title":"Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts","date":"2024-09-20","arxiv_id":"2409.13449","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/minstrel-structural-prompt-generation-with#ran","syntology_url":"https://syntology.ai/paper/2409.13449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13449"}},"official":{"repos":["sci-m-wang/minstrel"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/propaganda-is-all-you-need","slug":"propaganda-is-all-you-need","title":"Propaganda is all you need","date":"2024-09-13","arxiv_id":"2410.01810","repositories_listed":1,"syntology":null},{"url":"/paper/what-you-say-what-you-want-teaching-humans-to","slug":"what-you-say-what-you-want-teaching-humans-to","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","date":"2024-09-13","arxiv_id":"2409.08775","repositories_listed":1,"syntology":null}],"record_sha256":"3a3b5acc4b1c8cda19cd9eae77830fe98c272acfffeb9a6f3f89a120c5ce0a81","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}