{"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/8","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":8,"pages_in_order":38,"rows_per_page":100,"rows":[701,800],"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/7","next":"/method/linear-warmup-with-cosine-annealing/papers/9","papers":[{"paper":null,"slug":"emmett-efficient-multimodal-machine","title":"EMMeTT: Efficient Multimodal Machine Translation Training","date":"2024-09-20","arxiv_id":"2409.13523","n_code_links":0,"syntology":null},{"paper":"/paper/fair-gpt-a-virtual-consultant-for-research","slug":"fair-gpt-a-virtual-consultant-for-research","title":"FAIR GPT: A virtual consultant for research data management in ChatGPT","date":"2024-09-20","arxiv_id":"2410.07108","n_code_links":1,"syntology":null},{"paper":null,"slug":"hut-a-more-computation-efficient-fine-tuning","title":"HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation","date":"2024-09-20","arxiv_id":"2409.13501","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-knowledge-graphs-and-llms-to","title":"Leveraging Knowledge Graphs and LLMs to Support and Monitor Legislative Systems","date":"2024-09-20","arxiv_id":"2409.13252","n_code_links":0,"syntology":null},{"paper":"/paper/neural-symbolic-collaborative-distillation","slug":"neural-symbolic-collaborative-distillation","title":"Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks","date":"2024-09-20","arxiv_id":"2409.13203","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":4,"n_instrument":2,"unverified":1,"pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["xnhyacinth/nesycd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"talkmosaic-interactive-photomosaic-with-multi","title":"TalkMosaic: Interactive PhotoMosaic with Multi-modal LLM Q&A Interactions","date":"2024-09-20","arxiv_id":"2409.13941","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-tinybert-for-financial-sentiment-1","slug":"enhancing-tinybert-for-financial-sentiment-1","title":"Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillation","date":"2024-09-19","arxiv_id":"2409.18999","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-effectiveness-of-llms-for-manual-test","title":"On the Effectiveness of LLMs for Manual Test Verifications","date":"2024-09-19","arxiv_id":"2409.12405","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-test-generation-how-far","title":"Retrieval-Augmented Test Generation: How Far Are We?","date":"2024-09-19","arxiv_id":"2409.12682","n_code_links":0,"syntology":null},{"paper":"/paper/magicore-multi-agent-iterative-coarse-to-fine","slug":"magicore-multi-agent-iterative-coarse-to-fine","title":"MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning","date":"2024-09-18","arxiv_id":"2409.12147","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dinobby/magicore"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"recommendation-with-generative-models","title":"Recommendation with Generative Models","date":"2024-09-18","arxiv_id":"2409.15173","n_code_links":0,"syntology":null},{"paper":"/paper/tart-an-open-source-tool-augmented-framework","slug":"tart-an-open-source-tool-augmented-framework","title":"TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning","date":"2024-09-18","arxiv_id":"2409.11724","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-framework-to-classify-business","title":"A Unified Framework to Classify Business Activities into International Standard Industrial Classification through Large Language Models for Circular Economy","date":"2024-09-17","arxiv_id":"2409.18988","n_code_links":0,"syntology":null},{"paper":"/paper/small-language-models-can-outperform-humans","slug":"small-language-models-can-outperform-humans","title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","date":"2024-09-17","arxiv_id":"2409.11547","n_code_links":1,"syntology":null},{"paper":"/paper/benchmarking-large-language-model-uncertainty","slug":"benchmarking-large-language-model-uncertainty","title":"Benchmarking Large Language Model Uncertainty for Prompt Optimization","date":"2024-09-16","arxiv_id":"2409.10044","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-der-a-named-entity-recognition-method","title":"LLM-DER:A Named Entity Recognition Method Based on Large Language Models for Chinese Coal Chemical Domain","date":"2024-09-16","arxiv_id":"2409.10077","n_code_links":0,"syntology":null},{"paper":"/paper/select-sql-self-correcting-ensemble-chain-of","slug":"select-sql-self-correcting-ensemble-chain-of","title":"SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL","date":"2024-09-16","arxiv_id":"2409.10007","n_code_links":1,"syntology":null},{"paper":null,"slug":"detection-made-easy-potentials-of-large","title":"Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities","date":"2024-09-15","arxiv_id":"2409.10574","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinkmcts-refining-erroneous-thoughts-in","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation","date":"2024-09-15","arxiv_id":"2409.09584","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-evaluation-of-using-chatgpt-to","title":"An empirical evaluation of using ChatGPT to summarize disputes for recommending similar labor and employment cases in Chinese","date":"2024-09-14","arxiv_id":"2409.09280","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-ingredient-substitution-using","title":"Optimizing Ingredient Substitution Using Large Language Models to Enhance Phytochemical Content in Recipes","date":"2024-09-13","arxiv_id":"2409.08792","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimenting-with-legal-ai-solutions-the","title":"Experimenting with Legal AI Solutions: The Case of Question-Answering for Access to Justice","date":"2024-09-12","arxiv_id":"2409.07713","n_code_links":0,"syntology":null},{"paper":null,"slug":"stable-language-model-pre-training-by","title":"Stable Language Model Pre-training by Reducing Embedding Variability","date":"2024-09-12","arxiv_id":"2409.07787","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-mathematical-framework-for-objective","title":"A Novel Mathematical Framework for Objective Characterization of Ideas","date":"2024-09-11","arxiv_id":"2409.07578","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-fairer-health-recommendations-finding","title":"Towards Fairer Health Recommendations: finding informative unbiased samples via Word Sense Disambiguation","date":"2024-09-11","arxiv_id":"2409.07424","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-large-language-model-pretraining","title":"Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review","date":"2024-09-10","arxiv_id":"2409.06131","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-unlock-novel","slug":"can-large-language-models-unlock-novel","title":"Can Large Language Models Unlock Novel Scientific Research Ideas?","date":"2024-09-10","arxiv_id":"2409.06185","n_code_links":1,"syntology":{"ran":2,"of":11,"n_ran_checked":2,"n_instrument":0,"unverified":9,"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) · 9 unverified","official":{"repos":["sandeep82945/future-idea-generation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generative-ai-for-requirements-engineering-a","title":"Generative AI for Requirements Engineering: A Systematic Literature Review","date":"2024-09-10","arxiv_id":"2409.06741","n_code_links":0,"syntology":null},{"paper":"/paper/2409-13727","slug":"2409-13727","title":"Classification performance and reproducibility of GPT-4 omni for information extraction from veterinary electronic health records","date":"2024-09-09","arxiv_id":"2409.13727","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-sparql-capabilities-of-large","slug":"assessing-sparql-capabilities-of-large","title":"Assessing SPARQL capabilities of Large Language Models","date":"2024-09-09","arxiv_id":"2409.05925","n_code_links":2,"syntology":null},{"paper":null,"slug":"elsevier-arena-human-evaluation-of-chemistry","title":"Elsevier Arena: Human Evaluation of Chemistry/Biology/Health Foundational Large Language Models","date":"2024-09-09","arxiv_id":"2409.05486","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairhome-a-fair-housing-and-fair-lending","title":"FairHome: A Fair Housing and Fair Lending Dataset","date":"2024-09-09","arxiv_id":"2409.05990","n_code_links":0,"syntology":null},{"paper":null,"slug":"harmonic-reasoning-in-large-language-models","title":"Harmonic Reasoning in Large Language Models","date":"2024-09-09","arxiv_id":"2409.05521","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-the-sources-of-ideological-bias","title":"Identifying the sources of ideological bias in GPT models through linguistic variation in output","date":"2024-09-09","arxiv_id":"2409.06043","n_code_links":0,"syntology":null},{"paper":null,"slug":"regression-with-large-language-models-for","title":"Regression with Large Language Models for Materials and Molecular Property Prediction","date":"2024-09-09","arxiv_id":"2409.06080","n_code_links":0,"syntology":null},{"paper":"/paper/vision-fused-attack-advancing-aggressive-and","slug":"vision-fused-attack-advancing-aggressive-and","title":"Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation","date":"2024-09-08","arxiv_id":"2409.05021","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["levelower/vfa"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"column-vocabulary-association-cva-semantic","title":"Column Vocabulary Association (CVA): semantic interpretation of dataless tables","date":"2024-09-06","arxiv_id":"2409.13709","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-safer-online-spaces-simulating-and","title":"Towards Safer Online Spaces: Simulating and Assessing Intervention Strategies for Eating Disorder Discussions","date":"2024-09-06","arxiv_id":"2409.04043","n_code_links":0,"syntology":null},{"paper":null,"slug":"bypassing-darcy-defense-indistinguishable","title":"Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers","date":"2024-09-05","arxiv_id":"2409.03183","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-open-source-sparse-autoencoders-on","slug":"evaluating-open-source-sparse-autoencoders-on","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","date":"2024-09-05","arxiv_id":"2409.04478","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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","official":{"repos":["maheepchaudhary/sae-ravel"],"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"]}}},{"paper":null,"slug":"materialbench-evaluating-college-level","title":"MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models","date":"2024-09-05","arxiv_id":"2409.03161","n_code_links":0,"syntology":null},{"paper":null,"slug":"sketch-a-toolkit-for-streamlining-llm","title":"Sketch: A Toolkit for Streamlining LLM Operations","date":"2024-09-05","arxiv_id":"2409.03346","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-on-large-language-models","title":"A Comparative Study on Large Language Models for Log Parsing","date":"2024-09-04","arxiv_id":"2409.02474","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-privacy-savvy-are-large-language-models-a","title":"How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review","date":"2024-09-04","arxiv_id":"2409.02375","n_code_links":0,"syntology":null},{"paper":null,"slug":"irrelevant-alternatives-bias-large-language","title":"Irrelevant Alternatives Bias Large Language Model Hiring Decisions","date":"2024-09-04","arxiv_id":"2409.15299","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-efficient-reward","title":"Large Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Learning","date":"2024-09-04","arxiv_id":"2409.02428","n_code_links":0,"syntology":null},{"paper":"/paper/more-is-more-addition-bias-in-large-language","slug":"more-is-more-addition-bias-in-large-language","title":"More is More: Addition Bias in Large Language Models","date":"2024-09-04","arxiv_id":"2409.02569","n_code_links":1,"syntology":null},{"paper":null,"slug":"dialogue-you-can-trust-human-and-ai","title":"Dialogue You Can Trust: Human and AI Perspectives on Generated Conversations","date":"2024-09-03","arxiv_id":"2409.01808","n_code_links":0,"syntology":null},{"paper":"/paper/it-is-time-to-develop-an-auditing-framework","slug":"it-is-time-to-develop-an-auditing-framework","title":"It is Time to Develop an Auditing Framework to Promote Value Aware Chatbots","date":"2024-09-03","arxiv_id":"2409.01539","n_code_links":1,"syntology":null},{"paper":"/paper/lifegpt-topology-agnostic-generative","slug":"lifegpt-topology-agnostic-generative","title":"LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata","date":"2024-09-03","arxiv_id":"2409.12182","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-era-of-foundation-models-in-medical","title":"The Era of Foundation Models in Medical Imaging is Approaching : A Scoping Review of the Clinical Value of Large-Scale Generative AI Applications in Radiology","date":"2024-09-03","arxiv_id":"2409.12973","n_code_links":0,"syntology":null},{"paper":"/paper/self-judge-selective-instruction-following","slug":"self-judge-selective-instruction-following","title":"Self-Judge: Selective Instruction Following with Alignment Self-Evaluation","date":"2024-09-02","arxiv_id":"2409.00935","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nusnlp/Self-J"],"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":"deep-knowledge-infusion-for-explainable","title":"Deep Knowledge-Infusion For Explainable Depression Detection","date":"2024-09-01","arxiv_id":"2409.02122","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-information-extraction","title":"An Empirical Study on Information Extraction using Large Language Models","date":"2024-08-31","arxiv_id":"2409.00369","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-generative-language-models-in","slug":"assessing-generative-language-models-in","title":"Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain","date":"2024-08-30","arxiv_id":"2408.17362","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-large-language-models-address-open-target","title":"Can Large Language Models Address Open-Target Stance Detection?","date":"2024-08-30","arxiv_id":"2409.00222","n_code_links":0,"syntology":null},{"paper":"/paper/progres-prompted-generative-rescoring-on-asr","slug":"progres-prompted-generative-rescoring-on-asr","title":"ProGRes: Prompted Generative Rescoring on ASR n-Best","date":"2024-08-30","arxiv_id":"2409.00217","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-natural-language","title":"Retrieval-Augmented Natural Language Reasoning for Explainable Visual Question Answering","date":"2024-08-30","arxiv_id":"2408.17006","n_code_links":0,"syntology":null},{"paper":"/paper/training-ultra-long-context-language-model","slug":"training-ultra-long-context-language-model","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","date":"2024-08-30","arxiv_id":"2408.16978","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-large-language-models-for-online","title":"Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge","date":"2024-08-29","arxiv_id":"2408.16749","n_code_links":0,"syntology":null},{"paper":"/paper/llava-chef-a-multi-modal-generative-model-for","slug":"llava-chef-a-multi-modal-generative-model-for","title":"LLaVA-Chef: A Multi-modal Generative Model for Food Recipes","date":"2024-08-29","arxiv_id":"2408.16889","n_code_links":1,"syntology":null},{"paper":null,"slug":"fractured-sorry-bench-framework-for-revealing","title":"FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)","date":"2024-08-28","arxiv_id":"2408.16163","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-wireless","title":"Leveraging Large Language Models for Wireless Symbol Detection via In-Context Learning","date":"2024-08-28","arxiv_id":"2409.00124","n_code_links":0,"syntology":null},{"paper":"/paper/unleashing-the-temporal-spatial-reasoning","slug":"unleashing-the-temporal-spatial-reasoning","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation","date":"2024-08-28","arxiv_id":"2408.15876","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-large-language-models-for-3","title":"A Survey of Large Language Models for European Languages","date":"2024-08-27","arxiv_id":"2408.15040","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-optimization-and-challenges-of","title":"Strategic Optimization and Challenges of Large Language Models in Object-Oriented Programming","date":"2024-08-27","arxiv_id":"2408.14834","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-visual-reasoning-by-vision-language","title":"Zero-Shot Visual Reasoning by Vision-Language Models: Benchmarking and Analysis","date":"2024-08-27","arxiv_id":"2409.00106","n_code_links":0,"syntology":null},{"paper":"/paper/chartom-a-visual-theory-of-mind-benchmark-for","slug":"chartom-a-visual-theory-of-mind-benchmark-for","title":"CHARTOM: A Visual Theory-of-Mind Benchmark for Multimodal Large Language Models","date":"2024-08-26","arxiv_id":"2408.14419","n_code_links":1,"syntology":null},{"paper":null,"slug":"bidirectional-awareness-induction-in","title":"Bidirectional Awareness Induction in Autoregressive Seq2Seq Models","date":"2024-08-25","arxiv_id":"2408.13959","n_code_links":0,"syntology":null},{"paper":"/paper/codegraph-enhancing-graph-reasoning-of-llms","slug":"codegraph-enhancing-graph-reasoning-of-llms","title":"CodeGraph: Enhancing Graph Reasoning of LLMs with Code","date":"2024-08-25","arxiv_id":"2408.13863","n_code_links":1,"syntology":null},{"paper":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-exposure-from-llm-apps-an-in-depth","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","date":"2024-08-23","arxiv_id":"2408.13247","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-based-automated-program-repair","title":"Enhancing Automated Program Repair with Solution Design","date":"2024-08-22","arxiv_id":"2408.12056","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-hop-reasoning-through","title":"Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing","date":"2024-08-22","arxiv_id":"2408.12456","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-performance-how-compact-models","title":"Optimizing Performance: How Compact Models Match or Exceed GPT's Classification Capabilities through Fine-Tuning","date":"2024-08-22","arxiv_id":"2409.11408","n_code_links":0,"syntology":null},{"paper":null,"slug":"applying-and-evaluating-large-language-models","title":"Applying and Evaluating Large Language Models in Mental Health Care: A Scoping Review of Human-Assessed Generative Tasks","date":"2024-08-21","arxiv_id":"2408.11288","n_code_links":0,"syntology":null},{"paper":null,"slug":"d-rmgpt-robot-assisted-collaborative-tasks","title":"D-RMGPT: Robot-assisted collaborative tasks driven by large multimodal models","date":"2024-08-21","arxiv_id":"2408.11761","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixed-sparsity-training-achieving-4-times","title":"Mixed Sparsity Training: Achieving 4$\\times$ FLOP Reduction for Transformer Pretraining","date":"2024-08-21","arxiv_id":"2408.11746","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-adversarial-suffix-optimization","slug":"unlocking-adversarial-suffix-optimization","title":"Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer","date":"2024-08-21","arxiv_id":"2408.11313","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lenijwp/eclipse"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ctp-llm-clinical-trial-phase-transition","title":"CTP-LLM: Clinical Trial Phase Transition Prediction Using Large Language Models","date":"2024-08-20","arxiv_id":"2408.10995","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-well-do-large-language-models-serve-as","title":"How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python?","date":"2024-08-20","arxiv_id":"2408.10495","n_code_links":0,"syntology":null},{"paper":"/paper/language-modeling-on-tabular-data-a-survey-of","slug":"language-modeling-on-tabular-data-a-survey-of","title":"Language Modeling on Tabular Data: A Survey of Foundations, Techniques and Evolution","date":"2024-08-20","arxiv_id":"2408.10548","n_code_links":1,"syntology":null},{"paper":"/paper/soda-eval-open-domain-dialogue-evaluation-in","slug":"soda-eval-open-domain-dialogue-evaluation-in","title":"Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMs","date":"2024-08-20","arxiv_id":"2408.10902","n_code_links":1,"syntology":null},{"paper":null,"slug":"towardseffective-teaching-assistants-from","title":"Towardseffective teaching assistants: From intent-based chatbots to LLM-poweredteachingassistants","date":"2024-08-20","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tracing-privacy-leakage-of-language-models-to","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","date":"2024-08-20","arxiv_id":"2408.10468","n_code_links":0,"syntology":null},{"paper":"/paper/while-github-copilot-excels-at-coding-does-it","slug":"while-github-copilot-excels-at-coding-does-it","title":"Security Attacks on LLM-based Code Completion Tools","date":"2024-08-20","arxiv_id":"2408.11006","n_code_links":1,"syntology":null},{"paper":"/paper/enhance-lifelong-model-editing-with","slug":"enhance-lifelong-model-editing-with","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","date":"2024-08-19","arxiv_id":"2408.11869","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-augmented-reinforcement-learning-with","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","date":"2024-08-19","arxiv_id":"2408.10286","n_code_links":0,"syntology":null},{"paper":null,"slug":"rhyme-aware-chinese-lyric-generator-based-on","title":"Rhyme-aware Chinese lyric generator based on GPT","date":"2024-08-19","arxiv_id":"2408.10130","n_code_links":0,"syntology":null},{"paper":null,"slug":"tba-faster-large-language-model-training","title":"SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training","date":"2024-08-19","arxiv_id":"2408.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"conversum-a-contrastive-learning-based","title":"ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents","date":"2024-08-17","arxiv_id":"2408.09273","n_code_links":0,"syntology":null},{"paper":null,"slug":"tablebench-a-comprehensive-and-complex","title":"TableBench: A Comprehensive and Complex Benchmark for Table Question Answering","date":"2024-08-17","arxiv_id":"2408.09174","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-mean-field-ansatz-for-zero-shot-weight","title":"A Mean Field Ansatz for Zero-Shot Weight Transfer","date":"2024-08-16","arxiv_id":"2408.08681","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-llms-for-autonomous-spacecraft","slug":"fine-tuning-llms-for-autonomous-spacecraft","title":"Fine-tuning LLMs for Autonomous Spacecraft Control: A Case Study Using Kerbal Space Program","date":"2024-08-16","arxiv_id":"2408.08676","n_code_links":1,"syntology":null},{"paper":"/paper/the-fellowship-of-the-llms-multi-agent","slug":"the-fellowship-of-the-llms-multi-agent","title":"The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation","date":"2024-08-16","arxiv_id":"2408.08688","n_code_links":1,"syntology":null},{"paper":"/paper/fusechat-knowledge-fusion-of-chat-models-1","slug":"fusechat-knowledge-fusion-of-chat-models-1","title":"FuseChat: Knowledge Fusion of Chat Models","date":"2024-08-15","arxiv_id":"2408.07990","n_code_links":3,"syntology":null},{"paper":"/paper/leveraging-web-crawled-data-for-high-quality","slug":"leveraging-web-crawled-data-for-high-quality","title":"Leveraging Web-Crawled Data for High-Quality Fine-Tuning","date":"2024-08-15","arxiv_id":"2408.08003","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-lung-cancer-patient-prognosis-with","title":"Predicting Lung Cancer Patient Prognosis with Large Language Models","date":"2024-08-15","arxiv_id":"2408.07971","n_code_links":0,"syntology":null},{"paper":null,"slug":"codemirage-hallucinations-in-code-generated","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","date":"2024-08-14","arxiv_id":"2408.08333","n_code_links":0,"syntology":null},{"paper":null,"slug":"sage-rt-synthetic-alignment-data-generation","title":"SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming","date":"2024-08-14","arxiv_id":"2408.11851","n_code_links":0,"syntology":null}],"record_sha256":"8a4c8987e6584542dbef726c05e9632476205af3f8befbe41229a25ef5394efb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}