{"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/4","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":4,"pages_in_order":38,"rows_per_page":100,"rows":[301,400],"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/3","next":"/method/linear-warmup-with-cosine-annealing/papers/5","papers":[{"paper":null,"slug":"libra-measuring-bias-of-large-language-model","title":"LIBRA: Measuring Bias of Large Language Model from a Local Context","date":"2025-02-02","arxiv_id":"2502.01679","n_code_links":0,"syntology":null},{"paper":null,"slug":"coddllm-empowering-large-language-models-for","title":"CoddLLM: Empowering Large Language Models for Data Analytics","date":"2025-02-01","arxiv_id":"2502.00329","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-solvers-for-discrete-diffusion-models","title":"Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms","date":"2025-02-01","arxiv_id":"2502.00234","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-solve-the-peer-review-crisis-a-large","title":"Can AI Solve the Peer Review Crisis? A Large Scale Cross Model Experiment of LLMs' Performance and Biases in Evaluating over 1000 Economics Papers","date":"2025-01-31","arxiv_id":"2502.00070","n_code_links":0,"syntology":null},{"paper":"/paper/kbqa-o1-agentic-knowledge-base-question","slug":"kbqa-o1-agentic-knowledge-base-question","title":"KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search","date":"2025-01-31","arxiv_id":"2501.18922","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["lhrlab/kbqa-o1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-accuracy-in-emulating","title":"Large Language Models' Accuracy in Emulating Human Experts' Evaluation of Public Sentiments about Heated Tobacco Products on Social Media","date":"2025-01-31","arxiv_id":"2502.01658","n_code_links":0,"syntology":null},{"paper":null,"slug":"alphaadam-asynchronous-masked-optimization","title":"AlphaAdam:Asynchronous Masked Optimization with Dynamic Alpha for Selective Updates","date":"2025-01-30","arxiv_id":"2501.18094","n_code_links":0,"syntology":null},{"paper":null,"slug":"economic-rationality-under-specialization","title":"Economic Rationality under Specialization: Evidence of Decision Bias in AI Agents","date":"2025-01-30","arxiv_id":"2501.18190","n_code_links":0,"syntology":null},{"paper":null,"slug":"general-embedding-vs-task-specific-embedding","title":"General Embedding vs. Task-Specific Embedding: A Comparative Approach to Enhancing NLP Performance","date":"2025-01-30","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"structure-development-in-list-sorting","title":"Structure Development in List-Sorting Transformers","date":"2025-01-30","arxiv_id":"2501.18666","n_code_links":0,"syntology":null},{"paper":"/paper/unraveling-the-capabilities-of-language","slug":"unraveling-the-capabilities-of-language","title":"Unraveling the Capabilities of Language Models in News Summarization","date":"2025-01-30","arxiv_id":"2501.18128","n_code_links":1,"syntology":null},{"paper":"/paper/wildchat-50m-a-deep-dive-into-the-role-of","slug":"wildchat-50m-a-deep-dive-into-the-role-of","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","date":"2025-01-30","arxiv_id":"2501.18511","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["penfever/wildchat-50m"],"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":"hybrid-graphs-for-table-and-text-based","title":"Hybrid Graphs for Table-and-Text based Question Answering using LLMs","date":"2025-01-29","arxiv_id":"2501.17767","n_code_links":0,"syntology":null},{"paper":"/paper/graph-of-attacks-with-pruning-optimizing","slug":"graph-of-attacks-with-pruning-optimizing","title":"Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation","date":"2025-01-28","arxiv_id":"2501.18638","n_code_links":1,"syntology":null},{"paper":null,"slug":"open-source-retrieval-augmented-generation","title":"Open-Source Retrieval Augmented Generation Framework for Retrieving Accurate Medication Insights from Formularies for African Healthcare Workers","date":"2025-01-28","arxiv_id":"2502.15722","n_code_links":0,"syntology":null},{"paper":null,"slug":"kernels-of-selfhood-gpt-4o-shows-humanlike","title":"Kernels of Selfhood: GPT-4o shows humanlike patterns of cognitive consistency moderated by free choice","date":"2025-01-27","arxiv_id":"2502.07088","n_code_links":0,"syntology":null},{"paper":null,"slug":"weight-based-analysis-of-detokenization-in","title":"Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference","date":"2025-01-27","arxiv_id":"2501.15754","n_code_links":0,"syntology":null},{"paper":"/paper/an-ai-driven-live-systematic-reviews-in-the","slug":"an-ai-driven-live-systematic-reviews-in-the","title":"An AI-Driven Live Systematic Reviews in the Brain-Heart Interconnectome: Minimizing Research Waste and Advancing Evidence Synthesis","date":"2025-01-25","arxiv_id":"2501.17181","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-attempt-to-unraveling-token-prediction","title":"An Attempt to Unraveling Token Prediction Refinement and Identifying Essential Layers of Large Language Models","date":"2025-01-25","arxiv_id":"2501.15054","n_code_links":0,"syntology":null},{"paper":"/paper/speech-translation-refinement-using-large","slug":"speech-translation-refinement-using-large","title":"Speech Translation Refinement using Large Language Models","date":"2025-01-25","arxiv_id":"2501.15090","n_code_links":1,"syntology":null},{"paper":null,"slug":"darkmind-latent-chain-of-thought-backdoor-in","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","date":"2025-01-24","arxiv_id":"2501.18617","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-based-cost-effective-evaluation-and","title":"Prompt-Based Cost-Effective Evaluation and Operation of ChatGPT as a Computer Programming Teaching Assistant","date":"2025-01-24","arxiv_id":"2501.17176","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-table-instruction-tuning","slug":"rethinking-table-instruction-tuning","title":"Rethinking Table Instruction Tuning","date":"2025-01-24","arxiv_id":"2501.14693","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-are-vulnerable-to-malicious-prompts","title":"LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language","date":"2025-01-23","arxiv_id":"2501.14073","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-the-understanding-and-evaluation-of","slug":"advancing-the-understanding-and-evaluation-of","title":"Advancing the Understanding and Evaluation of AR-Generated Scenes: When Vision-Language Models Shine and Stumble","date":"2025-01-21","arxiv_id":"2501.13964","n_code_links":1,"syntology":null},{"paper":null,"slug":"divide-then-aggregate-an-efficient-tool","title":"Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation","date":"2025-01-21","arxiv_id":"2501.12432","n_code_links":0,"syntology":null},{"paper":null,"slug":"focus-first-order-concentrated-updating","title":"FOCUS: First Order Concentrated Updating Scheme","date":"2025-01-21","arxiv_id":"2501.12243","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-generative-pre-trained-transformer","title":"Harnessing Generative Pre-Trained Transformer for Datacenter Packet Trace Generation","date":"2025-01-21","arxiv_id":"2501.12033","n_code_links":0,"syntology":null},{"paper":null,"slug":"vision-language-models-for-automated-chest-x","title":"Vision-Language Models for Automated Chest X-ray Interpretation: Leveraging ViT and GPT-2","date":"2025-01-21","arxiv_id":"2501.12356","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-data-can-mislead-evaluations","title":"Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection","date":"2025-01-20","arxiv_id":"2501.11786","n_code_links":0,"syntology":null},{"paper":null,"slug":"trustformer-a-trusted-federated-transformer","title":"Trustformer: A Trusted Federated Transformer","date":"2025-01-20","arxiv_id":"2501.11706","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-arabic-text-to-puzzles-llm-driven","title":"From Arabic Text to Puzzles: LLM-Driven Development of Arabic Educational Crosswords","date":"2025-01-19","arxiv_id":"2501.11035","n_code_links":0,"syntology":null},{"paper":null,"slug":"fsmoe-a-flexible-and-scalable-training-system","title":"FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models","date":"2025-01-18","arxiv_id":"2501.10714","n_code_links":0,"syntology":null},{"paper":"/paper/bias-in-decision-making-for-ai-s-ethical","slug":"bias-in-decision-making-for-ai-s-ethical","title":"Bias in Decision-Making for AI's Ethical Dilemmas: A Comparative Study of ChatGPT and Claude","date":"2025-01-17","arxiv_id":"2501.10484","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-for-error-detection-in","slug":"confidence-estimation-for-error-detection-in","title":"Confidence Estimation for Error Detection in Text-to-SQL Systems","date":"2025-01-16","arxiv_id":"2501.09527","n_code_links":1,"syntology":null},{"paper":null,"slug":"perspective-transition-of-large-language","title":"Perspective Transition of Large Language Models for Solving Subjective Tasks","date":"2025-01-16","arxiv_id":"2501.09265","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-takes-a-statistics-exam-a","title":"Generative AI Takes a Statistics Exam: A Comparison of Performance between ChatGPT3.5, ChatGPT4, and ChatGPT4o-mini","date":"2025-01-15","arxiv_id":"2501.09171","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-big-five-personality-traits-on","title":"The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study","date":"2025-01-15","arxiv_id":"2503.15497","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-energy-efficiency-and","title":"Investigating Energy Efficiency and Performance Trade-offs in LLM Inference Across Tasks and DVFS Settings","date":"2025-01-14","arxiv_id":"2501.08219","n_code_links":0,"syntology":null},{"paper":"/paper/finerweb-10bt-refining-web-data-with-llm","slug":"finerweb-10bt-refining-web-data-with-llm","title":"FinerWeb-10BT: Refining Web Data with LLM-Based Line-Level Filtering","date":"2025-01-13","arxiv_id":"2501.07314","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-as-a-monte-carlo-language-tree-a","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","date":"2025-01-13","arxiv_id":"2501.07641","n_code_links":0,"syntology":null},{"paper":"/paper/how-gpt-learns-layer-by-layer","slug":"how-gpt-learns-layer-by-layer","title":"How GPT learns layer by layer","date":"2025-01-13","arxiv_id":"2501.07108","n_code_links":1,"syntology":null},{"paper":"/paper/zno-eval-benchmarking-reasoning-capabilities","slug":"zno-eval-benchmarking-reasoning-capabilities","title":"ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian","date":"2025-01-12","arxiv_id":"2501.06715","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-instructor-ai-cooperation-for","slug":"assessing-instructor-ai-cooperation-for","title":"Assessing instructor-AI cooperation for grading essay-type questions in an introductory sociology course","date":"2025-01-11","arxiv_id":"2501.06461","n_code_links":1,"syntology":null},{"paper":null,"slug":"openai-chatgpt-interprets-radiological-images","title":"OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up","date":"2025-01-09","arxiv_id":"2501.06269","n_code_links":0,"syntology":null},{"paper":"/paper/uav-vla-vision-language-action-system-for","slug":"uav-vla-vision-language-action-system-for","title":"UAV-VLA: Vision-Language-Action System for Large Scale Aerial Mission Generation","date":"2025-01-09","arxiv_id":"2501.05014","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-llms-with-its-recent-advances","title":"Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions","date":"2025-01-08","arxiv_id":"2501.04437","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaling-large-language-model-training-on","title":"Scaling Large Language Model Training on Frontier with Low-Bandwidth Partitioning","date":"2025-01-08","arxiv_id":"2501.04266","n_code_links":0,"syntology":null},{"paper":"/paper/finding-a-voice-evaluating-african-american","slug":"finding-a-voice-evaluating-african-american","title":"Finding A Voice: Evaluating African American Dialect Generation for Chatbot Technology","date":"2025-01-07","arxiv_id":"2501.03441","n_code_links":1,"syntology":null},{"paper":"/paper/decoding-fmri-data-into-captions-using-prefix","slug":"decoding-fmri-data-into-captions-using-prefix","title":"Decoding fMRI Data into Captions using Prefix Language Modeling","date":"2025-01-05","arxiv_id":"2501.02570","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-models-with-some","title":"A Survey on Large Language Models with some Insights on their Capabilities and Limitations","date":"2025-01-03","arxiv_id":"2501.04040","n_code_links":0,"syntology":null},{"paper":null,"slug":"agentrefine-enhancing-agent-generalization","title":"AgentRefine: Enhancing Agent Generalization through Refinement Tuning","date":"2025-01-03","arxiv_id":"2501.01702","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-mental-health-1","title":"Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case","date":"2025-01-02","arxiv_id":"2501.01305","n_code_links":0,"syntology":null},{"paper":"/paper/predicting-the-performance-of-black-box-llms","slug":"predicting-the-performance-of-black-box-llms","title":"Predicting the Performance of Black-box LLMs through Self-Queries","date":"2025-01-02","arxiv_id":"2501.01558","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dsam99/quere"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/column-property-annotation-using-large","slug":"column-property-annotation-using-large","title":"Column Property Annotation using Large Language Models","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/crrg-clip-automatic-generation-of-chest","slug":"crrg-clip-automatic-generation-of-chest","title":"CRRG-CLIP: Automatic Generation of Chest Radiology Reports and Classification of Chest Radiographs","date":"2024-12-31","arxiv_id":"2501.01989","n_code_links":1,"syntology":null},{"paper":null,"slug":"why-are-positional-encodings-nonessential-for","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","date":"2024-12-31","arxiv_id":"2501.00659","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-performance-of-advanced-nlp","title":"Comparative Performance of Advanced NLP Models and LLMs in Multilingual Geo-Entity Detection","date":"2024-12-29","arxiv_id":"2412.20414","n_code_links":0,"syntology":null},{"paper":"/paper/electra-and-gpt-4o-cost-effective-partners","slug":"electra-and-gpt-4o-cost-effective-partners","title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","date":"2024-12-29","arxiv_id":"2501.00062","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-adversarial-robustness-of-language-models","title":"On Adversarial Robustness of Language Models in Transfer Learning","date":"2024-12-29","arxiv_id":"2501.00066","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-text-classification-methods-for","title":"Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms","date":"2024-12-27","arxiv_id":"2412.19928","n_code_links":0,"syntology":null},{"paper":"/paper/drivingworld-constructingworld-model-for","slug":"drivingworld-constructingworld-model-for","title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","date":"2024-12-27","arxiv_id":"2412.19505","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":8,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yvanyin/drivingworld"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"feature-alignment-based-knowledge","title":"Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models","date":"2024-12-27","arxiv_id":"2412.19449","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-embedding-and","slug":"generative-pretrained-embedding-and","title":"Generative Pretrained Embedding and Hierarchical Irregular Time Series Representation for Daily Living Activity Recognition","date":"2024-12-27","arxiv_id":"2412.19732","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentiment-trading-with-large-language-models","title":"Sentiment trading with large language models","date":"2024-12-26","arxiv_id":"2412.19245","n_code_links":0,"syntology":null},{"paper":null,"slug":"saflite-fuzzing-autonomous-systems-via-large","title":"SAFLITE: Fuzzing Autonomous Systems via Large Language Models","date":"2024-12-25","arxiv_id":"2412.18727","n_code_links":0,"syntology":null},{"paper":null,"slug":"whose-morality-do-they-speak-unraveling","title":"Whose Morality Do They Speak? Unraveling Cultural Bias in Multilingual Language Models","date":"2024-12-25","arxiv_id":"2412.18863","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-understand-the-cognitive","title":"Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigm","date":"2024-12-24","arxiv_id":"2412.18120","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-auditory-perception-and-language","title":"Bridging Auditory Perception and Language Comprehension through MEG-Driven Encoding Models","date":"2024-12-22","arxiv_id":"2501.03246","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-fusing-chatgpt-and-ensemble-learning-in","title":"On Fusing ChatGPT and Ensemble Learning in Discon-tinuous Named Entity Recognition in Health Corpora","date":"2024-12-22","arxiv_id":"2412.16976","n_code_links":0,"syntology":null},{"paper":"/paper/psychadapter-adapting-llm-transformers-to","slug":"psychadapter-adapting-llm-transformers-to","title":"PsychAdapter: Adapting LLM Transformers to Reflect Traits, Personality and Mental Health","date":"2024-12-22","arxiv_id":"2412.16882","n_code_links":1,"syntology":null},{"paper":null,"slug":"robustness-of-large-language-models-against","title":"Robustness of Large Language Models Against Adversarial Attacks","date":"2024-12-22","arxiv_id":"2412.17011","n_code_links":0,"syntology":null},{"paper":null,"slug":"tar3d-creating-high-quality-3d-assets-via","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","date":"2024-12-22","arxiv_id":"2412.16919","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-social-alignment-do-personality","title":"Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?","date":"2024-12-21","arxiv_id":"2412.16772","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-performance-of-large-language-4","title":"Evaluating the Performance of Large Language Models in Scientific Claim Detection and Classification","date":"2024-12-21","arxiv_id":"2412.16486","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-fim-code-completions-via-context","title":"Improving FIM Code Completions via Context & Curriculum Based Learning","date":"2024-12-21","arxiv_id":"2412.16589","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-through-dynamic","title":"Adversarial Robustness through Dynamic Ensemble Learning","date":"2024-12-20","arxiv_id":"2412.16254","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-obfuscate-code-a-systematic-analysis","title":"Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation","date":"2024-12-20","arxiv_id":"2412.16135","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-readable-adversarial-prompts-an","title":"Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context","date":"2024-12-20","arxiv_id":"2412.16359","n_code_links":0,"syntology":null},{"paper":"/paper/linguistic-features-extracted-by-gpt-4","slug":"linguistic-features-extracted-by-gpt-4","title":"Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech","date":"2024-12-20","arxiv_id":"2412.15772","n_code_links":1,"syntology":null},{"paper":null,"slug":"graph-convolutional-networks-named-entity","title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering","date":"2024-12-19","arxiv_id":"2412.14867","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-good-is-gpt-at-writing-political-speeches","title":"How good is GPT at writing political speeches for the White House?","date":"2024-12-19","arxiv_id":"2412.14617","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-as-mediators-can-they-diagnose-conflicts","title":"LLMs as mediators: Can they diagnose conflicts accurately?","date":"2024-12-19","arxiv_id":"2412.14675","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-programming-with-foundation-models","title":"Relational Programming with Foundation Models","date":"2024-12-19","arxiv_id":"2412.14515","n_code_links":0,"syntology":null},{"paper":"/paper/resofilter-rine-grained-synthetic-data","slug":"resofilter-rine-grained-synthetic-data","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","date":"2024-12-19","arxiv_id":"2412.14809","n_code_links":1,"syntology":null},{"paper":"/paper/tomg-bench-evaluating-llms-on-text-based-open","slug":"tomg-bench-evaluating-llms-on-text-based-open","title":"TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation","date":"2024-12-19","arxiv_id":"2412.14642","n_code_links":1,"syntology":null},{"paper":"/paper/autonomous-microscopy-experiments-through","slug":"autonomous-microscopy-experiments-through","title":"Autonomous Microscopy Experiments through Large Language Model Agents","date":"2024-12-18","arxiv_id":"2501.10385","n_code_links":1,"syntology":null},{"paper":"/paper/mix-ln-unleashing-the-power-of-deeper-layers","slug":"mix-ln-unleashing-the-power-of-deeper-layers","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","date":"2024-12-18","arxiv_id":"2412.13795","n_code_links":1,"syntology":null},{"paper":null,"slug":"detecting-document-level-paraphrased-machine","title":"Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features","date":"2024-12-17","arxiv_id":"2412.12679","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-are-also-effective-embedding-models-an","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","date":"2024-12-17","arxiv_id":"2412.12591","n_code_links":0,"syntology":null},{"paper":"/paper/causal-diffusion-transformers-for-generative","slug":"causal-diffusion-transformers-for-generative","title":"Causal Diffusion Transformers for Generative Modeling","date":"2024-12-16","arxiv_id":"2412.12095","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["causalfusion/causalfusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/glimpse-enabling-white-box-methods-to-use","slug":"glimpse-enabling-white-box-methods-to-use","title":"Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection","date":"2024-12-16","arxiv_id":"2412.11506","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":["baoguangsheng/glimpse"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/look-ahead-text-understanding-and-llm","slug":"look-ahead-text-understanding-and-llm","title":"Look Ahead Text Understanding and LLM Stitching","date":"2024-12-16","arxiv_id":"2412.17836","n_code_links":1,"syntology":null},{"paper":"/paper/no-more-adam-learning-rate-scaling-at","slug":"no-more-adam-learning-rate-scaling-at","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","date":"2024-12-16","arxiv_id":"2412.11768","n_code_links":1,"syntology":null},{"paper":null,"slug":"priority-aware-model-distributed-inference-at","title":"Priority-Aware Model-Distributed Inference at Edge Networks","date":"2024-12-16","arxiv_id":"2412.12371","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-vision-models-understand-3d","slug":"do-large-language-vision-models-understand-3d","title":"Do large language vision models understand 3D shapes?","date":"2024-12-14","arxiv_id":"2412.10908","n_code_links":1,"syntology":null},{"paper":"/paper/does-multiple-choice-have-a-future-in-the-age","slug":"does-multiple-choice-have-a-future-in-the-age","title":"Does Multiple Choice Have a Future in the Age of Generative AI? A Posttest-only RCT","date":"2024-12-13","arxiv_id":"2412.10267","n_code_links":1,"syntology":null},{"paper":null,"slug":"reasoner-outperforms-generative-stance","title":"Reasoner Outperforms: Generative Stance Detection with Rationalization for Social Media","date":"2024-12-13","arxiv_id":"2412.10266","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-vulnerabilities-in-large-language","slug":"adversarial-vulnerabilities-in-large-language","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","date":"2024-12-11","arxiv_id":"2412.08099","n_code_links":1,"syntology":null}],"record_sha256":"128dcd358910604d6a40b8438e77a2e77a8c5ff55364c2ca43a1cf3ee6e272ff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}