{"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/9","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":9,"pages_in_order":38,"rows_per_page":100,"rows":[801,900],"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/8","next":"/method/linear-warmup-with-cosine-annealing/papers/10","papers":[{"paper":null,"slug":"transformers-and-large-language-models-for-1","title":"Transformers and Large Language Models for Efficient Intrusion Detection Systems: A Comprehensive Survey","date":"2024-08-14","arxiv_id":"2408.07583","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-cultural-adaptability-of-a-large","slug":"evaluating-cultural-adaptability-of-a-large","title":"Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas","date":"2024-08-13","arxiv_id":"2408.06929","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-ai-for-automatic-topic-labelling","title":"Generative AI for automatic topic labelling","date":"2024-08-13","arxiv_id":"2408.07003","n_code_links":0,"syntology":null},{"paper":null,"slug":"pragmatic-inference-of-scalar-implicature-by","title":"Pragmatic inference of scalar implicature by LLMs","date":"2024-08-13","arxiv_id":"2408.06673","n_code_links":0,"syntology":null},{"paper":"/paper/kov-transferable-and-naturalistic-black-box","slug":"kov-transferable-and-naturalistic-black-box","title":"Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search","date":"2024-08-11","arxiv_id":"2408.08899","n_code_links":1,"syntology":null},{"paper":"/paper/utilizing-large-language-models-to-optimize","slug":"utilizing-large-language-models-to-optimize","title":"PhishLang: A Real-Time, Fully Client-Side Phishing Detection Framework Using MobileBERT","date":"2024-08-11","arxiv_id":"2408.05667","n_code_links":2,"syntology":null},{"paper":null,"slug":"chain-of-condition-construct-verify-and-solve","title":"Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering","date":"2024-08-10","arxiv_id":"2408.05442","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-whisper-s-recognition-performance","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","date":"2024-08-10","arxiv_id":"2408.05554","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-the-code-debugging-ability-of-llms","slug":"enhancing-the-code-debugging-ability-of-llms","title":"COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis","date":"2024-08-09","arxiv_id":"2408.05006","n_code_links":1,"syntology":null},{"paper":null,"slug":"examining-the-behavior-of-llm-architectures","title":"Examining the Behavior of LLM Architectures Within the Framework of Standardized National Exams in Brazil","date":"2024-08-09","arxiv_id":"2408.05035","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-text-to-insight-leveraging-large","title":"From Text to Insight: Leveraging Large Language Models for Performance Evaluation in Management","date":"2024-08-09","arxiv_id":"2408.05328","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-code-completion-for-local","title":"Retrieval-augmented code completion for local projects using large language models","date":"2024-08-09","arxiv_id":"2408.05026","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-explainer-interactive-learning-of","slug":"transformer-explainer-interactive-learning-of","title":"Transformer Explainer: Interactive Learning of Text-Generative Models","date":"2024-08-08","arxiv_id":"2408.04619","n_code_links":1,"syntology":null},{"paper":null,"slug":"could-chatgpt-get-an-engineering-degree","title":"Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants","date":"2024-08-07","arxiv_id":"2408.11841","n_code_links":0,"syntology":null},{"paper":"/paper/image-to-latex-converter-for-mathematical","slug":"image-to-latex-converter-for-mathematical","title":"Image-to-LaTeX Converter for Mathematical Formulas and Text","date":"2024-08-07","arxiv_id":"2408.04015","n_code_links":1,"syntology":null},{"paper":"/paper/is-child-directed-speech-effective-training","slug":"is-child-directed-speech-effective-training","title":"Is Child-Directed Speech Effective Training Data for Language Models?","date":"2024-08-07","arxiv_id":"2408.03617","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["styfeng/tinydialogues"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/leveraging-llms-for-enhanced-open-vocabulary","slug":"leveraging-llms-for-enhanced-open-vocabulary","title":"Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian","date":"2024-08-07","arxiv_id":"2408.03516","n_code_links":1,"syntology":null},{"paper":null,"slug":"socfedgpt-federated-gpt-based-adaptive","title":"SocFedGPT: Federated GPT-based Adaptive Content Filtering System Leveraging User Interactions in Social Networks","date":"2024-08-07","arxiv_id":"2408.05243","n_code_links":0,"syntology":null},{"paper":"/paper/2408-02946","slug":"2408-02946","title":"Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws","date":"2024-08-06","arxiv_id":"2408.02946","n_code_links":2,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":5,"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) · 4 unverified","official":{"repos":["alignmentresearch/scaling-poisoning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"2408-03119","title":"Evaluating the Translation Performance of Large Language Models Based on Euas-20","date":"2024-08-06","arxiv_id":"2408.03119","n_code_links":0,"syntology":null},{"paper":null,"slug":"flash-federated-learning-based-llms-for","title":"FLASH: Federated Learning-Based LLMs for Advanced Query Processing in Social Networks through RAG","date":"2024-08-06","arxiv_id":"2408.05242","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-use-of-large-language-models-llm-for","title":"The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums","date":"2024-08-06","arxiv_id":"2408.03354","n_code_links":0,"syntology":null},{"paper":"/paper/trafficgpt-an-llm-approach-for-open-set","slug":"trafficgpt-an-llm-approach-for-open-set","title":"TrafficGPT: An LLM Approach for Open-Set Encrypted Traffic Classification","date":"2024-08-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/2408-02416","slug":"2408-02416","title":"Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models","date":"2024-08-05","arxiv_id":"2408.02416","n_code_links":1,"syntology":null},{"paper":"/paper/xmainframe-a-large-language-model-for","slug":"xmainframe-a-large-language-model-for","title":"XMainframe: A Large Language Model for Mainframe Modernization","date":"2024-08-05","arxiv_id":"2408.04660","n_code_links":1,"syntology":null},{"paper":"/paper/2408-01966","slug":"2408-01966","title":"ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science","date":"2024-08-04","arxiv_id":"2408.01966","n_code_links":1,"syntology":null},{"paper":"/paper/2408-02001","slug":"2408-02001","title":"AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis","date":"2024-08-04","arxiv_id":"2408.02001","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-02103","title":"Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Process","date":"2024-08-04","arxiv_id":"2408.02103","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-with-chain","title":"Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference","date":"2024-08-04","arxiv_id":"2408.04652","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01614","title":"Advancing Mental Health Pre-Screening: A New Custom GPT for Psychological Distress Assessment","date":"2024-08-03","arxiv_id":"2408.01614","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01866","title":"Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly","date":"2024-08-03","arxiv_id":"2408.01866","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-trust-in-mental-health-chatbots","title":"Building Trust in Mental Health Chatbots: Safety Metrics and LLM-Based Evaluation Tools","date":"2024-08-03","arxiv_id":"2408.04650","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01055","title":"LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems","date":"2024-08-02","arxiv_id":"2408.01055","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01214","title":"High-Throughput Phenotyping of Clinical Text Using Large Language Models","date":"2024-08-02","arxiv_id":"2408.01214","n_code_links":0,"syntology":null},{"paper":"/paper/2408-00727","slug":"2408-00727","title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","date":"2024-08-01","arxiv_id":"2408.00727","n_code_links":1,"syntology":null},{"paper":"/paper/2408-00764","slug":"2408-00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","date":"2024-08-01","arxiv_id":"2408.00764","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["lazychih114/AgentGen-Reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"what-comes-after-transformers-a-selective","title":"What comes after transformers? -- A selective survey connecting ideas in deep learning","date":"2024-08-01","arxiv_id":"2408.00386","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21330","title":"Performance of Recent Large Language Models for a Low-Resourced Language","date":"2024-07-31","arxiv_id":"2407.21330","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21443","title":"Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency","date":"2024-07-31","arxiv_id":"2407.21443","n_code_links":0,"syntology":null},{"paper":"/paper/2407-21491","slug":"2407-21491","title":"Generative Expressive Conversational Speech Synthesis","date":"2024-07-31","arxiv_id":"2407.21491","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-00197","title":"Automated Software Vulnerability Static Code Analysis Using Generative Pre-Trained Transformer Models","date":"2024-07-31","arxiv_id":"2408.00197","n_code_links":0,"syntology":null},{"paper":"/paper/2407-21170","slug":"2407-21170","title":"Decomposed Prompting to Answer Questions on a Course Discussion Board","date":"2024-07-30","arxiv_id":"2407.21170","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-and-llms-based-avgfp-brightness","title":"BERT and LLMs-Based avGFP Brightness Prediction and Mutation Design","date":"2024-07-30","arxiv_id":"2407.20534","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-agents-compromising-autonomous-llm","title":"Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification","date":"2024-07-30","arxiv_id":"2407.20859","n_code_links":0,"syntology":null},{"paper":"/paper/comparison-of-large-language-models-for","slug":"comparison-of-large-language-models-for","title":"Comparison of Large Language Models for Generating Contextually Relevant Questions","date":"2024-07-30","arxiv_id":"2407.20578","n_code_links":1,"syntology":null},{"paper":null,"slug":"ageval-a-benchmark-for-zero-shot-and-few-shot","title":"AgEval: A Benchmark for Zero-Shot and Few-Shot Plant Stress Phenotyping with Multimodal LLMs","date":"2024-07-29","arxiv_id":"2407.19617","n_code_links":0,"syntology":null},{"paper":"/paper/autoscale-automatic-prediction-of-compute","slug":"autoscale-automatic-prediction-of-compute","title":"AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs","date":"2024-07-29","arxiv_id":"2407.20177","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":["feiyang-k/autoscale"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/detecting-and-understanding-vulnerabilities","slug":"detecting-and-understanding-vulnerabilities","title":"Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability","date":"2024-07-29","arxiv_id":"2407.19842","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-code-translation-in-language-models","title":"Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation","date":"2024-07-29","arxiv_id":"2407.19619","n_code_links":0,"syntology":null},{"paper":null,"slug":"adacoder-adaptive-prompt-compression-for","title":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","date":"2024-07-28","arxiv_id":"2407.19410","n_code_links":0,"syntology":null},{"paper":"/paper/are-llms-good-annotators-for-discourse-level","slug":"are-llms-good-annotators-for-discourse-level","title":"Are LLMs Good Annotators for Discourse-level Event Relation Extraction?","date":"2024-07-28","arxiv_id":"2407.19568","n_code_links":1,"syntology":null},{"paper":null,"slug":"is-generative-ai-an-existential-threat-to","title":"Is Generative AI an Existential Threat to Human Creatives? Insights from Financial Economics","date":"2024-07-28","arxiv_id":"2407.19586","n_code_links":0,"syntology":null},{"paper":"/paper/motamot-a-dataset-for-revealing-the-supremacy","slug":"motamot-a-dataset-for-revealing-the-supremacy","title":"Motamot: A Dataset for Revealing the Supremacy of Large Language Models over Transformer Models in Bengali Political Sentiment Analysis","date":"2024-07-28","arxiv_id":"2407.19528","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-reliable-common-sense-reasoning-socialbot","title":"A Reliable Common-Sense Reasoning Socialbot Built Using LLMs and Goal-Directed ASP","date":"2024-07-26","arxiv_id":"2407.18498","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-artificial-intelligence-teaming-for","title":"Human-artificial intelligence teaming for scientific information extraction from data-driven additive manufacturing research using large language models","date":"2024-07-26","arxiv_id":"2407.18827","n_code_links":0,"syntology":null},{"paper":"/paper/is-larger-always-better-evaluating-and","slug":"is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","arxiv_id":"2407.18525","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yhzhu99/ehr-llm-benchmark"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tagify-llm-powered-tagging-interface-for","title":"TAGIFY: LLM-powered Tagging Interface for Improved Data Findability on OGD portals","date":"2024-07-26","arxiv_id":"2407.18764","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-the","title":"Using Large Language Models for the Interpretation of Building Regulations","date":"2024-07-26","arxiv_id":"2407.21060","n_code_links":0,"syntology":null},{"paper":null,"slug":"closing-the-gap-between-open-source-and","title":"Closing the gap between open-source and commercial large language models for medical evidence summarization","date":"2024-07-25","arxiv_id":"2408.00588","n_code_links":0,"syntology":null},{"paper":"/paper/cost-effective-instruction-learning-for","slug":"cost-effective-instruction-learning-for","title":"Cost-effective Instruction Learning for Pathology Vision and Language Analysis","date":"2024-07-25","arxiv_id":"2407.17734","n_code_links":1,"syntology":null},{"paper":"/paper/peft-u-parameter-efficient-fine-tuning-for","slug":"peft-u-parameter-efficient-fine-tuning-for","title":"PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization","date":"2024-07-25","arxiv_id":"2407.18078","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ChrisIsKing/Parameter-Efficient-Personalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/personagym-evaluating-persona-agents-and-llms","slug":"personagym-evaluating-persona-agents-and-llms","title":"PersonaGym: Evaluating Persona Agents and LLMs","date":"2024-07-25","arxiv_id":"2407.18416","n_code_links":1,"syntology":null},{"paper":null,"slug":"bailicai-a-domain-optimized-retrieval","title":"Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications","date":"2024-07-24","arxiv_id":"2407.21055","n_code_links":0,"syntology":null},{"paper":null,"slug":"testing-large-language-models-on-driving","title":"Testing Large Language Models on Driving Theory Knowledge and Skills for Connected Autonomous Vehicles","date":"2024-07-24","arxiv_id":"2407.17211","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-the-polysemy-evolution-using","title":"Analyzing Polysemy Evolution Using Semantic Cells","date":"2024-07-23","arxiv_id":"2407.16110","n_code_links":0,"syntology":null},{"paper":"/paper/data-mixture-inference-what-do-bpe-tokenizers","slug":"data-mixture-inference-what-do-bpe-tokenizers","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","date":"2024-07-23","arxiv_id":"2407.16607","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":["alisawuffles/tokenizer-attack"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/enhancing-llm-s-cognition-via-structurization","slug":"enhancing-llm-s-cognition-via-structurization","title":"Enhancing LLM's Cognition via Structurization","date":"2024-07-23","arxiv_id":"2407.16434","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["alibaba/struxgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/patched-rtc-evaluating-llms-for-diverse","slug":"patched-rtc-evaluating-llms-for-diverse","title":"Patched RTC: evaluating LLMs for diverse software development tasks","date":"2024-07-23","arxiv_id":"2407.16557","n_code_links":1,"syntology":null},{"paper":"/paper/robust-privacy-amidst-innovation-with-large","slug":"robust-privacy-amidst-innovation-with-large","title":"Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks","date":"2024-07-23","arxiv_id":"2407.16166","n_code_links":1,"syntology":null},{"paper":null,"slug":"impacts-of-anthropomorphizing-large-language","title":"Impacts of Anthropomorphizing Large Language Models in Learning Environments","date":"2024-07-22","arxiv_id":"2408.03945","n_code_links":0,"syntology":null},{"paper":null,"slug":"imposter-ai-adversarial-attacks-with-hidden","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","date":"2024-07-22","arxiv_id":"2407.15399","n_code_links":0,"syntology":null},{"paper":"/paper/inverted-activations","slug":"inverted-activations","title":"Inverted Activations: Reducing Memory Footprint in Neural Network Training","date":"2024-07-22","arxiv_id":"2407.15545","n_code_links":1,"syntology":null},{"paper":"/paper/mminstruct-a-high-quality-multi-modal","slug":"mminstruct-a-high-quality-multi-modal","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","date":"2024-07-22","arxiv_id":"2407.15838","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yuecao0119/mminstruct"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/radiorag-factual-large-language-models-for","slug":"radiorag-factual-large-language-models-for","title":"RadioRAG: Factual large language models for enhanced diagnostics in radiology using online retrieval augmented generation","date":"2024-07-22","arxiv_id":"2407.15621","n_code_links":1,"syntology":null},{"paper":"/paper/stretching-each-dollar-diffusion-training","slug":"stretching-each-dollar-diffusion-training","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","date":"2024-07-22","arxiv_id":"2407.15811","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["sonyresearch/micro_diffusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unlocking-the-potential-benchmarking-large","title":"Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research","date":"2024-07-22","arxiv_id":"2407.21045","n_code_links":0,"syntology":null},{"paper":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","n_code_links":1,"syntology":null},{"paper":null,"slug":"sqlfuse-enhancing-text-to-sql-performance","title":"SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy","date":"2024-07-19","arxiv_id":"2407.14568","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","n_code_links":2,"syntology":{"ran":5,"of":8,"n_ran_checked":3,"n_instrument":2,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-open-source-llms-compete-with-commercial","slug":"can-open-source-llms-compete-with-commercial","title":"Can Open-Source LLMs Compete with Commercial Models? Exploring the Few-Shot Performance of Current GPT Models in Biomedical Tasks","date":"2024-07-18","arxiv_id":"2407.13511","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-large-language-models-for-anxiety","slug":"evaluating-large-language-models-for-anxiety","title":"Evaluating Large Language Models for Anxiety and Depression Classification using Counseling and Psychotherapy Transcripts","date":"2024-07-18","arxiv_id":"2407.13228","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-as-reliable-knowledge","title":"How Reliable are LLMs as Knowledge Bases? Re-thinking Facutality and Consistency","date":"2024-07-18","arxiv_id":"2407.13578","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-mistakes-prompting-for","title":"Learning-From-Mistakes Prompting for Indigenous Language Translation","date":"2024-07-18","arxiv_id":"2407.13343","n_code_links":0,"syntology":null},{"paper":null,"slug":"pragyan-connecting-the-dots-in-tweets","title":"PRAGyan -- Connecting the Dots in Tweets","date":"2024-07-18","arxiv_id":"2407.13909","n_code_links":0,"syntology":null},{"paper":"/paper/werewolf-arena-a-case-study-in-llm-evaluation","slug":"werewolf-arena-a-case-study-in-llm-evaluation","title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","date":"2024-07-18","arxiv_id":"2407.13943","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["google/werewolf_arena"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"beyond-binary-multiclass-paraphasia-detection","title":"Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models","date":"2024-07-16","arxiv_id":"2407.11345","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatbcg-can-ai-read-your-slide-deck","title":"ChatBCG: Can AI Read Your Slide Deck?","date":"2024-07-16","arxiv_id":"2407.12875","n_code_links":0,"syntology":null},{"paper":"/paper/does-refusal-training-in-llms-generalize-to","slug":"does-refusal-training-in-llms-generalize-to","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","date":"2024-07-16","arxiv_id":"2407.11969","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/llm-past-tense"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-assisted-annotation-of-rhetorical-and","title":"GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text","date":"2024-07-16","arxiv_id":"2407.11827","n_code_links":0,"syntology":null},{"paper":"/paper/lami-detr-open-vocabulary-detection-with","slug":"lami-detr-open-vocabulary-detection-with","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","date":"2024-07-16","arxiv_id":"2407.11335","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eternaldolphin/lami-detr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-as-misleading","title":"Large Language Models as Misleading Assistants in Conversation","date":"2024-07-16","arxiv_id":"2407.11789","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-visual-language-models-are-also-good","title":"Large Visual-Language Models Are Also Good Classifiers: A Study of In-Context Multimodal Fake News Detection","date":"2024-07-16","arxiv_id":"2407.12879","n_code_links":0,"syntology":null},{"paper":null,"slug":"representation-bias-in-political-sample","title":"Representation Bias in Political Sample Simulations with Large Language Models","date":"2024-07-16","arxiv_id":"2407.11409","n_code_links":0,"syntology":null},{"paper":null,"slug":"review-feedback-reason-refer-a-novel","title":"ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models","date":"2024-07-16","arxiv_id":"2407.12877","n_code_links":0,"syntology":null},{"paper":"/paper/trust-no-bot-discovering-personal-disclosures","slug":"trust-no-bot-discovering-personal-disclosures","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","date":"2024-07-16","arxiv_id":"2407.11438","n_code_links":1,"syntology":null},{"paper":null,"slug":"empowering-llms-for-verilog-generation","title":"CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarization","date":"2024-07-15","arxiv_id":"2407.10424","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-llm-respondents-for-item","title":"Leveraging LLM-Respondents for Item Evaluation: a Psychometric Analysis","date":"2024-07-15","arxiv_id":"2407.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-new-connections-llms-as-puzzle","title":"Making New Connections: LLMs as Puzzle Generators for The New York Times' Connections Word Game","date":"2024-07-15","arxiv_id":"2407.11240","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-interpretability-of-large","title":"Mechanistic interpretability of large language models with applications to the financial services industry","date":"2024-07-15","arxiv_id":"2407.11215","n_code_links":0,"syntology":null},{"paper":"/paper/metallm-a-high-performant-and-cost-efficient","slug":"metallm-a-high-performant-and-cost-efficient","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","date":"2024-07-15","arxiv_id":"2407.10834","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mail-research/metallm-wrapper"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"ebaf45c8fa2a0ffcefcd92ba504c2fb683aed06815fb7f7297f82fcc425fde69","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}