{"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/cosine-annealing/papers/6","list_of":"/method/cosine-annealing","method":"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":6,"pages_in_order":40,"rows_per_page":100,"rows":[501,600],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/5","next":"/method/cosine-annealing/papers/7","papers":[{"paper":null,"slug":"prompting-and-fine-tuning-large-language","title":"Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation","date":"2024-11-15","arxiv_id":"2411.10129","n_code_links":0,"syntology":null},{"paper":null,"slug":"take-package-as-language-anomaly-detection","title":"Take Package as Language: Anomaly Detection Using Transformer","date":"2024-11-15","arxiv_id":"2412.04473","n_code_links":0,"syntology":null},{"paper":null,"slug":"babylm-challenge-exploring-the-effect-of","title":"BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency","date":"2024-11-14","arxiv_id":"2411.09587","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-static-tools-evaluating-large-language","title":"Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection","date":"2024-11-14","arxiv_id":"2411.09772","n_code_links":0,"syntology":null},{"paper":null,"slug":"hategpt-unleashing-gpt-3-5-turbo-to-combat","title":"HateGPT: Unleashing GPT-3.5 Turbo to Combat Hate Speech on X","date":"2024-11-14","arxiv_id":"2411.09214","n_code_links":0,"syntology":null},{"paper":null,"slug":"llmstinger-jailbreaking-llms-using-rl-fine","title":"LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs","date":"2024-11-13","arxiv_id":"2411.08862","n_code_links":0,"syntology":null},{"paper":null,"slug":"responsible-ai-in-construction-safety","title":"Responsible AI in Construction Safety: Systematic Evaluation of Large Language Models and Prompt Engineering","date":"2024-11-13","arxiv_id":"2411.08320","n_code_links":0,"syntology":null},{"paper":null,"slug":"valtest-automated-validation-of-language","title":"VALTEST: Automated Validation of Language Model Generated Test Cases","date":"2024-11-13","arxiv_id":"2411.08254","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-chatgpt-3-5-efficiency-in-solving","slug":"evaluating-chatgpt-3-5-efficiency-in-solving","title":"Evaluating ChatGPT-3.5 Efficiency in Solving Coding Problems of Different Complexity Levels: An Empirical Analysis","date":"2024-11-12","arxiv_id":"2411.07529","n_code_links":1,"syntology":null},{"paper":"/paper/fair-summarization-bridging-quality-and","slug":"fair-summarization-bridging-quality-and","title":"Fair Summarization: Bridging Quality and Diversity in Extractive Summaries","date":"2024-11-12","arxiv_id":"2411.07521","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["PortNLP/FairEXTSummarizer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"llm-app-squatting-and-cloning","title":"LLM App Squatting and Cloning","date":"2024-11-12","arxiv_id":"2411.07518","n_code_links":0,"syntology":null},{"paper":null,"slug":"ambient-ai-scribing-support-comparing-the","title":"Ambient AI Scribing Support: Comparing the Performance of Specialized AI Agentic Architecture to Leading Foundational Models","date":"2024-11-11","arxiv_id":"2411.06713","n_code_links":0,"syntology":null},{"paper":"/paper/autonomous-droplet-microfluidic-design","slug":"autonomous-droplet-microfluidic-design","title":"Autonomous Droplet Microfluidic Design Framework with Large Language Models","date":"2024-11-11","arxiv_id":"2411.06691","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancer-answer-empowering-cancer-care-with","title":"Cancer-Answer: Empowering Cancer Care with Advanced Large Language Models","date":"2024-11-11","arxiv_id":"2411.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"explore-the-reasoning-capability-of-llms-in","title":"Explore the Reasoning Capability of LLMs in the Chess Testbed","date":"2024-11-11","arxiv_id":"2411.06655","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-active-privacy-auditing-in-supervised-fine","title":"On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models","date":"2024-11-11","arxiv_id":"2411.07070","n_code_links":0,"syntology":null},{"paper":null,"slug":"spartan-a-sparse-transformer-learning-local","title":"SPARTAN: A Sparse Transformer Learning Local Causation","date":"2024-11-11","arxiv_id":"2411.06890","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-efficient-fine-tuning-for-gpt-like","title":"Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques","date":"2024-11-10","arxiv_id":"2411.06445","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-reference-errors-in-scientific","slug":"detecting-reference-errors-in-scientific","title":"Detecting Reference Errors in Scientific Literature with Large Language Models","date":"2024-11-09","arxiv_id":"2411.06101","n_code_links":1,"syntology":null},{"paper":null,"slug":"sufficient-context-a-new-lens-on-retrieval","title":"Sufficient Context: A New Lens on Retrieval Augmented Generation Systems","date":"2024-11-09","arxiv_id":"2411.06037","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-visual-classification-using","slug":"enhancing-visual-classification-using","title":"Enhancing Visual Classification using Comparative Descriptors","date":"2024-11-08","arxiv_id":"2411.05357","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-semantic-cache-reducing-llm-costs-and","title":"GPT Semantic Cache: Reducing LLM Costs and Latency via Semantic Embedding Caching","date":"2024-11-08","arxiv_id":"2411.05276","n_code_links":0,"syntology":null},{"paper":"/paper/learning-the-rules-of-peptide-self-assembly","slug":"learning-the-rules-of-peptide-self-assembly","title":"Learning the rules of peptide self-assembly through data mining with large language models","date":"2024-11-08","arxiv_id":"2411.05421","n_code_links":1,"syntology":null},{"paper":null,"slug":"neko-toward-post-recognition-generative","title":"NeKo: Toward Post Recognition Generative Correction Large Language Models with Task-Oriented Experts","date":"2024-11-08","arxiv_id":"2411.05945","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-robustness-of-in-context-learning","title":"Adversarial Robustness of In-Context Learning in Transformers for Linear Regression","date":"2024-11-07","arxiv_id":"2411.05189","n_code_links":0,"syntology":null},{"paper":"/paper/finetunebench-how-well-do-commercial-fine","slug":"finetunebench-how-well-do-commercial-fine","title":"FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?","date":"2024-11-07","arxiv_id":"2411.05059","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-guided-monte-carlo-tree-search-for","title":"GPT-Guided Monte Carlo Tree Search for Symbolic Regression in Financial Fraud Detection","date":"2024-11-07","arxiv_id":"2411.04459","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrievegpt-merging-prompts-and-mathematical","title":"RetrieveGPT: Merging Prompts and Mathematical Models for Enhanced Code-Mixed Information Retrieval","date":"2024-11-07","arxiv_id":"2411.04752","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-between-bert-and-gpt-for-text","title":"Selecting Between BERT and GPT for Text Classification in Political Science Research","date":"2024-11-07","arxiv_id":"2411.05050","n_code_links":0,"syntology":null},{"paper":null,"slug":"stand-guard-a-small-task-adaptive-content","title":"STAND-Guard: A Small Task-Adaptive Content Moderation Model","date":"2024-11-07","arxiv_id":"2411.05214","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-recent-large-language","title":"A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients","date":"2024-11-06","arxiv_id":"2411.03805","n_code_links":0,"syntology":null},{"paper":"/paper/can-custom-models-learn-in-context-an","slug":"can-custom-models-learn-in-context-an","title":"Can Custom Models Learn In-Context? An Exploration of Hybrid Architecture Performance on In-Context Learning Tasks","date":"2024-11-06","arxiv_id":"2411.03945","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-word-vectors-to-multimodal-embeddings","title":"From Word Vectors to Multimodal Embeddings: Techniques, Applications, and Future Directions For Large Language Models","date":"2024-11-06","arxiv_id":"2411.05036","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-device-emoji-classifier-trained-with-gpt","title":"On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard","date":"2024-11-06","arxiv_id":"2411.05031","n_code_links":0,"syntology":null},{"paper":null,"slug":"phdgpt-introducing-a-psychometric-and","title":"PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology","date":"2024-11-06","arxiv_id":"2411.10473","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-using-gpt-for-word-level","title":"Prompt Engineering Using GPT for Word-Level Code-Mixed Language Identification in Low-Resource Dravidian Languages","date":"2024-11-06","arxiv_id":"2411.04025","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpreting-language-models-a-case","slug":"towards-interpreting-language-models-a-case","title":"Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning","date":"2024-11-06","arxiv_id":"2411.05037","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["msakarvadia/attentionlens"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-the-effects-of-human-written","slug":"understanding-the-effects-of-human-written","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","date":"2024-11-06","arxiv_id":"2411.03806","n_code_links":1,"syntology":null},{"paper":null,"slug":"youtube-comments-decoded-leveraging-llms-for","title":"YouTube Comments Decoded: Leveraging LLMs for Low Resource Language Classification","date":"2024-11-06","arxiv_id":"2411.05039","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-generation-of-question-hints-for","title":"Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology","date":"2024-11-05","arxiv_id":"2411.03495","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-transformer-training-efficiency","title":"Enhancing Transformer Training Efficiency with Dynamic Dropout","date":"2024-11-05","arxiv_id":"2411.03236","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancements-and-limitations-of-llms-in","title":"Advancements and limitations of LLMs in replicating human color-word associations","date":"2024-11-04","arxiv_id":"2411.02116","n_code_links":0,"syntology":null},{"paper":"/paper/ask-and-it-shall-be-given-turing-completeness","slug":"ask-and-it-shall-be-given-turing-completeness","title":"Ask, and it shall be given: On the Turing completeness of prompting","date":"2024-11-04","arxiv_id":"2411.01992","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-ability-of-large-language-1","title":"Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast","date":"2024-11-04","arxiv_id":"2411.02318","n_code_links":0,"syntology":null},{"paper":null,"slug":"grounding-emotional-descriptions-to","title":"Grounding Emotional Descriptions to Electrovibration Haptic Signals","date":"2024-11-04","arxiv_id":"2411.02118","n_code_links":0,"syntology":null},{"paper":null,"slug":"mdeval-massively-multilingual-code-debugging","title":"MdEval: Massively Multilingual Code Debugging","date":"2024-11-04","arxiv_id":"2411.02310","n_code_links":0,"syntology":null},{"paper":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-neural-network-interpretability-1","slug":"enhancing-neural-network-interpretability-1","title":"Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders","date":"2024-11-02","arxiv_id":"2411.01220","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["luke-marks0/mutual-feature-regularization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-impact-of-lab-test-results-on","title":"Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes","date":"2024-11-01","arxiv_id":"2411.02523","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-a-game-changer-for-software-engineers","title":"LLMs: A Game-Changer for Software Engineers?","date":"2024-11-01","arxiv_id":"2411.00932","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-reducing-the-need-for-learning-rate","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","date":"2024-10-31","arxiv_id":"2410.23922","n_code_links":0,"syntology":null},{"paper":null,"slug":"automating-quantum-software-maintenance","title":"Automating Quantum Software Maintenance: Flakiness Detection and Root Cause Analysis","date":"2024-10-31","arxiv_id":"2410.23578","n_code_links":0,"syntology":null},{"paper":"/paper/selfcodealign-self-alignment-for-code","slug":"selfcodealign-self-alignment-for-code","title":"SelfCodeAlign: Self-Alignment for Code Generation","date":"2024-10-31","arxiv_id":"2410.24198","n_code_links":2,"syntology":{"ran":30,"of":37,"n_ran_checked":22,"n_instrument":8,"unverified":7,"pointer_only":0,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","official":{"repos":["bigcode-project/selfcodealign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["community","listed","official"]}}},{"paper":null,"slug":"a-comprehensive-study-on-quantization","title":"A Comprehensive Study on Quantization Techniques for Large Language Models","date":"2024-10-30","arxiv_id":"2411.02530","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-enrichment-of-the-quantum-cascade","slug":"semantic-enrichment-of-the-quantum-cascade","title":"Semantic Enrichment of the Quantum Cascade Laser Properties in Text- A Knowledge Graph Generation Approach","date":"2024-10-30","arxiv_id":"2410.22996","n_code_links":1,"syntology":null},{"paper":null,"slug":"cfsafety-comprehensive-fine-grained-safety","title":"CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs","date":"2024-10-29","arxiv_id":"2410.21695","n_code_links":0,"syntology":null},{"paper":null,"slug":"coupling-quantum-like-cognition-with-the","title":"Coupling quantum-like cognition with the neuronal networks within generalized probability theory","date":"2024-10-29","arxiv_id":"2411.00036","n_code_links":0,"syntology":null},{"paper":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequential-choice-in-ordered-bundles","title":"Sequential choice in ordered bundles","date":"2024-10-29","arxiv_id":"2410.21670","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-yet-effective-corpus-construction-1","slug":"a-simple-yet-effective-corpus-construction-1","title":"A Simple Yet Effective Corpus Construction Framework for Indonesian Grammatical Error Correction","date":"2024-10-28","arxiv_id":"2410.20838","n_code_links":1,"syntology":null},{"paper":"/paper/blast-block-level-adaptive-structured","slug":"blast-block-level-adaptive-structured","title":"BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference","date":"2024-10-28","arxiv_id":"2410.21262","n_code_links":1,"syntology":null},{"paper":null,"slug":"causal-interventions-on-causal-paths-mapping","title":"Causal Interventions on Causal Paths: Mapping GPT-2's Reasoning From Syntax to Semantics","date":"2024-10-28","arxiv_id":"2410.21353","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-4-less-politically-biased-than-gpt-3-5","title":"Is GPT-4 Less Politically Biased than GPT-3.5? A Renewed Investigation of ChatGPT's Political Biases","date":"2024-10-28","arxiv_id":"2410.21008","n_code_links":0,"syntology":null},{"paper":"/paper/multitok-variable-length-tokenization-for","slug":"multitok-variable-length-tokenization-for","title":"MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression","date":"2024-10-28","arxiv_id":"2410.21548","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-search-evaluation","title":"Semantic Search Evaluation","date":"2024-10-28","arxiv_id":"2410.21549","n_code_links":0,"syntology":null},{"paper":null,"slug":"stealthy-jailbreak-attacks-on-large-language","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","date":"2024-10-28","arxiv_id":"2410.21083","n_code_links":0,"syntology":null},{"paper":"/paper/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","n_code_links":1,"syntology":null},{"paper":null,"slug":"think-carefully-and-check-again-meta","title":"Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization","date":"2024-10-26","arxiv_id":"2410.20021","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-tutorial-on-teaching-data-analytics-with","title":"A Tutorial on Teaching Data Analytics with Generative AI","date":"2024-10-25","arxiv_id":"2411.07244","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-large-language-models-with-2","title":"Integrating Large Language Models with Internet of Things Applications","date":"2024-10-25","arxiv_id":"2410.19223","n_code_links":0,"syntology":null},{"paper":"/paper/iterative-self-tuning-llms-for-enhanced","slug":"iterative-self-tuning-llms-for-enhanced","title":"Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities","date":"2024-10-24","arxiv_id":"2410.18469","n_code_links":1,"syntology":null},{"paper":"/paper/little-giants-synthesizing-high-quality","slug":"little-giants-synthesizing-high-quality","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","date":"2024-10-24","arxiv_id":"2410.18634","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":11,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["haon-chen/SPEED"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"probing-ranking-llms-mechanistic","title":"Understanding Ranking LLMs: A Mechanistic Analysis for Information Retrieval","date":"2024-10-24","arxiv_id":"2410.18527","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-up-masked-diffusion-models-on-text","slug":"scaling-up-masked-diffusion-models-on-text","title":"Scaling up Masked Diffusion Models on Text","date":"2024-10-24","arxiv_id":"2410.18514","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ml-gsai/smdm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/differentially-private-learning-needs-better","slug":"differentially-private-learning-needs-better","title":"Differentially Private Learning Needs Better Model Initialization and Self-Distillation","date":"2024-10-23","arxiv_id":"2410.17566","n_code_links":1,"syntology":null},{"paper":null,"slug":"future-token-prediction-causal-language","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","date":"2024-10-23","arxiv_id":"2410.18160","n_code_links":0,"syntology":null},{"paper":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","n_code_links":1,"syntology":null},{"paper":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","n_code_links":1,"syntology":null},{"paper":null,"slug":"scattered-forest-search-smarter-code-space","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","date":"2024-10-22","arxiv_id":"2411.05010","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-system-for-automatic-map","slug":"an-efficient-system-for-automatic-map","title":"An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps","date":"2024-10-21","arxiv_id":"2410.15780","n_code_links":1,"syntology":null},{"paper":"/paper/developing-retrieval-augmented-generation-rag","slug":"developing-retrieval-augmented-generation-rag","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","date":"2024-10-21","arxiv_id":"2410.15944","n_code_links":1,"syntology":null},{"paper":null,"slug":"guardians-of-discourse-evaluating-llms-on","title":"Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection","date":"2024-10-21","arxiv_id":"2410.15623","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-neuron-level-interpretability-with","title":"Improving Neuron-level Interpretability with White-box Language Models","date":"2024-10-21","arxiv_id":"2410.16443","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-body-language-models","title":"Large Body Language Models","date":"2024-10-21","arxiv_id":"2410.16533","n_code_links":0,"syntology":null},{"paper":"/paper/on-creating-an-english-thai-code-switched","slug":"on-creating-an-english-thai-code-switched","title":"On Creating an English-Thai Code-switched Machine Translation in Medical Domain","date":"2024-10-21","arxiv_id":"2410.16221","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-gpt-models-for-qualitative-and","title":"Using GPT Models for Qualitative and Quantitative News Analytics in the 2024 US Presidental Election Process","date":"2024-10-21","arxiv_id":"2410.15884","n_code_links":0,"syntology":null},{"paper":"/paper/brief-bridging-retrieval-and-inference-for","slug":"brief-bridging-retrieval-and-inference-for","title":"BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression","date":"2024-10-20","arxiv_id":"2410.15277","n_code_links":1,"syntology":null},{"paper":"/paper/does-chatgpt-have-a-poetic-style","slug":"does-chatgpt-have-a-poetic-style","title":"Does ChatGPT Have a Poetic Style?","date":"2024-10-20","arxiv_id":"2410.15299","n_code_links":1,"syntology":null},{"paper":null,"slug":"sdp4bit-toward-4-bit-communication","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","date":"2024-10-20","arxiv_id":"2410.15526","n_code_links":0,"syntology":null},{"paper":null,"slug":"bias-amplification-language-models-as","title":"Bias Amplification: Language Models as Increasingly Biased Media","date":"2024-10-19","arxiv_id":"2410.15234","n_code_links":0,"syntology":null},{"paper":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/faithbench-a-diverse-hallucination-benchmark","slug":"faithbench-a-diverse-hallucination-benchmark","title":"FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs","date":"2024-10-17","arxiv_id":"2410.13210","n_code_links":2,"syntology":null},{"paper":"/paper/help-me-identify-is-an-llm-vqa-system-all-we","slug":"help-me-identify-is-an-llm-vqa-system-all-we","title":"Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?","date":"2024-10-17","arxiv_id":"2410.13651","n_code_links":1,"syntology":null},{"paper":null,"slug":"jailbreaking-llm-controlled-robots","title":"Jailbreaking LLM-Controlled Robots","date":"2024-10-17","arxiv_id":"2410.13691","n_code_links":0,"syntology":null},{"paper":null,"slug":"metacognitive-monitoring-a-human-ability","title":"Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence","date":"2024-10-17","arxiv_id":"2410.13392","n_code_links":0,"syntology":null},{"paper":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-compute-optimal-vision-transformers","title":"Training Compute-Optimal Vision Transformers for Brain Encoding","date":"2024-10-17","arxiv_id":"2410.19810","n_code_links":0,"syntology":null}],"record_sha256":"23e01af5b9491ad047797a160748a8a9fb2e52353470c8877c065711944abeaf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}