{"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/multi-head-attention/papers/53","list_of":"/method/multi-head-attention","method":"Multi-Head Attention","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":53,"pages_in_order":249,"rows_per_page":100,"rows":[5201,5300],"of":24855,"counts":{"archive_papers_tagged":24855,"with_a_code_link":11214,"where_syntology_ran_a_sample":3454,"not_listed_spam_title":0,"listed":24855,"listed_where_code_ran":3454,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2916,"every_run_a_failure_of_syntologys_instrument":538,"listed_with_a_run_with_no_instrument_failure":2916,"listed_every_run_a_failure_of_syntologys_instrument":538,"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/multi-head-attention","prev":"/method/multi-head-attention/papers/52","next":"/method/multi-head-attention/papers/54","papers":[{"paper":"/paper/exploring-retrieval-augmented-generation-in","slug":"exploring-retrieval-augmented-generation-in","title":"Exploring Retrieval Augmented Generation in Arabic","date":"2024-08-14","arxiv_id":"2408.07425","n_code_links":1,"syntology":null},{"paper":null,"slug":"g-2-v-2-former-graph-guided-video-vision","title":"G$^2$V$^2$former: Graph Guided Video Vision Transformer for Face Anti-Spoofing","date":"2024-08-14","arxiv_id":"2408.07675","n_code_links":0,"syntology":null},{"paper":"/paper/improved-3d-whole-heart-geometry-from-sparse","slug":"improved-3d-whole-heart-geometry-from-sparse","title":"Improved 3D Whole Heart Geometry from Sparse CMR Slices","date":"2024-08-14","arxiv_id":"2408.07532","n_code_links":1,"syntology":null},{"paper":null,"slug":"kraken-inherently-parallel-transformers-for","title":"Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference","date":"2024-08-14","arxiv_id":"2408.07802","n_code_links":0,"syntology":null},{"paper":"/paper/lipcot-linear-predictive-coding-based","slug":"lipcot-linear-predictive-coding-based","title":"LiPCoT: Linear Predictive Coding based Tokenizer for Self-supervised Learning of Time Series Data via Language Models","date":"2024-08-14","arxiv_id":"2408.07292","n_code_links":1,"syntology":null},{"paper":"/paper/metaseg-metaformer-based-global-contexts","slug":"metaseg-metaformer-based-global-contexts","title":"MetaSeg: MetaFormer-based Global Contexts-aware Network for Efficient Semantic Segmentation","date":"2024-08-14","arxiv_id":"2408.07576","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-periodicity-dependency-transformer","title":"Multi-periodicity dependency Transformer based on spectrum offset for radio frequency fingerprint identification","date":"2024-08-14","arxiv_id":"2408.07592","n_code_links":0,"syntology":null},{"paper":null,"slug":"sage-rt-synthetic-alignment-data-generation","title":"SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming","date":"2024-08-14","arxiv_id":"2408.11851","n_code_links":0,"syntology":null},{"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":null,"slug":"uahoi-uncertainty-aware-robust-interaction","title":"UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection","date":"2024-08-14","arxiv_id":"2408.07430","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-perspective-on-large-language-models","title":"A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition","date":"2024-08-13","arxiv_id":"2408.06598","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-s-conceptual-cartography-mapping-the","title":"BERT's Conceptual Cartography: Mapping the Landscapes of Meaning","date":"2024-08-13","arxiv_id":"2408.07190","n_code_links":0,"syntology":null},{"paper":"/paper/cross-view-geolocalization-and-disaster","slug":"cross-view-geolocalization-and-disaster","title":"Cross-View Geolocalization and Disaster Mapping with Street-View and VHR Satellite Imagery: A Case Study of Hurricane IAN","date":"2024-08-13","arxiv_id":"2408.06761","n_code_links":1,"syntology":null},{"paper":null,"slug":"divide-and-conquer-improving-multi-camera-3d","title":"Divide and Conquer: Improving Multi-Camera 3D Perception with 2D Semantic-Depth Priors and Input-Dependent Queries","date":"2024-08-13","arxiv_id":"2408.06901","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":"flatfusion-delving-into-details-of-sparse","title":"FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving","date":"2024-08-13","arxiv_id":"2408.06832","n_code_links":0,"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":"harnessing-earnings-reports-for-stock","title":"Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach","date":"2024-08-13","arxiv_id":"2408.06634","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-language-models-for-emotion-and","title":"Leveraging Language Models for Emotion and Behavior Analysis in Education","date":"2024-08-13","arxiv_id":"2408.06874","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-preprocessing-for-joint-detection-and","title":"Optimal Preprocessing for Joint Detection and Classification of Wireless Communication Signals in Congested Spectrum Using Computer Vision Methods","date":"2024-08-13","arxiv_id":"2408.06545","n_code_links":0,"syntology":null},{"paper":"/paper/photometric-inverse-rendering-shading-cues","slug":"photometric-inverse-rendering-shading-cues","title":"PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization","date":"2024-08-13","arxiv_id":"2408.06828","n_code_links":1,"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/reclip-learn-to-rectify-the-bias-of-clip-for","slug":"reclip-learn-to-rectify-the-bias-of-clip-for","title":"ReCLIP++: Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation","date":"2024-08-13","arxiv_id":"2408.06747","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":{"repos":["dogehhh/reclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/spectrum-prediction-with-deep-3d-pyramid","slug":"spectrum-prediction-with-deep-3d-pyramid","title":"Spectrum Prediction With Deep 3D Pyramid Vision Transformer Learning","date":"2024-08-13","arxiv_id":"2408.06870","n_code_links":1,"syntology":null},{"paper":"/paper/sumotosima-a-framework-and-dataset-for","slug":"sumotosima-a-framework-and-dataset-for","title":"Sumotosima: A Framework and Dataset for Classifying and Summarizing Otoscopic Images","date":"2024-08-13","arxiv_id":"2408.06755","n_code_links":1,"syntology":null},{"paper":null,"slug":"tableguard-securing-structured-unstructured","title":"TableGuard -- Securing Structured & Unstructured Data","date":"2024-08-13","arxiv_id":"2408.07045","n_code_links":0,"syntology":null},{"paper":"/paper/unlocking-efficiency-adaptive-masking-for","slug":"unlocking-efficiency-adaptive-masking-for","title":"Unlocking Efficiency: Adaptive Masking for Gene Transformer Models","date":"2024-08-13","arxiv_id":"2408.07180","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-advanced-llms-to-enhance-smaller-llms","title":"Using Advanced LLMs to Enhance Smaller LLMs: An Interpretable Knowledge Distillation Approach","date":"2024-08-13","arxiv_id":"2408.07238","n_code_links":0,"syntology":null},{"paper":null,"slug":"vulcatch-enhancing-binary-vulnerability","title":"VulCatch: Enhancing Binary Vulnerability Detection through CodeT5 Decompilation and KAN Advanced Feature Extraction","date":"2024-08-13","arxiv_id":"2408.07181","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-load-forecasting-approach-for-integrated","title":"A load forecasting approach for integrated energy systems based on aggregation hybrid modal decomposition and combined model","date":"2024-08-12","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-vision-transformers-and-open-set","title":"Advanced Vision Transformers and Open-Set Learning for Robust Mosquito Classification: A Novel Approach to Entomological Studies","date":"2024-08-12","arxiv_id":"2408.06457","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesian-inference-to-improve-quality-of","title":"Bayesian inference to improve quality of Retrieval Augmented Generation","date":"2024-08-12","arxiv_id":"2408.08901","n_code_links":0,"syntology":null},{"paper":null,"slug":"body-transformer-leveraging-robot-embodiment","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","date":"2024-08-12","arxiv_id":"2408.06316","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-conversational-speech","title":"Cross-Lingual Conversational Speech Summarization with Large Language Models","date":"2024-08-12","arxiv_id":"2408.06484","n_code_links":0,"syntology":null},{"paper":null,"slug":"dpdetr-decoupled-position-detection","title":"DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection","date":"2024-08-12","arxiv_id":"2408.06123","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-and-scalable-point-cloud-generation","slug":"efficient-and-scalable-point-cloud-generation","title":"Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models","date":"2024-08-12","arxiv_id":"2408.06145","n_code_links":2,"syntology":null},{"paper":null,"slug":"endogenous-crashes-as-phase-transitions","title":"Endogenous Crashes as Phase Transitions","date":"2024-08-12","arxiv_id":"2408.06433","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-3d-transformer-segmentation-model","slug":"enhancing-3d-transformer-segmentation-model","title":"Enhancing 3D Transformer Segmentation Model for Medical Image with Token-level Representation Learning","date":"2024-08-12","arxiv_id":"2408.05889","n_code_links":1,"syntology":null},{"paper":"/paper/hat-history-augmented-anchor-transformer-for","slug":"hat-history-augmented-anchor-transformer-for","title":"HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization","date":"2024-08-12","arxiv_id":"2408.06437","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":12,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"13 ran (of which 3 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sakibreza/eccv24-hat"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":3,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"improving-structural-diversity-of-blackbox","title":"Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting","date":"2024-08-12","arxiv_id":"2408.06186","n_code_links":0,"syntology":null},{"paper":null,"slug":"lolgorithm-integrating-semantic-syntactic-and","title":"LOLgorithm: Integrating Semantic,Syntactic and Contextual Elements for Humor Classification","date":"2024-08-12","arxiv_id":"2408.06335","n_code_links":0,"syntology":null},{"paper":null,"slug":"med42-v2-a-suite-of-clinical-llms","title":"Med42-v2: A Suite of Clinical LLMs","date":"2024-08-12","arxiv_id":"2408.06142","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-rag-techniques-for-automotive","title":"Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models","date":"2024-08-12","arxiv_id":"2408.05933","n_code_links":0,"syntology":null},{"paper":"/paper/paformer-part-aware-transformer-for-person-re","slug":"paformer-part-aware-transformer-for-person-re","title":"PAFormer: Part Aware Transformer for Person Re-identification","date":"2024-08-12","arxiv_id":"2408.05918","n_code_links":0,"syntology":null},{"paper":null,"slug":"phago-protein-function-annotation-for","title":"PhaGO: Protein function annotation for bacteriophages by integrating the genomic context","date":"2024-08-12","arxiv_id":"2408.06402","n_code_links":0,"syntology":null},{"paper":"/paper/risurconv-rotation-invariant-surface","slug":"risurconv-rotation-invariant-surface","title":"RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation","date":"2024-08-12","arxiv_id":"2408.06110","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":2,"n_instrument":9,"unverified":5,"pointer_only":0,"phrase":"11 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; 9 where Syntology's instrument failed) · 5 unverified","official":{"repos":["cszyzhang/RISurConv"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/spacetime-e-n-transformer-equivariant","slug":"spacetime-e-n-transformer-equivariant","title":"Spacetime $E(n)$-Transformer: Equivariant Attention for Spatio-temporal Graphs","date":"2024-08-12","arxiv_id":"2408.06039","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-language-of-trauma-modeling-traumatic","title":"The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI","date":"2024-08-12","arxiv_id":"2408.05977","n_code_links":0,"syntology":null},{"paper":null,"slug":"utilize-transformers-for-translating","title":"Utilize Transformers for translating Wikipedia category names","date":"2024-08-12","arxiv_id":"2408.06124","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-hoi-using-a-training-free","title":"An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set","date":"2024-08-11","arxiv_id":"2408.05772","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-emulates-average-human-emotional","title":"GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective","date":"2024-08-11","arxiv_id":"2408.13718","n_code_links":0,"syntology":null},{"paper":"/paper/hyspark-hybrid-sparse-masking-for-large-scale","slug":"hyspark-hybrid-sparse-masking-for-large-scale","title":"HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training","date":"2024-08-11","arxiv_id":"2408.05815","n_code_links":1,"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":null,"slug":"sampling-foundational-transformer-a","title":"Sampling Foundational Transformer: A Theoretical Perspective","date":"2024-08-11","arxiv_id":"2408.05822","n_code_links":0,"syntology":null},{"paper":"/paper/tc-kanrecon-high-quality-and-accelerated-mri","slug":"tc-kanrecon-high-quality-and-accelerated-mri","title":"TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature Scaling","date":"2024-08-11","arxiv_id":"2408.05705","n_code_links":1,"syntology":null},{"paper":"/paper/u-decn-end-to-end-underwater-object-detection","slug":"u-decn-end-to-end-underwater-object-detection","title":"U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training","date":"2024-08-11","arxiv_id":"2408.05780","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":"beyondct-a-deep-learning-model-for-predicting","title":"BeyondCT: A deep learning model for predicting pulmonary function from chest CT scans","date":"2024-08-10","arxiv_id":"2408.05645","n_code_links":0,"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":null,"slug":"modeling-multi-step-scientific-processes-with","title":"Modeling Multi-Step Scientific Processes with Graph Transformer Networks","date":"2024-08-10","arxiv_id":"2408.05425","n_code_links":0,"syntology":null},{"paper":"/paper/personvit-large-scale-self-supervised-vision","slug":"personvit-large-scale-self-supervised-vision","title":"PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification","date":"2024-08-10","arxiv_id":"2408.05398","n_code_links":1,"syntology":null},{"paper":null,"slug":"pointmt-efficient-point-cloud-analysis-with","title":"PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecture","date":"2024-08-10","arxiv_id":"2408.05508","n_code_links":0,"syntology":null},{"paper":"/paper/swift-a-scalable-lightweight-infrastructure","slug":"swift-a-scalable-lightweight-infrastructure","title":"SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning","date":"2024-08-10","arxiv_id":"2408.05517","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["modelscope/ms-swift","modelscope/swift"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"a-hybrid-rag-system-with-comprehensive","title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","date":"2024-08-09","arxiv_id":"2408.05141","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-meets-iris-biometrics","title":"ChatGPT Meets Iris Biometrics","date":"2024-08-09","arxiv_id":"2408.04868","n_code_links":0,"syntology":null},{"paper":null,"slug":"confusedpilot-compromising-enterprise","title":"ConfusedPilot: Confused Deputy Risks in RAG-based LLMs","date":"2024-08-09","arxiv_id":"2408.04870","n_code_links":0,"syntology":null},{"paper":"/paper/deepinteraction-multi-modality-interaction","slug":"deepinteraction-multi-modality-interaction","title":"DeepInteraction++: Multi-Modality Interaction for Autonomous Driving","date":"2024-08-09","arxiv_id":"2408.05075","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["fudan-zvg/deepinteraction"],"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":"/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":"ensemble-bert-a-student-social-network-text","title":"Ensemble BERT: A student social network text sentiment classification model based on ensemble learning and BERT architecture","date":"2024-08-09","arxiv_id":"2408.04849","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-capability-of-large-language","title":"Evaluating the capability of large language models to personalize science texts for diverse middle-school-age learners","date":"2024-08-09","arxiv_id":"2408.05204","n_code_links":0,"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":"hybridrag-integrating-knowledge-graphs-and","title":"HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction","date":"2024-08-09","arxiv_id":"2408.04948","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-thematic-analysis","title":"Large Language Models and Thematic Analysis: Human-AI Synergy in Researching Hate Speech on Social Media","date":"2024-08-09","arxiv_id":"2408.05126","n_code_links":0,"syntology":null},{"paper":"/paper/llmjudge-llms-for-relevance-judgments","slug":"llmjudge-llms-for-relevance-judgments","title":"LLMJudge: LLMs for Relevance Judgments","date":"2024-08-09","arxiv_id":"2408.08896","n_code_links":1,"syntology":null},{"paper":null,"slug":"midi-to-tab-guitar-tablature-inference-via","title":"MIDI-to-Tab: Guitar Tablature Inference via Masked Language Modeling","date":"2024-08-09","arxiv_id":"2408.05024","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-portfolio-with-two-sided","title":"Optimizing Portfolio with Two-Sided Transactions and Lending: A Reinforcement Learning Framework","date":"2024-08-09","arxiv_id":"2408.05382","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-and-roll-an-end-to-end-evaluation-of","title":"Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks","date":"2024-08-09","arxiv_id":"2408.05025","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":null,"slug":"analysis-of-argument-structure-constructions","title":"Analysis of Argument Structure Constructions in the Large Language Model BERT","date":"2024-08-08","arxiv_id":"2408.04270","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-mechanism-and-context-modeling","title":"Attention Mechanism and Context Modeling System for Text Mining Machine Translation","date":"2024-08-08","arxiv_id":"2408.04216","n_code_links":0,"syntology":null},{"paper":"/paper/brat-bonus-orthogonal-token-for-architecture","slug":"brat-bonus-orthogonal-token-for-architecture","title":"BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion","date":"2024-08-08","arxiv_id":"2408.04785","n_code_links":1,"syntology":null},{"paper":null,"slug":"can-gpt-4-models-detect-misleading","title":"Can GPT-4 Models Detect Misleading Visualizations?","date":"2024-08-08","arxiv_id":"2408.12617","n_code_links":0,"syntology":null},{"paper":"/paper/efficientrag-efficient-retriever-for-multi","slug":"efficientrag-efficient-retriever-for-multi","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","date":"2024-08-08","arxiv_id":"2408.04259","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":["nil-zhuang/efficientrag-official"],"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":null,"slug":"how-transformers-utilize-multi-head-attention","title":"How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression","date":"2024-08-08","arxiv_id":"2408.04532","n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-student-teacher-large-language-model","title":"Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction","date":"2024-08-08","arxiv_id":"2408.04775","n_code_links":0,"syntology":null},{"paper":null,"slug":"m2ef-nns-multimodal-multi-instance-evidence","title":"M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Prediction","date":"2024-08-08","arxiv_id":"2408.04170","n_code_links":0,"syntology":null},{"paper":"/paper/medical-graph-rag-towards-safe-medical-large","slug":"medical-graph-rag-towards-safe-medical-large","title":"Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation","date":"2024-08-08","arxiv_id":"2408.04187","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["medicinetoken/medical-graph-rag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"multi-turn-context-jailbreak-attack-on-large","title":"Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles","date":"2024-08-08","arxiv_id":"2408.04686","n_code_links":0,"syntology":null},{"paper":"/paper/scalable-transformer-for-high-dimensional","slug":"scalable-transformer-for-high-dimensional","title":"Scalable Transformer for High Dimensional Multivariate Time Series Forecasting","date":"2024-08-08","arxiv_id":"2408.04245","n_code_links":1,"syntology":null},{"paper":null,"slug":"scene-evaluating-explainable-ai-techniques","title":"SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals","date":"2024-08-08","arxiv_id":"2408.04575","n_code_links":0,"syntology":null},{"paper":null,"slug":"survey-transformer-based-models-in-data","title":"Survey: Transformer-based Models in Data Modality Conversion","date":"2024-08-08","arxiv_id":"2408.04723","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-explainable-network-intrusion","title":"Towards Explainable Network Intrusion Detection using Large Language Models","date":"2024-08-08","arxiv_id":"2408.04342","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-resilient-and-efficient-llms-a","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","date":"2024-08-08","arxiv_id":"2408.04585","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":"uhnet-an-ultra-lightweight-and-high-speed","title":"UHNet: An Ultra-Lightweight and High-Speed Edge Detection Network","date":"2024-08-08","arxiv_id":"2408.04258","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-llm-finetuning-methods","title":"A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case","date":"2024-08-07","arxiv_id":"2408.03562","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-level-spatial-and-channel-aware","title":"Bi-Level Spatial and Channel-aware Transformer for Learned Image Compression","date":"2024-08-07","arxiv_id":"2408.03842","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-rule-based-insights-enhance-llms-for","title":"Can Rule-Based Insights Enhance LLMs for Radiology Report Classification? Introducing the RadPrompt Methodology","date":"2024-08-07","arxiv_id":"2408.04121","n_code_links":0,"syntology":null}],"record_sha256":"9bc05b35ac9cb69174e616096e38c034d0df8bac4d02afa99b567bfbe4c0a70a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}