{"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/wordpiece/papers/15","list_of":"/method/wordpiece","method":"WordPiece","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":15,"pages_in_order":71,"rows_per_page":100,"rows":[1401,1500],"of":7063,"counts":{"archive_papers_tagged":7063,"with_a_code_link":2910,"where_syntology_ran_a_sample":650,"not_listed_spam_title":0,"listed":7063,"listed_where_code_ran":650,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":529,"every_run_a_failure_of_syntologys_instrument":121,"listed_with_a_run_with_no_instrument_failure":529,"listed_every_run_a_failure_of_syntologys_instrument":121,"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/wordpiece","prev":"/method/wordpiece/papers/14","next":"/method/wordpiece/papers/16","papers":[{"paper":null,"slug":"enhancing-visual-question-answering-through-1","title":"Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion","date":"2024-08-14","arxiv_id":"2408.07303","n_code_links":0,"syntology":null},{"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":"/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":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":"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":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":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":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":"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":"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":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":"/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":"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":"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":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":"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":"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":"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":"/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":"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":"/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":"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":"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":"/paper/exploring-rag-based-vulnerability","slug":"exploring-rag-based-vulnerability","title":"VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs","date":"2024-08-07","arxiv_id":"2408.04125","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":null,"slug":"maxmind-a-memory-loop-network-to-enhance","title":"MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models","date":"2024-08-07","arxiv_id":"2408.03841","n_code_links":0,"syntology":null},{"paper":"/paper/2408-03099","slug":"2408-03099","title":"Topic Modeling with Fine-tuning LLMs and Bag of Sentences","date":"2024-08-06","arxiv_id":"2408.03099","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":["johntailor/ft-topic"],"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":"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":"2408-03172","title":"Leveraging Parameter Efficient Training Methods for Low Resource Text Classification: A Case Study in Marathi","date":"2024-08-06","arxiv_id":"2408.03172","n_code_links":0,"syntology":null},{"paper":"/paper/training-llms-to-recognize-hedges-in","slug":"training-llms-to-recognize-hedges-in","title":"Training LLMs to Recognize Hedges in Spontaneous Narratives","date":"2024-08-06","arxiv_id":"2408.03319","n_code_links":1,"syntology":null},{"paper":"/paper/2408-02545","slug":"2408-02545","title":"RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation","date":"2024-08-05","arxiv_id":"2408.02545","n_code_links":2,"syntology":null},{"paper":null,"slug":"2408-02854","title":"Wiping out the limitations of Large Language Models -- A Taxonomy for Retrieval Augmented Generation","date":"2024-08-05","arxiv_id":"2408.02854","n_code_links":0,"syntology":null},{"paper":null,"slug":"appagent-v2-advanced-agent-for-flexible","title":"AppAgent v2: Advanced Agent for Flexible Mobile Interactions","date":"2024-08-05","arxiv_id":"2408.11824","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-agents-improve-semantic-code-search","title":"LLM Agents Improve Semantic Code Search","date":"2024-08-05","arxiv_id":"2408.11058","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01935","title":"Defining and Evaluating Decision and Composite Risk in Language Models Applied to Natural Language Inference","date":"2024-08-04","arxiv_id":"2408.01935","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01745","title":"Indexing and Visualization of Climate Change Narratives Using BERT and Causal Extraction","date":"2024-08-03","arxiv_id":"2408.01745","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01838","title":"Tracking Emotional Dynamics in Chat Conversations: A Hybrid Approach using DistilBERT and Emoji Sentiment Analysis","date":"2024-08-03","arxiv_id":"2408.01838","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-00981","title":"Cross-domain Named Entity Recognition via Graph Matching","date":"2024-08-02","arxiv_id":"2408.00981","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01107","title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning","date":"2024-08-02","arxiv_id":"2408.01107","n_code_links":0,"syntology":null},{"paper":"/paper/2408-01262","slug":"2408-01262","title":"RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework","date":"2024-08-02","arxiv_id":"2408.01262","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-advanced-llm","title":"Evaluating the Impact of Advanced LLM Techniques on AI-Lecture Tutors for a Robotics Course","date":"2024-08-02","arxiv_id":"2408.04645","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/guiding-sentiment-analysis-with-hierarchical","slug":"guiding-sentiment-analysis-with-hierarchical","title":"Guiding Sentiment Analysis with Hierarchical Text Clustering: Analyzing the German X/Twitter Discourse on Face Masks in the 2020 COVID-19 Pandemic","date":"2024-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"ontological-relations-from-word-embeddings","title":"Ontological Relations from Word Embeddings","date":"2024-08-01","arxiv_id":"2408.00444","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21276","title":"Multi-Level Querying using A Knowledge Pyramid","date":"2024-07-31","arxiv_id":"2407.21276","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21300","title":"SAKR: Enhancing Retrieval-Augmented Generation via Streaming Algorithm and K-Means Clustering","date":"2024-07-31","arxiv_id":"2407.21300","n_code_links":0,"syntology":null},{"paper":"/paper/2407-21320","slug":"2407-21320","title":"MetaOpenFOAM: an LLM-based multi-agent framework for CFD","date":"2024-07-31","arxiv_id":"2407.21320","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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["terry-cyx/metaopenfoam"],"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":"2407-21712","title":"Adaptive Retrieval-Augmented Generation for Conversational Systems","date":"2024-07-31","arxiv_id":"2407.21712","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02680","title":"Recording First-person Experiences to Build a New Type of Foundation Model","date":"2024-07-31","arxiv_id":"2408.02680","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-new-type-of-foundation-model-based-on","title":"A New Type of Foundation Model Based on Recordings of People's Emotions and Physiology","date":"2024-07-31","arxiv_id":"2408.00030","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21153","title":"Event-Arguments Extraction Corpus and Modeling using BERT for Arabic","date":"2024-07-30","arxiv_id":"2407.21153","n_code_links":0,"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":"/paper/cleft-language-image-contrastive-learning","slug":"cleft-language-image-contrastive-learning","title":"CLEFT: Language-Image Contrastive Learning with Efficient Large Language Model and Prompt Fine-Tuning","date":"2024-07-30","arxiv_id":"2407.21011","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-on-the-implementation-method-of-an","title":"A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph","date":"2024-07-29","arxiv_id":"2407.19994","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":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":"introducing-a-new-hyper-parameter-for-rag","title":"Introducing a new hyper-parameter for RAG: Context Window Utilization","date":"2024-07-29","arxiv_id":"2407.19794","n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-analysis-of-lithuanian-online","title":"Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models","date":"2024-07-29","arxiv_id":"2407.19914","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-01462","title":"Faculty Perspectives on the Potential of RAG in Computer Science Higher Education","date":"2024-07-28","arxiv_id":"2408.01462","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-genre-and-success-classification","title":"Exploring Genre and Success Classification through Song Lyrics using DistilBERT: A Fun NLP Venture","date":"2024-07-28","arxiv_id":"2407.21068","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":"farssibert-a-novel-transformer-based-model","title":"FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts","date":"2024-07-27","arxiv_id":"2407.19173","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21059","title":"Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks","date":"2024-07-26","arxiv_id":"2407.21059","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":"mistralbsm-leveraging-mistral-7b-for","title":"MistralBSM: Leveraging Mistral-7B for Vehicular Networks Misbehavior Detection","date":"2024-07-26","arxiv_id":"2407.18462","n_code_links":0,"syntology":null},{"paper":null,"slug":"reaper-reasoning-based-retrieval-planning-for","title":"REAPER: Reasoning based Retrieval Planning for Complex RAG Systems","date":"2024-07-26","arxiv_id":"2407.18553","n_code_links":0,"syntology":null},{"paper":null,"slug":"banyan-improved-representation-learning-with","title":"Banyan: Improved Representation Learning with Explicit Structure","date":"2024-07-25","arxiv_id":"2407.17771","n_code_links":0,"syntology":null},{"paper":null,"slug":"roberta-resnext-and-bilstm-with-self","title":"RoBERTa, ResNeXt and BiLSTM with self-attention: The ultimate trio for customer sentiment analysis","date":"2024-07-25","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geometry-of-queries-query-based","title":"The Geometry of Queries: Query-Based Innovations in Retrieval-Augmented Generation","date":"2024-07-25","arxiv_id":"2407.18044","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-the-interplay-of-scale-data-and","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","date":"2024-07-25","arxiv_id":"2407.21058","n_code_links":0,"syntology":null},{"paper":null,"slug":"2407-21056","title":"What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers","date":"2024-07-24","arxiv_id":"2407.21056","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comprehensive-approach-to-misspelling","title":"A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance","date":"2024-07-24","arxiv_id":"2407.17383","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-two-step-fine-tuning-pipeline-for","title":"A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks","date":"2024-07-24","arxiv_id":"2407.17284","n_code_links":0,"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":"artificial-intelligence-in-extracting","title":"Artificial Intelligence in Extracting Diagnostic Data from Dental Records","date":"2024-07-23","arxiv_id":"2407.21050","n_code_links":0,"syntology":null},{"paper":null,"slug":"lawluo-a-chinese-law-firm-co-run-by-llm","title":"LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation","date":"2024-07-23","arxiv_id":"2407.16252","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-or-long","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","date":"2024-07-23","arxiv_id":"2407.16833","n_code_links":0,"syntology":null},{"paper":null,"slug":"tookabert-a-step-forward-for-persian-nlu","title":"TookaBERT: A Step Forward for Persian NLU","date":"2024-07-23","arxiv_id":"2407.16382","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-comparison-of-video-frame","title":"An Empirical Comparison of Video Frame Sampling Methods for Multi-Modal RAG Retrieval","date":"2024-07-22","arxiv_id":"2408.03340","n_code_links":0,"syntology":null},{"paper":null,"slug":"customized-retrieval-augmented-generation-and","title":"Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QA","date":"2024-07-22","arxiv_id":"2407.15353","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/llmmap-fingerprinting-for-large-language","slug":"llmmap-fingerprinting-for-large-language","title":"LLMmap: Fingerprinting For Large Language Models","date":"2024-07-22","arxiv_id":"2407.15847","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"pointer_only":0,"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) · 7 unverified","official":{"repos":["pasquini-dario/LLMmap"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"morse-bridging-the-gap-in-cybersecurity","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","date":"2024-07-22","arxiv_id":"2407.15748","n_code_links":0,"syntology":null},{"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":null,"slug":"zzu-nlp-at-sighan-2024-dimabsa-task-aspect","title":"ZZU-NLP at SIGHAN-2024 dimABSA Task: Aspect-Based Sentiment Analysis with Coarse-to-Fine In-context Learning","date":"2024-07-22","arxiv_id":"2407.15341","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-level-multi-label-text-classification","title":"A multi-level multi-label text classification dataset of 19th century Ottoman and Russian literary and critical texts","date":"2024-07-21","arxiv_id":"2407.15136","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-00798","title":"Golden-Retriever: High-Fidelity Agentic Retrieval Augmented Generation for Industrial Knowledge Base","date":"2024-07-20","arxiv_id":"2408.00798","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-generation-of-fashion-images-using","slug":"automatic-generation-of-fashion-images-using","title":"Automatic Generation of Fashion Images using Prompting in Generative Machine Learning Models","date":"2024-07-20","arxiv_id":"2407.14944","n_code_links":1,"syntology":null},{"paper":null,"slug":"differential-privacy-of-cross-attention-with","title":"Differential Privacy of Cross-Attention with Provable Guarantee","date":"2024-07-20","arxiv_id":"2407.14717","n_code_links":0,"syntology":null},{"paper":null,"slug":"adversarial-databases-improve-success-in","title":"Adversarial Databases Improve Success in Retrieval-based Large Language Models","date":"2024-07-19","arxiv_id":"2407.14609","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatqa-2-bridging-the-gap-to-proprietary-llms","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","date":"2024-07-19","arxiv_id":"2407.14482","n_code_links":0,"syntology":null},{"paper":"/paper/conditioning-chat-gpt-for-information","slug":"conditioning-chat-gpt-for-information","title":"Unipa-GPT: Large Language Models for university-oriented QA in Italian","date":"2024-07-19","arxiv_id":"2407.14246","n_code_links":1,"syntology":null},{"paper":null,"slug":"black-box-opinion-manipulation-attacks-to","title":"Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-07-18","arxiv_id":"2407.13757","n_code_links":0,"syntology":null},{"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":"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":null,"slug":"qalam-a-multimodal-llm-for-arabic-optical","title":"Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","date":"2024-07-18","arxiv_id":"2407.13559","n_code_links":0,"syntology":null},{"paper":null,"slug":"reconstruct-the-pruned-model-without-any","title":"Reconstruct the Pruned Model without Any Retraining","date":"2024-07-18","arxiv_id":"2407.13331","n_code_links":0,"syntology":null}],"record_sha256":"148b54560c1cf196ab8e758f27512b1737b053869c4f7d46a9afb69dc6ec2cd6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}