{"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/9","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":9,"pages_in_order":71,"rows_per_page":100,"rows":[801,900],"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/8","next":"/method/wordpiece/papers/10","papers":[{"paper":"/paper/a-reality-check-on-context-utilisation-for","slug":"a-reality-check-on-context-utilisation-for","title":"A Reality Check on Context Utilisation for Retrieval-Augmented Generation","date":"2024-12-22","arxiv_id":"2412.17031","n_code_links":1,"syntology":null},{"paper":null,"slug":"alzheimerrag-multimodal-retrieval-augmented","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for PubMed articles","date":"2024-12-21","arxiv_id":"2412.16701","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-large-language-models-for-1","title":"Distilling Large Language Models for Efficient Clinical Information Extraction","date":"2024-12-21","arxiv_id":"2501.00031","n_code_links":0,"syntology":null},{"paper":null,"slug":"formal-language-knowledge-corpus-for","title":"Formal Language Knowledge Corpus for Retrieval Augmented Generation","date":"2024-12-21","arxiv_id":"2412.16689","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-cyberbullying-roles-in-social","title":"Identifying Cyberbullying Roles in Social Media","date":"2024-12-21","arxiv_id":"2412.16417","n_code_links":0,"syntology":null},{"paper":"/paper/quantum-like-contextuality-in-large-language","slug":"quantum-like-contextuality-in-large-language","title":"Quantum-Like Contextuality in Large Language Models","date":"2024-12-21","arxiv_id":"2412.16806","n_code_links":1,"syntology":null},{"paper":null,"slug":"research-on-violent-text-detection-system","title":"Research on Violent Text Detection System Based on BERT-fasttext Model","date":"2024-12-21","arxiv_id":"2412.16455","n_code_links":0,"syntology":null},{"paper":null,"slug":"timerag-boosting-llm-time-series-forecasting","title":"TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation","date":"2024-12-21","arxiv_id":"2412.16643","n_code_links":0,"syntology":null},{"paper":"/paper/towards-more-robust-retrieval-augmented","slug":"towards-more-robust-retrieval-augmented","title":"Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks","date":"2024-12-21","arxiv_id":"2412.16708","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-robustness-through-dynamic","title":"Adversarial Robustness through Dynamic Ensemble Learning","date":"2024-12-20","arxiv_id":"2412.16254","n_code_links":0,"syntology":null},{"paper":null,"slug":"decoding-linguistic-nuances-in-mental-health","title":"Decoding Linguistic Nuances in Mental Health Text Classification Using Expressive Narrative Stories","date":"2024-12-20","arxiv_id":"2412.16302","n_code_links":0,"syntology":null},{"paper":"/paper/don-t-do-rag-when-cache-augmented-generation","slug":"don-t-do-rag-when-cache-augmented-generation","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","date":"2024-12-20","arxiv_id":"2412.15605","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["hhhuang/cag"],"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":"hybgrag-hybrid-retrieval-augmented-generation","title":"HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases","date":"2024-12-20","arxiv_id":"2412.16311","n_code_links":0,"syntology":null},{"paper":"/paper/towards-interpretable-radiology-report","slug":"towards-interpretable-radiology-report","title":"Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG","date":"2024-12-20","arxiv_id":"2412.16086","n_code_links":1,"syntology":null},{"paper":"/paper/xrag-examining-the-core-benchmarking","slug":"xrag-examining-the-core-benchmarking","title":"XRAG: eXamining the Core -- Benchmarking Foundational Components in Advanced Retrieval-Augmented Generation","date":"2024-12-20","arxiv_id":"2412.15529","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["docailab/xrag"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"analysis-and-visualization-of-linguistic","title":"Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT","date":"2024-12-19","arxiv_id":"2412.14670","n_code_links":0,"syntology":null},{"paper":null,"slug":"cord-balancing-consistency-and-rank","title":"CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation","date":"2024-12-19","arxiv_id":"2412.14581","n_code_links":0,"syntology":null},{"paper":null,"slug":"decade-of-natural-language-processing-in","title":"Decade of Natural Language Processing in Chronic Pain: A Systematic Review","date":"2024-12-19","arxiv_id":"2412.15360","n_code_links":0,"syntology":null},{"paper":null,"slug":"dehallucinating-parallel-context-extension","title":"Dehallucinating Parallel Context Extension for Retrieval-Augmented Generation","date":"2024-12-19","arxiv_id":"2412.14905","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamickv-task-aware-adaptive-kv-cache","title":"DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs","date":"2024-12-19","arxiv_id":"2412.14838","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-convolutional-networks-named-entity","title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering","date":"2024-12-19","arxiv_id":"2412.14867","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-injection-via-prompt-distillation","title":"Knowledge Injection via Prompt Distillation","date":"2024-12-19","arxiv_id":"2412.14964","n_code_links":0,"syntology":null},{"paper":"/paper/pa-rag-rag-alignment-via-multi-perspective","slug":"pa-rag-rag-alignment-via-multi-perspective","title":"PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization","date":"2024-12-19","arxiv_id":"2412.14510","n_code_links":1,"syntology":null},{"paper":null,"slug":"query-pipeline-optimization-for-cancer","title":"Query pipeline optimization for cancer patient question answering systems","date":"2024-12-19","arxiv_id":"2412.14751","n_code_links":0,"syntology":null},{"paper":null,"slug":"review-then-refine-a-dynamic-framework-for","title":"Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability","date":"2024-12-19","arxiv_id":"2412.15101","n_code_links":0,"syntology":null},{"paper":null,"slug":"sketch-structured-knowledge-enhanced-text","title":"SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval","date":"2024-12-19","arxiv_id":"2412.15443","n_code_links":0,"syntology":null},{"paper":"/paper/till-the-layers-collapse-compressing-a-deep","slug":"till-the-layers-collapse-compressing-a-deep","title":"Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers","date":"2024-12-19","arxiv_id":"2412.15077","n_code_links":1,"syntology":null},{"paper":null,"slug":"visa-retrieval-augmented-generation-with","title":"VISA: Retrieval Augmented Generation with Visual Source Attribution","date":"2024-12-19","arxiv_id":"2412.14457","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-rhetorical-figure-annotation-an","slug":"enhancing-rhetorical-figure-annotation-an","title":"Enhancing Rhetorical Figure Annotation: An Ontology-Based Web Application with RAG Integration","date":"2024-12-18","arxiv_id":"2412.13799","n_code_links":1,"syntology":null},{"paper":null,"slug":"evowiki-evaluating-llms-on-evolving-knowledge","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","date":"2024-12-18","arxiv_id":"2412.13582","n_code_links":0,"syntology":null},{"paper":"/paper/farexstance-explainable-stance-detection-for","slug":"farexstance-explainable-stance-detection-for","title":"FarExStance: Explainable Stance Detection for Farsi","date":"2024-12-18","arxiv_id":"2412.14008","n_code_links":2,"syntology":null},{"paper":null,"slug":"federated-learning-and-rag-integration-a","title":"Federated Learning and RAG Integration: A Scalable Approach for Medical Large Language Models","date":"2024-12-18","arxiv_id":"2412.13720","n_code_links":0,"syntology":null},{"paper":"/paper/rag-rewardbench-benchmarking-reward-models-in","slug":"rag-rewardbench-benchmarking-reward-models-in","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","date":"2024-12-18","arxiv_id":"2412.13746","n_code_links":1,"syntology":null},{"paper":"/paper/smarter-better-faster-longer-a-modern","slug":"smarter-better-faster-longer-a-modern","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","date":"2024-12-18","arxiv_id":"2412.13663","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["answerdotai/modernbert"],"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-mapreduce-approach-to-effectively-utilize","title":"A MapReduce Approach to Effectively Utilize Long Context Information in Retrieval Augmented Language Models","date":"2024-12-17","arxiv_id":"2412.15271","n_code_links":0,"syntology":null},{"paper":"/paper/adaptations-of-ai-models-for-querying-the","slug":"adaptations-of-ai-models-for-querying-the","title":"Adaptations of AI models for querying the LandMatrix database in natural language","date":"2024-12-17","arxiv_id":"2412.12961","n_code_links":1,"syntology":null},{"paper":null,"slug":"c-fedrag-a-confidential-federated-retrieval","title":"C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System","date":"2024-12-17","arxiv_id":"2412.13163","n_code_links":0,"syntology":null},{"paper":null,"slug":"chinese-safetyqa-a-safety-short-form","title":"Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models","date":"2024-12-17","arxiv_id":"2412.15265","n_code_links":0,"syntology":null},{"paper":"/paper/exit-context-aware-extractive-compression-for","slug":"exit-context-aware-extractive-compression-for","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.12559","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-are-also-effective-embedding-models-an","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","date":"2024-12-17","arxiv_id":"2412.12591","n_code_links":0,"syntology":null},{"paper":"/paper/omnieval-an-omnidirectional-and-automatic-rag","slug":"omnieval-an-omnidirectional-and-automatic-rag","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","date":"2024-12-17","arxiv_id":"2412.13018","n_code_links":1,"syntology":null},{"paper":null,"slug":"perc-plan-as-query-example-retrieval-for","title":"PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation","date":"2024-12-17","arxiv_id":"2412.12447","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-star-enhancing-deliberative-reasoning","title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","date":"2024-12-17","arxiv_id":"2412.12881","n_code_links":0,"syntology":null},{"paper":null,"slug":"remoterag-a-privacy-preserving-llm-cloud-rag","title":"RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service","date":"2024-12-17","arxiv_id":"2412.12775","n_code_links":0,"syntology":null},{"paper":"/paper/simgrag-leveraging-similar-subgraphs-for","slug":"simgrag-leveraging-similar-subgraphs-for","title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.15272","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-external-knowledge-is-preferred-by-llms","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context","date":"2024-12-17","arxiv_id":"2412.12632","n_code_links":0,"syntology":null},{"paper":"/paper/a-benchmark-and-robustness-study-of-in","slug":"a-benchmark-and-robustness-study-of-in","title":"A Benchmark and Robustness Study of In-Context-Learning with Large Language Models in Music Entity Detection","date":"2024-12-16","arxiv_id":"2412.11851","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-mixture-of-experts-in-dense","title":"Investigating Mixture of Experts in Dense Retrieval","date":"2024-12-16","arxiv_id":"2412.11864","n_code_links":0,"syntology":null},{"paper":"/paper/look-ahead-text-understanding-and-llm","slug":"look-ahead-text-understanding-and-llm","title":"Look Ahead Text Understanding and LLM Stitching","date":"2024-12-16","arxiv_id":"2412.17836","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimized-quran-passage-retrieval-using-an","title":"Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models","date":"2024-12-16","arxiv_id":"2412.11431","n_code_links":0,"syntology":null},{"paper":"/paper/rag-playground-a-framework-for-systematic","slug":"rag-playground-a-framework-for-systematic","title":"RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems","date":"2024-12-16","arxiv_id":"2412.12322","n_code_links":1,"syntology":null},{"paper":null,"slug":"unanswerability-evaluation-for-retreival","title":"Unanswerability Evaluation for Retrieval Augmented Generation","date":"2024-12-16","arxiv_id":"2412.12300","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-contextualized-bert-model-for-knowledge","title":"A Contextualized BERT model for Knowledge Graph Completion","date":"2024-12-15","arxiv_id":"2412.11016","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-retrieval-augmented-generation","title":"Accelerating Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.15246","n_code_links":0,"syntology":null},{"paper":null,"slug":"inference-scaling-for-bridging-retrieval-and","title":"Inference Scaling for Bridging Retrieval and Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10684","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokens-the-oft-overlooked-appetizer-large","title":"Tokens, the oft-overlooked appetizer: Large language models, the distributional hypothesis, and meaning","date":"2024-12-14","arxiv_id":"2412.10924","n_code_links":0,"syntology":null},{"paper":null,"slug":"visdom-multi-document-qa-with-visually-rich","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10704","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidence-contextualization-and-counterfactual","title":"Evidence Contextualization and Counterfactual Attribution for Conversational QA over Heterogeneous Data with RAG Systems","date":"2024-12-13","arxiv_id":"2412.10571","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragserve-fast-quality-aware-rag-systems-with","title":"RAGServe: Fast Quality-Aware RAG Systems with Configuration Adaptation","date":"2024-12-13","arxiv_id":"2412.10543","n_code_links":0,"syntology":null},{"paper":null,"slug":"vlr-bench-multilingual-benchmark-dataset-for","title":"VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation","date":"2024-12-13","arxiv_id":"2412.10151","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-the-robustness-of-retrieval","title":"Assessing the Robustness of Retrieval-Augmented Generation Systems in K-12 Educational Question Answering with Knowledge Discrepancies","date":"2024-12-12","arxiv_id":"2412.08985","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-canvas-enhancing-text-to-image","title":"Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG","date":"2024-12-12","arxiv_id":"2412.09614","n_code_links":0,"syntology":null},{"paper":null,"slug":"og-rag-ontology-grounded-retrieval-augmented","title":"OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models","date":"2024-12-12","arxiv_id":"2412.15235","n_code_links":0,"syntology":null},{"paper":null,"slug":"accurate-medical-named-entity-recognition","title":"Accurate Medical Named Entity Recognition Through Specialized NLP Models","date":"2024-12-11","arxiv_id":"2412.08255","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-single-and-multi-task-text","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","date":"2024-12-11","arxiv_id":"2412.08587","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-graph-rag-and-prompt-engineering","title":"Leveraging Graph-RAG and Prompt Engineering to Enhance LLM-Based Automated Requirement Traceability and Compliance Checks","date":"2024-12-11","arxiv_id":"2412.08593","n_code_links":0,"syntology":null},{"paper":"/paper/nlpineers-nlu-of-devanagari-script-languages","slug":"nlpineers-nlu-of-devanagari-script-languages","title":"NLPineers@ NLU of Devanagari Script Languages 2025: Hate Speech Detection using Ensembling of BERT-based models","date":"2024-12-11","arxiv_id":"2412.08163","n_code_links":2,"syntology":null},{"paper":"/paper/adapting-to-non-stationary-environments-multi","slug":"adapting-to-non-stationary-environments-multi","title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","date":"2024-12-10","arxiv_id":"2412.07618","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":7,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["futureeeeee/dynamic-rag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bumblebee-foundation-model-for-particle","title":"Bumblebee: Foundation Model for Particle Physics Discovery","date":"2024-12-10","arxiv_id":"2412.07867","n_code_links":0,"syntology":null},{"paper":"/paper/can-linguists-better-understand-dna","slug":"can-linguists-better-understand-dna","title":"Can linguists better understand DNA?","date":"2024-12-10","arxiv_id":"2412.07678","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-knowledge-graphs-from-large","title":"Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT","date":"2024-12-10","arxiv_id":"2412.07412","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-as-hpc-expert-extending-rag-architecture","title":"LLM as HPC Expert: Extending RAG Architecture for HPC Data","date":"2024-12-09","arxiv_id":"2501.14733","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-multi-task-learning-for-enhanced","title":"Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models","date":"2024-12-09","arxiv_id":"2412.06249","n_code_links":0,"syntology":null},{"paper":"/paper/sirerag-indexing-similar-and-related","slug":"sirerag-indexing-similar-and-related","title":"SiReRAG: Indexing Similar and Related Information for Multihop Reasoning","date":"2024-12-09","arxiv_id":"2412.06206","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"the-rosetta-paradox-domain-specific","title":"The Rosetta Paradox: Domain-Specific Performance Inversions in Large Language Models","date":"2024-12-09","arxiv_id":"2412.17821","n_code_links":0,"syntology":null},{"paper":null,"slug":"unseen-attack-detection-in-software-defined","title":"Unseen Attack Detection in Software-Defined Networking Using a BERT-Based Large Language Model","date":"2024-12-09","arxiv_id":"2412.06239","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-collaborative-multi-agent-approach-to","title":"A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data","date":"2024-12-08","arxiv_id":"2412.05838","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixture-of-pageranks-replacing-long-context","title":"Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAG","date":"2024-12-08","arxiv_id":"2412.06078","n_code_links":0,"syntology":null},{"paper":null,"slug":"bertcaps-bert-capsule-for-persian-multi","title":"BERTCaps: BERT Capsule for Persian Multi-Domain Sentiment Analysis","date":"2024-12-07","arxiv_id":"2412.05591","n_code_links":0,"syntology":null},{"paper":"/paper/kg-retriever-efficient-knowledge-indexing-for","slug":"kg-retriever-efficient-knowledge-indexing-for","title":"KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models","date":"2024-12-07","arxiv_id":"2412.05547","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["bai-lab/kg-retriever"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"shifting-ner-into-high-gear-the-auto-adver","title":"Shifting NER into High Gear: The Auto-AdvER Approach","date":"2024-12-07","arxiv_id":"2412.05655","n_code_links":0,"syntology":null},{"paper":null,"slug":"sla-management-in-reconfigurable-multi-agent","title":"SLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering","date":"2024-12-07","arxiv_id":"2412.06832","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-graph-based-approach-for-conversational-ai","title":"TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG","date":"2024-12-06","arxiv_id":"2412.05447","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-cross-language-code-translation-via","title":"Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation","date":"2024-12-06","arxiv_id":"2412.05159","n_code_links":0,"syntology":null},{"paper":"/paper/nlp-adbench-nlp-anomaly-detection-benchmark","slug":"nlp-adbench-nlp-anomaly-detection-benchmark","title":"NLP-ADBench: NLP Anomaly Detection Benchmark","date":"2024-12-06","arxiv_id":"2412.04784","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-preserving-retrieval-augmented","title":"Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy","date":"2024-12-06","arxiv_id":"2412.04697","n_code_links":0,"syntology":null},{"paper":null,"slug":"queen-a-large-language-model-for-quechua","title":"QueEn: A Large Language Model for Quechua-English Translation","date":"2024-12-06","arxiv_id":"2412.05184","n_code_links":0,"syntology":null},{"paper":null,"slug":"addressing-hallucinations-with-rag-and-nmiss","title":"Addressing Hallucinations with RAG and NMISS in Italian Healthcare LLM Chatbots","date":"2024-12-05","arxiv_id":"2412.04235","n_code_links":0,"syntology":null},{"paper":null,"slug":"comprehensive-audio-query-handling-system","title":"Comprehensive Audio Query Handling System with Integrated Expert Models and Contextual Understanding","date":"2024-12-05","arxiv_id":"2412.03980","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-ai-text-generation-retrieval","title":"Exploring AI Text Generation, Retrieval-Augmented Generation, and Detection Technologies: a Comprehensive Overview","date":"2024-12-05","arxiv_id":"2412.03933","n_code_links":0,"syntology":null},{"paper":"/paper/heal-hierarchical-embedding-alignment-loss","slug":"heal-hierarchical-embedding-alignment-loss","title":"HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning","date":"2024-12-05","arxiv_id":"2412.04661","n_code_links":1,"syntology":null},{"paper":null,"slug":"uniform-discretized-integrated-gradients-an","title":"Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models","date":"2024-12-05","arxiv_id":"2412.03886","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-conversational-psychotherapy","title":"Advancing Conversational Psychotherapy: Integrating Privacy, Dual-Memory, and Domain Expertise with Large Language Models","date":"2024-12-04","arxiv_id":"2412.02987","n_code_links":0,"syntology":null},{"paper":null,"slug":"fanal-financial-activity-news-alerting","title":"FANAL -- Financial Activity News Alerting Language Modeling Framework","date":"2024-12-04","arxiv_id":"2412.03527","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-sentiment-analysis-based-on-bert","title":"Multimodal Sentiment Analysis Based on BERT and ResNet","date":"2024-12-04","arxiv_id":"2412.03625","n_code_links":0,"syntology":null},{"paper":null,"slug":"achieving-semantic-consistency-using-bert","title":"Achieving Semantic Consistency: Contextualized Word Representations for Political Text Analysis","date":"2024-12-03","arxiv_id":"2412.04505","n_code_links":0,"syntology":null},{"paper":null,"slug":"caisson-concept-augmented-inference-suite-of","title":"CAISSON: Concept-Augmented Inference Suite of Self-Organizing Neural Networks","date":"2024-12-03","arxiv_id":"2412.02835","n_code_links":0,"syntology":null},{"paper":null,"slug":"cptquant-a-novel-mixed-precision-post","title":"CPTQuant -- A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models","date":"2024-12-03","arxiv_id":"2412.03599","n_code_links":0,"syntology":null},{"paper":"/paper/gracefully-filtering-backdoor-samples-for","slug":"gracefully-filtering-backdoor-samples-for","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","date":"2024-12-03","arxiv_id":"2412.02454","n_code_links":1,"syntology":null},{"paper":"/paper/ocr-hinders-rag-evaluating-the-cascading","slug":"ocr-hinders-rag-evaluating-the-cascading","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","date":"2024-12-03","arxiv_id":"2412.02592","n_code_links":1,"syntology":null}],"record_sha256":"e52a48b749a7aba6b27694180d8d3d364bc86ededcba0c40d4a41bfc0bb9eeeb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}