{"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/5","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":5,"pages_in_order":71,"rows_per_page":100,"rows":[401,500],"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/4","next":"/method/wordpiece/papers/6","papers":[{"paper":"/paper/towards-lighter-and-robust-evaluation-for","slug":"towards-lighter-and-robust-evaluation-for","title":"Towards Lighter and Robust Evaluation for Retrieval Augmented Generation","date":"2025-03-20","arxiv_id":"2503.16161","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":["razvanip13/towards_lighter_and_robust_evaluation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/tuning-llms-by-rag-principles-towards-llm","slug":"tuning-llms-by-rag-principles-towards-llm","title":"Tuning LLMs by RAG Principles: Towards LLM-native Memory","date":"2025-03-20","arxiv_id":"2503.16071","n_code_links":1,"syntology":null},{"paper":"/paper/typed-rag-type-aware-multi-aspect","slug":"typed-rag-type-aware-multi-aspect","title":"Typed-RAG: Type-aware Multi-Aspect Decomposition for Non-Factoid Question Answering","date":"2025-03-20","arxiv_id":"2503.15879","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-pancreatic-cancer-staging-with","title":"Enhancing Pancreatic Cancer Staging with Large Language Models: The Role of Retrieval-Augmented Generation","date":"2025-03-19","arxiv_id":"2503.15664","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-bias-in-retrieval-augmented","title":"Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems","date":"2025-03-19","arxiv_id":"2503.15454","n_code_links":0,"syntology":null},{"paper":"/paper/optimizing-retrieval-strategies-for-financial","slug":"optimizing-retrieval-strategies-for-financial","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","date":"2025-03-19","arxiv_id":"2503.15191","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":["seohyunwoo-0407/gar"],"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":"rag-based-user-profiling-for-precision","title":"RAG-based User Profiling for Precision Planning in Mixed-precision Over-the-Air Federated Learning","date":"2025-03-19","arxiv_id":"2503.15569","n_code_links":0,"syntology":null},{"paper":null,"slug":"shushing-let-s-imagine-an-authentic-speech","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","date":"2025-03-19","arxiv_id":"2503.14928","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-llm-generation-with-knowledge","title":"Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine","date":"2025-03-18","arxiv_id":"2503.16530","n_code_links":0,"syntology":null},{"paper":null,"slug":"good-evil-reputation-judgment-of-celebrities","title":"Good/Evil Reputation Judgment of Celebrities by LLMs via Retrieval Augmented Generation","date":"2025-03-18","arxiv_id":"2503.14382","n_code_links":0,"syntology":null},{"paper":"/paper/judge-benchmarking-judgment-document","slug":"judge-benchmarking-judgment-document","title":"JuDGE: Benchmarking Judgment Document Generation for Chinese Legal System","date":"2025-03-18","arxiv_id":"2503.14258","n_code_links":1,"syntology":null},{"paper":null,"slug":"kg-irag-a-knowledge-graph-based-iterative","title":"Beyond Single Pass, Looping Through Time: KG-IRAG with Iterative Knowledge Retrieval","date":"2025-03-18","arxiv_id":"2503.14234","n_code_links":0,"syntology":null},{"paper":"/paper/mdocagent-a-multi-modal-multi-agent-framework","slug":"mdocagent-a-multi-modal-multi-agent-framework","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","date":"2025-03-18","arxiv_id":"2503.13964","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aiming-lab/mdocagent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mok-rag-mixture-of-knowledge-paths-enhanced","title":"MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environments","date":"2025-03-18","arxiv_id":"2503.13882","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-human-choice-between-textually","title":"Predicting Human Choice Between Textually Described Lotteries","date":"2025-03-18","arxiv_id":"2503.14004","n_code_links":0,"syntology":null},{"paper":"/paper/rago-systematic-performance-optimization-for","slug":"rago-systematic-performance-optimization-for","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","date":"2025-03-18","arxiv_id":"2503.14649","n_code_links":1,"syntology":null},{"paper":"/paper/mes-rag-bringing-multi-modal-entity-storage","slug":"mes-rag-bringing-multi-modal-entity-storage","title":"MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG","date":"2025-03-17","arxiv_id":"2503.13563","n_code_links":1,"syntology":null},{"paper":null,"slug":"oscar-online-soft-compression-and-reranking","title":"OSCAR: Online Soft Compression And Reranking","date":"2025-03-17","arxiv_id":"2504.07109","n_code_links":0,"syntology":null},{"paper":"/paper/pause-low-latency-and-privacy-aware-active","slug":"pause-low-latency-and-privacy-aware-active","title":"PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning","date":"2025-03-17","arxiv_id":"2503.13173","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-aware-rag-secure-and-isolated","title":"Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval","date":"2025-03-17","arxiv_id":"2503.15548","n_code_links":0,"syntology":null},{"paper":null,"slug":"grapheval-a-lightweight-graph-based-llm","title":"GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation","date":"2025-03-16","arxiv_id":"2503.12600","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-matters-multimodal-features-for","title":"Semantic Matters: Multimodal Features for Affective Analysis","date":"2025-03-16","arxiv_id":"2504.11460","n_code_links":0,"syntology":null},{"paper":null,"slug":"integrating-chain-of-thought-and-retrieval","title":"Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes","date":"2025-03-15","arxiv_id":"2503.12286","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-for-automated-classification","title":"Language Models for Automated Classification of Brain MRI Reports and Growth Chart Generation","date":"2025-03-15","arxiv_id":"2503.12143","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-kg-il-a-multi-agent-hybrid-framework-for","title":"RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration","date":"2025-03-14","arxiv_id":"2503.13514","n_code_links":0,"syntology":null},{"paper":"/paper/relevance-isn-t-all-you-need-scaling-rag","slug":"relevance-isn-t-all-you-need-scaling-rag","title":"Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking","date":"2025-03-14","arxiv_id":"2504.07104","n_code_links":2,"syntology":null},{"paper":null,"slug":"semantic-and-contextual-modeling-for","title":"Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM","date":"2025-03-14","arxiv_id":"2503.11084","n_code_links":0,"syntology":null},{"paper":null,"slug":"arled-leveraging-led-based-arman-model-for","title":"ARLED: Leveraging LED-based ARMAN Model for Abstractive Summarization of Persian Long Documents","date":"2025-03-13","arxiv_id":"2503.10233","n_code_links":0,"syntology":null},{"paper":null,"slug":"attentionrag-attention-guided-context-pruning","title":"AttentionRAG: Attention-Guided Context Pruning in Retrieval-Augmented Generation","date":"2025-03-13","arxiv_id":"2503.10720","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-mental-llm-leveraging-reasoning-in","slug":"cognitive-mental-llm-leveraging-reasoning-in","title":"Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text","date":"2025-03-13","arxiv_id":"2503.10095","n_code_links":1,"syntology":null},{"paper":"/paper/fg-rag-enhancing-query-focused-summarization","slug":"fg-rag-enhancing-query-focused-summarization","title":"FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAG","date":"2025-03-13","arxiv_id":"2504.07103","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-stock-movement-with-bertweet-and","title":"Predicting Stock Movement with BERTweet and Transformers","date":"2025-03-13","arxiv_id":"2503.10957","n_code_links":0,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-with-1","slug":"retrieval-augmented-generation-with-1","title":"Retrieval-Augmented Generation with Hierarchical Knowledge","date":"2025-03-13","arxiv_id":"2503.10150","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["hhy-huang/HiRAG"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"taxonomic-reasoning-for-rare-arthropods","title":"Taxonomic Reasoning for Rare Arthropods: Combining Dense Image Captioning and RAG for Interpretable Classification","date":"2025-03-13","arxiv_id":"2503.10886","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-evaluation-of-llms-for-detecting-harmful","title":"An Evaluation of LLMs for Detecting Harmful Computing Terms","date":"2025-03-12","arxiv_id":"2503.09341","n_code_links":0,"syntology":null},{"paper":null,"slug":"claimtrust-propagation-trust-scoring-for-rag","title":"ClaimTrust: Propagation Trust Scoring for RAG Systems","date":"2025-03-12","arxiv_id":"2503.10702","n_code_links":0,"syntology":null},{"paper":"/paper/conversational-gold-evaluating-personalized","slug":"conversational-gold-evaluating-personalized","title":"Conversational Gold: Evaluating Personalized Conversational Search System using Gold Nuggets","date":"2025-03-12","arxiv_id":"2503.09902","n_code_links":1,"syntology":null},{"paper":null,"slug":"deepinnovation-ai-a-global-dataset-mapping","title":"A Global Dataset Mapping the AI Innovation from Academic Research to Industrial Patents","date":"2025-03-12","arxiv_id":"2503.09257","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-protect-yourself-from-5g-radiation","slug":"how-to-protect-yourself-from-5g-radiation","title":"How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformation","date":"2025-03-12","arxiv_id":"2503.09598","n_code_links":1,"syntology":null},{"paper":null,"slug":"memory-enhanced-retrieval-augmentation-for","title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","date":"2025-03-12","arxiv_id":"2503.09149","n_code_links":0,"syntology":null},{"paper":"/paper/moc-mixtures-of-text-chunking-learners-for","slug":"moc-mixtures-of-text-chunking-learners-for","title":"MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System","date":"2025-03-12","arxiv_id":"2503.09600","n_code_links":1,"syntology":null},{"paper":"/paper/search-r1-training-llms-to-reason-and","slug":"search-r1-training-llms-to-reason-and","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","date":"2025-03-12","arxiv_id":"2503.09516","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["petergriffinjin/search-r1"],"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","unlocated"]}}},{"paper":null,"slug":"a-grey-box-text-attack-framework-using","title":"A Grey-box Text Attack Framework using Explainable AI","date":"2025-03-11","arxiv_id":"2503.08226","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-knowledge-oriented-retrieval","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","date":"2025-03-11","arxiv_id":"2503.10677","n_code_links":0,"syntology":null},{"paper":null,"slug":"esnlir-a-spanish-multi-genre-dataset-with","title":"ESNLIR: A Spanish Multi-Genre Dataset with Causal Relationships","date":"2025-03-11","arxiv_id":"2503.08803","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-corroborating-and-refuting-evidence","title":"LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification","date":"2025-03-11","arxiv_id":"2503.07937","n_code_links":0,"syntology":null},{"paper":null,"slug":"openrag-optimizing-rag-end-to-end-via-in","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","date":"2025-03-11","arxiv_id":"2503.08398","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-longformer-based-framework-for-accurate-and","title":"A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization","date":"2025-03-10","arxiv_id":"2503.06888","n_code_links":0,"syntology":null},{"paper":null,"slug":"ctrlrag-black-box-adversarial-attacks-based","title":"CtrlRAG: Black-box Adversarial Attacks Based on Masked Language Models in Retrieval-Augmented Language Generation","date":"2025-03-10","arxiv_id":"2503.06950","n_code_links":0,"syntology":null},{"paper":null,"slug":"talking-to-gdelt-through-knowledge-graphs","title":"Talking to GDELT Through Knowledge Graphs","date":"2025-03-10","arxiv_id":"2503.07584","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-cognition-inspired-rag-with-knowledge","title":"Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving","date":"2025-03-09","arxiv_id":"2503.06567","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-emotion-recognition-and-sentiment","title":"Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts","date":"2025-03-09","arxiv_id":"2503.06805","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-delta-parameters-as-jpeg-images-data","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","date":"2025-03-09","arxiv_id":"2503.06676","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-free-from-mmi-a-new-frontier-in","slug":"breaking-free-from-mmi-a-new-frontier-in","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","date":"2025-03-08","arxiv_id":"2503.06202","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jugechengzi/Rationalization-N2R"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/constructions-are-revealed-in-word","slug":"constructions-are-revealed-in-word","title":"Constructions are Revealed in Word Distributions","date":"2025-03-08","arxiv_id":"2503.06048","n_code_links":1,"syntology":null},{"paper":null,"slug":"poisoned-mrag-knowledge-poisoning-attacks-to","title":"Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation","date":"2025-03-08","arxiv_id":"2503.06254","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-open-source-large-language-models","title":"Evaluating open-source Large Language Models for automated fact-checking","date":"2025-03-07","arxiv_id":"2503.05565","n_code_links":0,"syntology":null},{"paper":null,"slug":"fmt-a-multimodal-pneumonia-detection-model","title":"FMT:A Multimodal Pneumonia Detection Model Based on Stacking MOE Framework","date":"2025-03-07","arxiv_id":"2503.05626","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-approximate-caching-for-faster","title":"Leveraging Approximate Caching for Faster Retrieval-Augmented Generation","date":"2025-03-07","arxiv_id":"2503.05530","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-semantic-type-dependencies-for","title":"Leveraging Semantic Type Dependencies for Clinical Named Entity Recognition","date":"2025-03-07","arxiv_id":"2503.05373","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-the-robustness-of-retrieval","title":"Quantifying the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","date":"2025-03-07","arxiv_id":"2503.05587","n_code_links":0,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-search","slug":"r1-searcher-incentivizing-the-search","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05592","n_code_links":5,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"beyond-rag-task-aware-kv-cache-compression","title":"Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning","date":"2025-03-06","arxiv_id":"2503.04973","n_code_links":0,"syntology":null},{"paper":null,"slug":"collapse-of-dense-retrievers-short-early-and","title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","date":"2025-03-06","arxiv_id":"2503.05037","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-depth-analysis-of-graph-based-rag-in-a","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","date":"2025-03-06","arxiv_id":"2503.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"incentivizing-multi-tenant-split-federated","title":"Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge","date":"2025-03-06","arxiv_id":"2503.04971","n_code_links":0,"syntology":null},{"paper":"/paper/can-frontier-llms-replace-annotators-in","slug":"can-frontier-llms-replace-annotators-in","title":"Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions","date":"2025-03-05","arxiv_id":"2503.03261","n_code_links":1,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning","title":"Intermediate-Task Transfer Learning: Leveraging Sarcasm Detection for Stance Detection","date":"2025-03-05","arxiv_id":"2503.03172","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-finance-estimating","title":"Large language models in finance : what is financial sentiment?","date":"2025-03-05","arxiv_id":"2503.03612","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-federated-fine-tuning-for","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","date":"2025-03-05","arxiv_id":"2503.03920","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarcasm-detection-as-a-catalyst-improving","title":"Sarcasm Detection as a Catalyst: Improving Stance Detection with Cross-Target Capabilities","date":"2025-03-05","arxiv_id":"2503.03787","n_code_links":0,"syntology":null},{"paper":"/paper/the-box-is-in-the-pen-evaluating-commonsense-1","slug":"the-box-is-in-the-pen-evaluating-commonsense-1","title":"The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation","date":"2025-03-05","arxiv_id":"2503.03308","n_code_links":1,"syntology":null},{"paper":null,"slug":"llave-large-language-and-vision-embedding","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","date":"2025-03-04","arxiv_id":"2503.04812","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-open-domain-question-answering","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","date":"2025-03-04","arxiv_id":"2503.02922","n_code_links":0,"syntology":null},{"paper":null,"slug":"pennylang-pioneering-llm-based-quantum-code","title":"PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset","date":"2025-03-04","arxiv_id":"2503.02497","n_code_links":0,"syntology":null},{"paper":"/paper/wikipedia-in-the-era-of-llms-evolution-and","slug":"wikipedia-in-the-era-of-llms-evolution-and","title":"Wikipedia in the Era of LLMs: Evolution and Risks","date":"2025-03-04","arxiv_id":"2503.02879","n_code_links":1,"syntology":null},{"paper":null,"slug":"2503-01394","title":"Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election","date":"2025-03-03","arxiv_id":"2503.01394","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01713","title":"SAGE: A Framework of Precise Retrieval for RAG","date":"2025-03-03","arxiv_id":"2503.01713","n_code_links":0,"syntology":null},{"paper":null,"slug":"boolean-aware-attention-for-dense-retrieval","title":"Boolean-aware Attention for Dense Retrieval","date":"2025-03-03","arxiv_id":"2503.01753","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-or-powerful-trade-offs-between","title":"Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media","date":"2025-03-03","arxiv_id":"2503.01082","n_code_links":0,"syntology":null},{"paper":"/paper/hoh-a-dynamic-benchmark-for-evaluating-the","slug":"hoh-a-dynamic-benchmark-for-evaluating-the","title":"HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation","date":"2025-03-03","arxiv_id":"2503.04800","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":"/paper/retrieval-augmented-perception-high","slug":"retrieval-augmented-perception-high","title":"Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG","date":"2025-03-03","arxiv_id":"2503.01222","n_code_links":1,"syntology":null},{"paper":"/paper/seper-measure-retrieval-utility-through-the","slug":"seper-measure-retrieval-utility-through-the","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","date":"2025-03-03","arxiv_id":"2503.01478","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sepermetric/seper"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"srag-structured-retrieval-augmented","title":"SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph","date":"2025-03-03","arxiv_id":"2503.01346","n_code_links":0,"syntology":null},{"paper":null,"slug":"er-rag-enhance-rag-with-er-based-unified","title":"ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources","date":"2025-03-02","arxiv_id":"2504.06271","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-multi-hop-document-retrieval","title":"Optimizing Multi-Hop Document Retrieval Through Intermediate Representations","date":"2025-03-02","arxiv_id":"2503.04796","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-00309","title":"Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM","date":"2025-03-01","arxiv_id":"2503.00309","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-00596","title":"BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge","date":"2025-03-01","arxiv_id":"2503.00596","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-multi-stage-bert-fusion","title":"Hierarchical Multi-Stage BERT Fusion Framework with Dual Attention for Enhanced Cyberbullying Detection in Social Media","date":"2025-03-01","arxiv_id":"2503.00342","n_code_links":0,"syntology":null},{"paper":"/paper/u-niah-unified-rag-and-llm-evaluation-for","slug":"u-niah-unified-rag-and-llm-evaluation-for","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","date":"2025-03-01","arxiv_id":"2503.00353","n_code_links":1,"syntology":null},{"paper":"/paper/2503-00211","slug":"2503-00211","title":"SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models","date":"2025-02-28","arxiv_id":"2503.00211","n_code_links":1,"syntology":null},{"paper":null,"slug":"ext2gen-alignment-through-unified-extraction","title":"Ext2Gen: Alignment through Unified Extraction and Generation for Robust Retrieval-Augmented Generation","date":"2025-02-28","arxiv_id":"2503.04789","n_code_links":0,"syntology":null},{"paper":"/paper/lexrag-benchmarking-retrieval-augmented","slug":"lexrag-benchmarking-retrieval-augmented","title":"LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation","date":"2025-02-28","arxiv_id":"2502.20640","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-for-topic","title":"Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration","date":"2025-02-28","arxiv_id":"2502.20963","n_code_links":0,"syntology":null},{"paper":"/paper/ruccod-towards-automated-icd-coding-in","slug":"ruccod-towards-automated-icd-coding-in","title":"RuCCoD: Towards Automated ICD Coding in Russian","date":"2025-02-28","arxiv_id":"2502.21263","n_code_links":1,"syntology":null},{"paper":null,"slug":"superrag-beyond-rag-with-layout-aware-graph","title":"SuperRAG: Beyond RAG with Layout-Aware Graph Modeling","date":"2025-02-28","arxiv_id":"2503.04790","n_code_links":0,"syntology":null},{"paper":null,"slug":"telerag-efficient-retrieval-augmented","title":"TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval","date":"2025-02-28","arxiv_id":"2502.20969","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-rag-paradox-a-black-box-attack-exploiting","title":"The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems","date":"2025-02-28","arxiv_id":"2502.20995","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-deep-learning-techniques-for","title":"Advanced Deep Learning Techniques for Analyzing Earnings Call Transcripts: Methodologies and Applications","date":"2025-02-27","arxiv_id":"2503.01886","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-features-to-improve-the","title":"An exploration of features to improve the generalisability of fake news detection models","date":"2025-02-27","arxiv_id":"2502.20299","n_code_links":0,"syntology":null}],"record_sha256":"74cabe6e210b07838ddbfd9459d2e5d94a32a606ce5e4cd76ad008b4b4b68260","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}