{"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/13","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":13,"pages_in_order":71,"rows_per_page":100,"rows":[1201,1300],"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/12","next":"/method/wordpiece/papers/14","papers":[{"paper":"/paper/swiftkv-fast-prefill-optimized-inference-with","slug":"swiftkv-fast-prefill-optimized-inference-with","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","date":"2024-10-04","arxiv_id":"2410.03960","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-linguistically-aware-and-language","title":"Towards Linguistically-Aware and Language-Independent Tokenization for Large Language Models (LLMs)","date":"2024-10-04","arxiv_id":"2410.03568","n_code_links":0,"syntology":null},{"paper":"/paper/variational-language-concepts-for","slug":"variational-language-concepts-for","title":"Variational Language Concepts for Interpreting Foundation Language Models","date":"2024-10-04","arxiv_id":"2410.03964","n_code_links":1,"syntology":null},{"paper":"/paper/vulnerability-detection-via-topological","slug":"vulnerability-detection-via-topological","title":"Vulnerability Detection via Topological Analysis of Attention Maps","date":"2024-10-04","arxiv_id":"2410.03470","n_code_links":1,"syntology":null},{"paper":"/paper/ward-provable-rag-dataset-inference-via-llm","slug":"ward-provable-rag-dataset-inference-via-llm","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","date":"2024-10-04","arxiv_id":"2410.03537","n_code_links":0,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"a-comprehensive-survey-of-retrieval-augmented","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","date":"2024-10-03","arxiv_id":"2410.12837","n_code_links":0,"syntology":null},{"paper":"/paper/controlled-generation-of-natural-adversarial","slug":"controlled-generation-of-natural-adversarial","title":"Adversarial Decoding: Generating Readable Documents for Adversarial Objectives","date":"2024-10-03","arxiv_id":"2410.02163","n_code_links":1,"syntology":null},{"paper":null,"slug":"domain-specific-retrieval-augmented","title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","date":"2024-10-03","arxiv_id":"2410.02721","n_code_links":0,"syntology":null},{"paper":"/paper/helmet-how-to-evaluate-long-context-language","slug":"helmet-how-to-evaluate-long-context-language","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","date":"2024-10-03","arxiv_id":"2410.02694","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["princeton-nlp/helmet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-much-can-rag-help-the-reasoning-of-llm","title":"How Much Can RAG Help the Reasoning of LLM?","date":"2024-10-03","arxiv_id":"2410.02338","n_code_links":0,"syntology":null},{"paper":null,"slug":"indicsenteval-how-effectively-do-multilingual","title":"IndicSentEval: How Effectively do Multilingual Transformer Models encode Linguistic Properties for Indic Languages?","date":"2024-10-03","arxiv_id":"2410.02611","n_code_links":0,"syntology":null},{"paper":null,"slug":"intrinsic-evaluation-of-rag-systems-for-deep","title":"Intrinsic Evaluation of RAG Systems for Deep-Logic Questions","date":"2024-10-03","arxiv_id":"2410.02932","n_code_links":0,"syntology":null},{"paper":"/paper/l-citeeval-do-long-context-models-truly","slug":"l-citeeval-do-long-context-models-truly","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","date":"2024-10-03","arxiv_id":"2410.02115","n_code_links":2,"syntology":null},{"paper":null,"slug":"morphological-evaluation-of-subwords","title":"Morphological evaluation of subwords vocabulary used by BETO language model","date":"2024-10-03","arxiv_id":"2410.02283","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-rag-enhancing-rag-with-reward-driven","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","date":"2024-10-03","arxiv_id":"2410.03780","n_code_links":0,"syntology":null},{"paper":null,"slug":"uncertaintyrag-span-level-uncertainty","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","date":"2024-10-03","arxiv_id":"2410.02719","n_code_links":0,"syntology":null},{"paper":"/paper/bordirlines-a-dataset-for-evaluating-cross","slug":"bordirlines-a-dataset-for-evaluating-cross","title":"BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation","date":"2024-10-02","arxiv_id":"2410.01171","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["manestay/bordirlines"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emotion-aware-response-generation-using","title":"Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation","date":"2024-10-02","arxiv_id":"2410.01306","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-retrieval-in-qa-systems-with","slug":"enhancing-retrieval-in-qa-systems-with","title":"Enhancing Retrieval in QA Systems with Derived Feature Association","date":"2024-10-02","arxiv_id":"2410.03754","n_code_links":1,"syntology":null},{"paper":null,"slug":"financial-sentiment-analysis-on-news-and","title":"Financial Sentiment Analysis on News and Reports Using Large Language Models and FinBERT","date":"2024-10-02","arxiv_id":"2410.01987","n_code_links":0,"syntology":null},{"paper":"/paper/open-rag-enhanced-retrieval-augmented","slug":"open-rag-enhanced-retrieval-augmented","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","date":"2024-10-02","arxiv_id":"2410.01782","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-speech-recognition-with-pre","slug":"end-to-end-speech-recognition-with-pre","title":"End-to-End Speech Recognition with Pre-trained Masked Language Model","date":"2024-10-01","arxiv_id":"2410.00528","n_code_links":1,"syntology":null},{"paper":"/paper/optimizing-and-evaluating-enterprise","slug":"optimizing-and-evaluating-enterprise","title":"Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective","date":"2024-10-01","arxiv_id":"2410.12812","n_code_links":1,"syntology":null},{"paper":null,"slug":"quantifying-reliance-on-external-information","title":"Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis","date":"2024-10-01","arxiv_id":"2410.00857","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-methodology-for-explainable-large-language","title":"A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification","date":"2024-09-30","arxiv_id":"2410.00250","n_code_links":0,"syntology":null},{"paper":null,"slug":"bsharedrag-backbone-shared-retrieval","title":"BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain","date":"2024-09-30","arxiv_id":"2409.20075","n_code_links":0,"syntology":null},{"paper":null,"slug":"depression-detection-in-social-media-posts-1","title":"Depression detection in social media posts using transformer-based models and auxiliary features","date":"2024-09-30","arxiv_id":"2409.20048","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-the-fairness-of-task-adaptive","slug":"evaluating-the-fairness-of-task-adaptive","title":"Evaluating the fairness of task-adaptive pretraining on unlabeled test data before few-shot text classification","date":"2024-09-30","arxiv_id":"2410.00179","n_code_links":1,"syntology":null},{"paper":null,"slug":"ingest-and-ground-dispelling-hallucinations","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","date":"2024-09-30","arxiv_id":"2410.02825","n_code_links":0,"syntology":null},{"paper":"/paper/qaencoder-towards-aligned-representation","slug":"qaencoder-towards-aligned-representation","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering System","date":"2024-09-30","arxiv_id":"2409.20434","n_code_links":1,"syntology":null},{"paper":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pear-position-embedding-agnostic-attention-re","title":"PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead","date":"2024-09-29","arxiv_id":"2409.19745","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-federated-intrusion-detection-in-5g","slug":"efficient-federated-intrusion-detection-in-5g","title":"Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model","date":"2024-09-28","arxiv_id":"2409.19390","n_code_links":1,"syntology":null},{"paper":"/paper/insightbuddy-ai-medication-extraction-and","slug":"insightbuddy-ai-medication-extraction-and","title":"INSIGHTBUDDY-AI: Medication Extraction and Entity Linking using Large Language Models and Ensemble Learning","date":"2024-09-28","arxiv_id":"2409.19467","n_code_links":2,"syntology":null},{"paper":null,"slug":"aipatient-simulating-patients-with-ehrs-and","title":"AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow","date":"2024-09-27","arxiv_id":"2409.18924","n_code_links":0,"syntology":null},{"paper":"/paper/cottention-linear-transformers-with-cosine","slug":"cottention-linear-transformers-with-cosine","title":"Cottention: Linear Transformers With Cosine Attention","date":"2024-09-27","arxiv_id":"2409.18747","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gmongaras/Cottention_Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"experimental-evaluation-of-machine-learning","title":"Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture","date":"2024-09-27","arxiv_id":"2409.18568","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-rtl-reinforcement-based-meta-transfer","title":"Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoning","date":"2024-09-27","arxiv_id":"2409.19075","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-source-hard-and-soft-information-fusion","title":"Multi-Source Hard and Soft Information Fusion Approach for Accurate Cryptocurrency Price Movement Prediction","date":"2024-09-27","arxiv_id":"2409.18895","n_code_links":0,"syntology":null},{"paper":null,"slug":"suicide-phenotyping-from-clinical-notes-in","title":"Suicide Phenotyping from Clinical Notes in Safety-Net Psychiatric Hospital Using Multi-Label Classification with Pre-Trained Language Models","date":"2024-09-27","arxiv_id":"2409.18878","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-unidirectional-bidirectional-and","title":"Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code","date":"2024-09-26","arxiv_id":"2409.17513","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-in-domain-question-answering-for","title":"Efficient In-Domain Question Answering for Resource-Constrained Environments","date":"2024-09-26","arxiv_id":"2409.17648","n_code_links":0,"syntology":null},{"paper":null,"slug":"embodied-rag-general-non-parametric-embodied","title":"Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation","date":"2024-09-26","arxiv_id":"2409.18313","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-tourism-recommender-systems-for","title":"Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation","date":"2024-09-26","arxiv_id":"2409.18003","n_code_links":0,"syntology":null},{"paper":"/paper/multiclimate-multimodal-stance-detection-on","slug":"multiclimate-multimodal-stance-detection-on","title":"MultiClimate: Multimodal Stance Detection on Climate Change Videos","date":"2024-09-26","arxiv_id":"2409.18346","n_code_links":1,"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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["werywjw/multiclimate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"predicting-anchored-text-from-translation","title":"Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods","date":"2024-09-26","arxiv_id":"2409.17939","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-prompting-based-representation-learning","title":"A Prompting-Based Representation Learning Method for Recommendation with Large Language Models","date":"2024-09-25","arxiv_id":"2409.16674","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-and-machine-learning-advancing","title":"Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Handy Appetizer","date":"2024-09-25","arxiv_id":"2409.17120","n_code_links":0,"syntology":null},{"paper":null,"slug":"llama-sciq-an-educational-chatbot-for","title":"LLaMa-SciQ: An Educational Chatbot for Answering Science MCQ","date":"2024-09-25","arxiv_id":"2409.16779","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-stationary-bert-exploring-augmented-imu","title":"Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition","date":"2024-09-25","arxiv_id":"2409.16730","n_code_links":0,"syntology":null},{"paper":"/paper/controlling-risk-of-retrieval-augmented","slug":"controlling-risk-of-retrieval-augmented","title":"Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework","date":"2024-09-24","arxiv_id":"2409.16146","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ict-bigdatalab/rc-rag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"from-pixels-to-words-leveraging","title":"From Pixels to Words: Leveraging Explainability in Face Recognition through Interactive Natural Language Processing","date":"2024-09-24","arxiv_id":"2409.16089","n_code_links":0,"syntology":null},{"paper":"/paper/irsc-a-zero-shot-evaluation-benchmark-for","slug":"irsc-a-zero-shot-evaluation-benchmark-for","title":"IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios","date":"2024-09-24","arxiv_id":"2409.15763","n_code_links":1,"syntology":null},{"paper":null,"slug":"lighter-and-better-towards-flexible-context","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","date":"2024-09-24","arxiv_id":"2409.15699","n_code_links":0,"syntology":null},{"paper":null,"slug":"spelling-correction-through-rewriting-of-non","title":"Spelling Correction through Rewriting of Non-Autoregressive ASR Lattices","date":"2024-09-24","arxiv_id":"2409.16469","n_code_links":0,"syntology":null},{"paper":null,"slug":"swiftdossier-tailored-automatic-dossier-for","title":"SwiftDossier: Tailored Automatic Dossier for Drug Discovery with LLMs and Agents","date":"2024-09-24","arxiv_id":"2409.15817","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-scientific-reproducibility-through","title":"Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications","date":"2024-09-23","arxiv_id":"2409.15076","n_code_links":0,"syntology":null},{"paper":null,"slug":"gem-rag-graphical-eigen-memories-for","title":"GEM-RAG: Graphical Eigen Memories For Retrieval Augmented Generation","date":"2024-09-23","arxiv_id":"2409.15566","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-ai-is-not-ready-for-clinical-use","title":"Generative AI Is Not Ready for Clinical Use in Patient Education for Lower Back Pain Patients, Even With Retrieval-Augmented Generation","date":"2024-09-23","arxiv_id":"2409.15260","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-academic-skills-assessment-with-nlp","title":"Improving Academic Skills Assessment with NLP and Ensemble Learning","date":"2024-09-23","arxiv_id":"2409.19013","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-when-to-retrieve-what-to-rewrite-and","title":"Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA","date":"2024-09-23","arxiv_id":"2409.15515","n_code_links":0,"syntology":null},{"paper":null,"slug":"lessons-learned-on-information-retrieval-in","title":"Lessons Learned on Information Retrieval in Electronic Health Records: A Comparison of Embedding Models and Pooling Strategies","date":"2024-09-23","arxiv_id":"2409.15163","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-rag-and-beyond","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","date":"2024-09-23","arxiv_id":"2409.14924","n_code_links":0,"syntology":null},{"paper":"/paper/j2n-nominal-adjective-identification-and-its","slug":"j2n-nominal-adjective-identification-and-its","title":"J2N -- Nominal Adjective Identification and its Application","date":"2024-09-22","arxiv_id":"2409.14374","n_code_links":1,"syntology":null},{"paper":null,"slug":"2409-13992","title":"SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval","date":"2024-09-21","arxiv_id":"2409.13992","n_code_links":0,"syntology":null},{"paper":null,"slug":"2409-14097","title":"Probing Context Localization of Polysemous Words in Pre-trained Language Model Sub-Layers","date":"2024-09-21","arxiv_id":"2409.14097","n_code_links":0,"syntology":null},{"paper":null,"slug":"2409-14168","title":"Towards Building Efficient Sentence BERT Models using Layer Pruning","date":"2024-09-21","arxiv_id":"2409.14168","n_code_links":0,"syntology":null},{"paper":"/paper/2409-14175","slug":"2409-14175","title":"QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling","date":"2024-09-21","arxiv_id":"2409.14175","n_code_links":1,"syntology":null},{"paper":null,"slug":"drift-to-remember","title":"Drift to Remember","date":"2024-09-21","arxiv_id":"2409.13997","n_code_links":0,"syntology":null},{"paper":"/paper/2409-13385","slug":"2409-13385","title":"Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey","date":"2024-09-20","arxiv_id":"2409.13385","n_code_links":1,"syntology":null},{"paper":null,"slug":"applying-pre-trained-multilingual-bert-in","title":"Applying Pre-trained Multilingual BERT in Embeddings for Improved Malicious Prompt Injection Attacks Detection","date":"2024-09-20","arxiv_id":"2409.13331","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-large-language-models-with-domain","title":"Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology","date":"2024-09-20","arxiv_id":"2409.13902","n_code_links":0,"syntology":null},{"paper":null,"slug":"hut-a-more-computation-efficient-fine-tuning","title":"HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation","date":"2024-09-20","arxiv_id":"2409.13501","n_code_links":0,"syntology":null},{"paper":"/paper/shizishangpt-an-agricultural-large-language","slug":"shizishangpt-an-agricultural-large-language","title":"ShizishanGPT: An Agricultural Large Language Model Integrating Tools and Resources","date":"2024-09-20","arxiv_id":"2409.13537","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-e-commerce-product-title","title":"Enhancing E-commerce Product Title Translation with Retrieval-Augmented Generation and Large Language Models","date":"2024-09-19","arxiv_id":"2409.12880","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-tinybert-for-financial-sentiment-1","slug":"enhancing-tinybert-for-financial-sentiment-1","title":"Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillation","date":"2024-09-19","arxiv_id":"2409.18999","n_code_links":1,"syntology":null},{"paper":"/paper/fact-fetch-and-reason-a-unified-evaluation-of","slug":"fact-fetch-and-reason-a-unified-evaluation-of","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","date":"2024-09-19","arxiv_id":"2409.12941","n_code_links":2,"syntology":null},{"paper":null,"slug":"incremental-and-data-efficient-concept","title":"Incremental and Data-Efficient Concept Formation to Support Masked Word Prediction","date":"2024-09-19","arxiv_id":"2409.12440","n_code_links":0,"syntology":null},{"paper":"/paper/profiling-patient-transcript-using-large","slug":"profiling-patient-transcript-using-large","title":"Profiling Patient Transcript Using Large Language Model Reasoning Augmentation for Alzheimer's Disease Detection","date":"2024-09-19","arxiv_id":"2409.12541","n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieval-augmented-test-generation-how-far","title":"Retrieval-Augmented Test Generation: How Far Are We?","date":"2024-09-19","arxiv_id":"2409.12682","n_code_links":0,"syntology":null},{"paper":"/paper/should-rag-chatbots-forget-unimportant","slug":"should-rag-chatbots-forget-unimportant","title":"Should RAG Chatbots Forget Unimportant Conversations? Exploring Importance and Forgetting with Psychological Insights","date":"2024-09-19","arxiv_id":"2409.12524","n_code_links":1,"syntology":null},{"paper":"/paper/text2traj2text-learning-by-synthesis","slug":"text2traj2text-learning-by-synthesis","title":"Text2Traj2Text: Learning-by-Synthesis Framework for Contextual Captioning of Human Movement Trajectories","date":"2024-09-19","arxiv_id":"2409.12670","n_code_links":1,"syntology":null},{"paper":null,"slug":"bert-vbd-vietnamese-multi-document","title":"BERT-VBD: Vietnamese Multi-Document Summarization Framework","date":"2024-09-18","arxiv_id":"2409.12134","n_code_links":0,"syntology":null},{"paper":"/paper/multi-grid-graph-neural-networks-with-self","slug":"multi-grid-graph-neural-networks-with-self","title":"Multi-Grid Graph Neural Networks with Self-Attention for Computational Mechanics","date":"2024-09-18","arxiv_id":"2409.11899","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["DonsetPG/graph-physics"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vera-validation-and-enhancement-for-retrieval","title":"VERA: Validation and Enhancement for Retrieval Augmented systems","date":"2024-09-18","arxiv_id":"2409.15364","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-transfer-of-multilingual-models","slug":"cross-lingual-transfer-of-multilingual-models","title":"Cross-lingual transfer of multilingual models on low resource African Languages","date":"2024-09-17","arxiv_id":"2409.10965","n_code_links":2,"syntology":null},{"paper":"/paper/hearts-a-holistic-framework-for-explainable","slug":"hearts-a-holistic-framework-for-explainable","title":"HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection","date":"2024-09-17","arxiv_id":"2409.11579","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-variant-product-relationship-and","title":"Learning variant product relationship and variation attributes from e-commerce website structures","date":"2024-09-17","arxiv_id":"2410.02779","n_code_links":0,"syntology":null},{"paper":"/paper/measuring-and-enhancing-trustworthiness-of","slug":"measuring-and-enhancing-trustworthiness-of","title":"Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse","date":"2024-09-17","arxiv_id":"2409.11242","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["declare-lab/trust-align"],"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":"p-rag-progressive-retrieval-augmented","title":"P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task","date":"2024-09-17","arxiv_id":"2409.11279","n_code_links":0,"syntology":null},{"paper":"/paper/thames-an-end-to-end-tool-for-hallucination","slug":"thames-an-end-to-end-tool-for-hallucination","title":"THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models","date":"2024-09-17","arxiv_id":"2409.11353","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":{"repos":["holistic-ai/THaMES"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-fair-rag-on-the-impact-of-fair","slug":"towards-fair-rag-on-the-impact-of-fair","title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","date":"2024-09-17","arxiv_id":"2409.11598","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kimdanny/fair-rag"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"lab-ai-retrieval-augmented-language-model-for","title":"Lab-AI: Using Retrieval Augmentation to Enhance Language Models for Personalized Lab Test Interpretation in Clinical Medicine","date":"2024-09-16","arxiv_id":"2409.18986","n_code_links":0,"syntology":null},{"paper":null,"slug":"sfr-rag-towards-contextually-faithful-llms","title":"SFR-RAG: Towards Contextually Faithful LLMs","date":"2024-09-16","arxiv_id":"2409.09916","n_code_links":0,"syntology":null},{"paper":"/paper/trustworthiness-in-retrieval-augmented","slug":"trustworthiness-in-retrieval-augmented","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","date":"2024-09-16","arxiv_id":"2409.10102","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["smallporridge/trustworthyrag"],"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":"integrating-ai-s-carbon-footprint-into-risk","title":"Integrating AI's Carbon Footprint into Risk Management Frameworks: Strategies and Tools for Sustainable Compliance in Banking Sector","date":"2024-09-15","arxiv_id":"2410.01818","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-and-retrieval-augmented","title":"Language Models and Retrieval Augmented Generation for Automated Structured Data Extraction from Diagnostic Reports","date":"2024-09-15","arxiv_id":"2409.10576","n_code_links":0,"syntology":null},{"paper":"/paper/towards-understanding-evolution-of-science","slug":"towards-understanding-evolution-of-science","title":"Towards understanding evolution of science through language model series","date":"2024-09-15","arxiv_id":"2409.09636","n_code_links":1,"syntology":null},{"paper":"/paper/active-learning-to-guide-labeling-efforts-for","slug":"active-learning-to-guide-labeling-efforts-for","title":"Active Learning to Guide Labeling Efforts for Question Difficulty Estimation","date":"2024-09-14","arxiv_id":"2409.09258","n_code_links":1,"syntology":null},{"paper":"/paper/block-attention-for-efficient-rag","slug":"block-attention-for-efficient-rag","title":"Block-Attention for Efficient RAG","date":"2024-09-14","arxiv_id":"2409.15355","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":0,"n_instrument":1,"unverified":6,"pointer_only":7,"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) · 6 unverified","official":{"repos":["temporarylora/block-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}}],"record_sha256":"c15988298d21670adc9c511fb7c9b9430d6d8dad0afa646ef78673814ea8b4b8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}