{"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/attention-dropout/papers/14","list_of":"/method/attention-dropout","method":"Attention Dropout","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":14,"pages_in_order":109,"rows_per_page":100,"rows":[1301,1400],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"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/attention-dropout","prev":"/method/attention-dropout/papers/13","next":"/method/attention-dropout/papers/15","papers":[{"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":"/paper/do-large-language-vision-models-understand-3d","slug":"do-large-language-vision-models-understand-3d","title":"Do large language vision models understand 3D shapes?","date":"2024-12-14","arxiv_id":"2412.10908","n_code_links":1,"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":"/paper/does-multiple-choice-have-a-future-in-the-age","slug":"does-multiple-choice-have-a-future-in-the-age","title":"Does Multiple Choice Have a Future in the Age of Generative AI? A Posttest-only RCT","date":"2024-12-13","arxiv_id":"2412.10267","n_code_links":1,"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":"reasoner-outperforms-generative-stance","title":"Reasoner Outperforms: Generative Stance Detection with Rationalization for Social Media","date":"2024-12-13","arxiv_id":"2412.10266","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":"neural-text-normalization-for-luxembourgish","title":"Neural Text Normalization for Luxembourgish using Real-Life Variation Data","date":"2024-12-12","arxiv_id":"2412.09383","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":"text-generation-models-for-luxembourgish-with","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","date":"2024-12-12","arxiv_id":"2412.09415","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":"/paper/adversarial-vulnerabilities-in-large-language","slug":"adversarial-vulnerabilities-in-large-language","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","date":"2024-12-11","arxiv_id":"2412.08099","n_code_links":1,"syntology":null},{"paper":null,"slug":"auto-generating-earnings-report-analysis-via","title":"Auto-Generating Earnings Report Analysis via a Financial-Augmented LLM","date":"2024-12-11","arxiv_id":"2412.08179","n_code_links":0,"syntology":null},{"paper":"/paper/exploiting-the-index-gradients-for","slug":"exploiting-the-index-gradients-for","title":"Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models","date":"2024-12-11","arxiv_id":"2412.08615","n_code_links":1,"syntology":null},{"paper":null,"slug":"graphtool-instruction-revolutionizing-graph","title":"GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction","date":"2024-12-11","arxiv_id":"2412.12152","n_code_links":0,"syntology":null},{"paper":null,"slug":"imitate-before-detect-aligning-machine","title":"Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection","date":"2024-12-11","arxiv_id":"2412.10432","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-still-face-challenges","title":"Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge","date":"2024-12-11","arxiv_id":"2412.08317","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":"/paper/causal-world-representation-in-the-gpt-model","slug":"causal-world-representation-in-the-gpt-model","title":"A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment","date":"2024-12-10","arxiv_id":"2412.07446","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":"gpt-2-through-the-lens-of-vector-symbolic","title":"GPT-2 Through the Lens of Vector Symbolic Architectures","date":"2024-12-10","arxiv_id":"2412.07947","n_code_links":0,"syntology":null},{"paper":"/paper/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","n_code_links":1,"syntology":null},{"paper":"/paper/rag-based-question-answering-over","slug":"rag-based-question-answering-over","title":"RAG-based Question Answering over Heterogeneous Data and Text","date":"2024-12-10","arxiv_id":"2412.07420","n_code_links":0,"syntology":null},{"paper":"/paper/superficial-consciousness-hypothesis-for","slug":"superficial-consciousness-hypothesis-for","title":"Superficial Consciousness Hypothesis for Autoregressive Transformers","date":"2024-12-10","arxiv_id":"2412.07278","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-predictive-communication-with-brain","title":"Towards Predictive Communication with Brain-Computer Interfaces integrating Large Language Models","date":"2024-12-10","arxiv_id":"2412.07355","n_code_links":0,"syntology":null},{"paper":"/paper/batchtopk-sparse-autoencoders","slug":"batchtopk-sparse-autoencoders","title":"BatchTopK Sparse Autoencoders","date":"2024-12-09","arxiv_id":"2412.06410","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bartbussmann/batchtopk"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-memorization-and-copyright","title":"Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit","date":"2024-12-09","arxiv_id":"2412.06370","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":"/paper/are-clinical-t5-models-better-for-clinical","slug":"are-clinical-t5-models-better-for-clinical","title":"Are Clinical T5 Models Better for Clinical Text?","date":"2024-12-08","arxiv_id":"2412.05845","n_code_links":1,"syntology":null},{"paper":"/paper/m-3-20m-a-large-scale-multi-modal-molecule","slug":"m-3-20m-a-large-scale-multi-modal-molecule","title":"M$^{3}$-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery","date":"2024-12-08","arxiv_id":"2412.06847","n_code_links":1,"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/characterbox-evaluating-the-role-playing","slug":"characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","arxiv_id":"2412.05631","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["paitesanshi/characterbox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-the-use-of-llms-for-sql-equivalence","title":"Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking","date":"2024-12-07","arxiv_id":"2412.05561","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":"/paper/privagent-agentic-based-red-teaming-for-llm","slug":"privagent-agentic-based-red-teaming-for-llm","title":"PrivAgent: Agentic-based Red-teaming for LLM Privacy Leakage","date":"2024-12-07","arxiv_id":"2412.05734","n_code_links":1,"syntology":null},{"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":"100-hallucination-elimination-using-acurai","title":"100% Elimination of Hallucinations on RAGTruth for GPT-4 and GPT-3.5 Turbo","date":"2024-12-06","arxiv_id":"2412.05223","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":"are-frontier-large-language-models-suitable","title":"Are Frontier Large Language Models Suitable for Q&A in Science Centres?","date":"2024-12-06","arxiv_id":"2412.05200","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":"how-good-is-chatgpt-in-giving-adaptive","title":"How Good is ChatGPT in Giving Adaptive Guidance Using Knowledge Graphs in E-Learning Environments?","date":"2024-12-05","arxiv_id":"2412.03856","n_code_links":0,"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":"controlling-the-mutation-in-large-language","title":"Controlling the Mutation in Large Language Models for the Efficient Evolution of Algorithms","date":"2024-12-04","arxiv_id":"2412.03250","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":"compressing-kv-cache-for-long-context-llm","title":"Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity","date":"2024-12-03","arxiv_id":"2412.02252","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/dp-2stage-adapting-language-models-as","slug":"dp-2stage-adapting-language-models-as","title":"DP-2Stage: Adapting Language Models as Differentially Private Tabular Data Generators","date":"2024-12-03","arxiv_id":"2412.02467","n_code_links":1,"syntology":null},{"paper":null,"slug":"flattering-to-deceive-the-impact-of","title":"Flattering to Deceive: The Impact of Sycophantic Behavior on User Trust in Large Language Model","date":"2024-12-03","arxiv_id":"2412.02802","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":null,"slug":"impact-of-data-snooping-on-deep-learning","title":"Impact of Data Snooping on Deep Learning Models for Locating Vulnerabilities in Lifted Code","date":"2024-12-03","arxiv_id":"2412.02048","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-20","title":"Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms","date":"2024-12-03","arxiv_id":"2412.02149","n_code_links":0,"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},{"paper":null,"slug":"scaling-bert-models-for-turkish-automatic","title":"Scaling BERT Models for Turkish Automatic Punctuation and Capitalization Correction","date":"2024-12-03","arxiv_id":"2412.02698","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-tokens-in-retrieval-augmented","title":"Semantic Tokens in Retrieval Augmented Generation","date":"2024-12-03","arxiv_id":"2412.02563","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-asymptotic-behavior-of-attention-in","title":"The Asymptotic Behavior of Attention in Transformers","date":"2024-12-03","arxiv_id":"2412.02682","n_code_links":0,"syntology":null},{"paper":"/paper/mba-rag-a-bandit-approach-for-adaptive","slug":"mba-rag-a-bandit-approach-for-adaptive","title":"MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity","date":"2024-12-02","arxiv_id":"2412.01572","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["futureeeeee/mba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/sitse-sinhala-text-simplification-dataset-and","slug":"sitse-sinhala-text-simplification-dataset-and","title":"SiTSE: Sinhala Text Simplification Dataset and Evaluation","date":"2024-12-02","arxiv_id":"2412.01293","n_code_links":1,"syntology":null},{"paper":null,"slug":"su-roberta-a-semi-supervised-approach-to","title":"Su-RoBERTa: A Semi-supervised Approach to Predicting Suicide Risk through Social Media using Base Language Models","date":"2024-12-02","arxiv_id":"2412.01353","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-promise-and-peril-of-generative-ai","title":"The Promise and Peril of Generative AI: Evidence from GPT-4 as Sell-Side Analysts","date":"2024-12-02","arxiv_id":"2412.01069","n_code_links":0,"syntology":null},{"paper":null,"slug":"tokenizing-3d-molecule-structure-with","title":"Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates","date":"2024-12-02","arxiv_id":"2412.01564","n_code_links":0,"syntology":null},{"paper":"/paper/a-comprehensive-guide-to-explainable-ai-from","slug":"a-comprehensive-guide-to-explainable-ai-from","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","date":"2024-12-01","arxiv_id":"2412.00800","n_code_links":1,"syntology":null},{"paper":null,"slug":"eventgpt-event-stream-understanding-with","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","date":"2024-12-01","arxiv_id":"2412.00832","n_code_links":0,"syntology":null},{"paper":"/paper/lightweight-contenders-navigating-semi","slug":"lightweight-contenders-navigating-semi","title":"Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence","date":"2024-12-01","arxiv_id":"2412.00883","n_code_links":1,"syntology":null},{"paper":null,"slug":"cdemapper-enhancing-nih-common-data-element","title":"CDEMapper: Enhancing NIH Common Data Element Normalization using Large Language Models","date":"2024-11-30","arxiv_id":"2412.00491","n_code_links":0,"syntology":null},{"paper":null,"slug":"cognitive-biases-in-large-language-models-a","title":"Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments","date":"2024-11-30","arxiv_id":"2412.00323","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-self-attention-need-separate-weights-in","title":"Does Self-Attention Need Separate Weights in Transformers?","date":"2024-11-30","arxiv_id":"2412.00359","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-the-deaf-and-hard-of-hearing","title":"Empowering the Deaf and Hard of Hearing Community: Enhancing Video Captions Using Large Language Models","date":"2024-11-30","arxiv_id":"2412.00342","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairness-at-every-intersection-uncovering-and","title":"Fairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions","date":"2024-11-30","arxiv_id":"2412.00606","n_code_links":0,"syntology":null},{"paper":null,"slug":"forma-mentis-networks-predict-creativity","title":"Forma mentis networks predict creativity ratings of short texts via interpretable artificial intelligence in human and GPT-simulated raters","date":"2024-11-30","arxiv_id":"2412.00530","n_code_links":0,"syntology":null},{"paper":null,"slug":"advanced-system-integration-analyzing-openapi","title":"Advanced System Integration: Analyzing OpenAPI Chunking for Retrieval-Augmented Generation","date":"2024-11-29","arxiv_id":"2411.19804","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-a-low-code-complete-workflow-via","title":"Generating a Low-code Complete Workflow via Task Decomposition and RAG","date":"2024-11-29","arxiv_id":"2412.00239","n_code_links":0,"syntology":null}],"record_sha256":"0c3b1a836118a4318abcd9efc7f61a811483db317abde551d95e41c1996a0151","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}