{"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/34","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":34,"pages_in_order":109,"rows_per_page":100,"rows":[3301,3400],"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/33","next":"/method/attention-dropout/papers/35","papers":[{"paper":null,"slug":"improving-retrieval-for-rag-based-question","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","date":"2024-03-23","arxiv_id":"2404.07221","n_code_links":0,"syntology":null},{"paper":"/paper/llambert-large-scale-low-cost-data-annotation","slug":"llambert-large-scale-low-cost-data-annotation","title":"LlamBERT: Large-scale low-cost data annotation in NLP","date":"2024-03-23","arxiv_id":"2403.15938","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-textbf-rag-based-summarization","slug":"towards-a-textbf-rag-based-summarization","title":"Towards a RAG-based Summarization Agent for the Electron-Ion Collider","date":"2024-03-23","arxiv_id":"2403.15729","n_code_links":1,"syntology":null},{"paper":null,"slug":"using-large-language-models-for-ontoclean","title":"Using Large Language Models for OntoClean-based Ontology Refinement","date":"2024-03-23","arxiv_id":"2403.15864","n_code_links":0,"syntology":null},{"paper":"/paper/when-llm-based-code-generation-meets-the","slug":"when-llm-based-code-generation-meets-the","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","date":"2024-03-23","arxiv_id":"2403.15852","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapprox-adaptive-approximation-in-adam","title":"Adapprox: Adaptive Approximation in Adam Optimization via Randomized Low-Rank Matrices","date":"2024-03-22","arxiv_id":"2403.14958","n_code_links":0,"syntology":null},{"paper":"/paper/blended-rag-improving-rag-retriever-augmented","slug":"blended-rag-improving-rag-retriever-augmented","title":"Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers","date":"2024-03-22","arxiv_id":"2404.07220","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["ibm-ecosystem-engineering/blended-rag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"can-large-language-models-explore-in-context","title":"Can large language models explore in-context?","date":"2024-03-22","arxiv_id":"2403.15371","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-evaluation-and-insights-into-1","slug":"comprehensive-evaluation-and-insights-into-1","title":"Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation","date":"2024-03-22","arxiv_id":"2403.14965","n_code_links":1,"syntology":null},{"paper":null,"slug":"masontigers-at-semeval-2024-task-1-an","title":"MasonTigers at SemEval-2024 Task 1: An Ensemble Approach for Semantic Textual Relatedness","date":"2024-03-22","arxiv_id":"2403.14990","n_code_links":0,"syntology":null},{"paper":null,"slug":"measuring-gender-and-racial-biases-in-large","title":"Measuring Gender and Racial Biases in Large Language Models","date":"2024-03-22","arxiv_id":"2403.15281","n_code_links":0,"syntology":null},{"paper":"/paper/on-zero-shot-counterspeech-generation-by-llms","slug":"on-zero-shot-counterspeech-generation-by-llms","title":"On Zero-Shot Counterspeech Generation by LLMs","date":"2024-03-22","arxiv_id":"2403.14938","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimal-path-for-biomedical-text","title":"Optimal path for Biomedical Text Summarization Using Pointer GPT","date":"2024-03-22","arxiv_id":"2404.08654","n_code_links":0,"syntology":null},{"paper":null,"slug":"selecting-query-bag-as-pseudo-relevance","title":"Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations","date":"2024-03-22","arxiv_id":"2404.04272","n_code_links":0,"syntology":null},{"paper":null,"slug":"sensoryt5-infusing-sensorimotor-norms-into-t5","title":"SensoryT5: Infusing Sensorimotor Norms into T5 for Enhanced Fine-grained Emotion Classification","date":"2024-03-22","arxiv_id":"2403.15574","n_code_links":0,"syntology":null},{"paper":null,"slug":"text-clustering-with-llm-embeddings","title":"Text Clustering with Large Language Model Embeddings","date":"2024-03-22","arxiv_id":"2403.15112","n_code_links":0,"syntology":null},{"paper":"/paper/emergent-world-models-and-latent-variable","slug":"emergent-world-models-and-latent-variable","title":"Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models","date":"2024-03-21","arxiv_id":"2403.15498","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: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["adamkarvonen/chess_llm_interpretability"],"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":null,"slug":"fit-rag-black-box-rag-with-factual","title":"FIT-RAG: Black-Box RAG with Factual Information and Token Reduction","date":"2024-03-21","arxiv_id":"2403.14374","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-based-extraction-of-contradictions-from","title":"LLM-based Extraction of Contradictions from Patents","date":"2024-03-21","arxiv_id":"2403.14258","n_code_links":0,"syntology":null},{"paper":"/paper/psalm-pixelwise-segmentation-with-large-multi","slug":"psalm-pixelwise-segmentation-with-large-multi","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","date":"2024-03-21","arxiv_id":"2403.14598","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":{"repos":["zamling/psalm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/vurf-a-general-purpose-reasoning-and-self","slug":"vurf-a-general-purpose-reasoning-and-self","title":"VURF: A General-purpose Reasoning and Self-refinement Framework for Video Understanding","date":"2024-03-21","arxiv_id":"2403.14743","n_code_links":1,"syntology":null},{"paper":null,"slug":"amp-autoregressive-motion-prediction","title":"AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving","date":"2024-03-20","arxiv_id":"2403.13331","n_code_links":0,"syntology":null},{"paper":null,"slug":"aud-tgn-advancing-action-unit-detection-with","title":"AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts","date":"2024-03-20","arxiv_id":"2403.13678","n_code_links":0,"syntology":null},{"paper":"/paper/ax-to-grind-urdu-benchmark-dataset-for-urdu","slug":"ax-to-grind-urdu-benchmark-dataset-for-urdu","title":"Ax-to-Grind Urdu: Benchmark Dataset for Urdu Fake News Detection","date":"2024-03-20","arxiv_id":"2403.14037","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-argument-classification-with","title":"Efficient argument classification with compact language models and ChatGPT-4 refinements","date":"2024-03-20","arxiv_id":"2403.15473","n_code_links":0,"syntology":null},{"paper":"/paper/incentivizing-news-consumption-on-social","slug":"incentivizing-news-consumption-on-social","title":"Incentivizing News Consumption on Social Media Platforms Using Large Language Models and Realistic Bot Accounts","date":"2024-03-20","arxiv_id":"2403.13362","n_code_links":1,"syntology":null},{"paper":"/paper/motion-generation-from-fine-grained-textual","slug":"motion-generation-from-fine-grained-textual","title":"Motion Generation from Fine-grained Textual Descriptions","date":"2024-03-20","arxiv_id":"2403.13518","n_code_links":1,"syntology":null},{"paper":null,"slug":"natural-language-as-polices-reasoning-for","title":"Natural Language as Policies: Reasoning for Coordinate-Level Embodied Control with LLMs","date":"2024-03-20","arxiv_id":"2403.13801","n_code_links":0,"syntology":null},{"paper":null,"slug":"paramanu-ayn-an-efficient-novel-generative","title":"PARAMANU-AYN: Pretrain from scratch or Continual Pretraining of LLMs for Legal Domain Adaptation?","date":"2024-03-20","arxiv_id":"2403.13681","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-data-curation-for-robust-language","title":"Automated Data Curation for Robust Language Model Fine-Tuning","date":"2024-03-19","arxiv_id":"2403.12776","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-summarization-of-doctor-patient","title":"Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning","date":"2024-03-19","arxiv_id":"2403.13089","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-outperform-human-experts-in-creating","title":"Can AI Outperform Human Experts in Creating Social Media Creatives?","date":"2024-03-19","arxiv_id":"2404.00018","n_code_links":0,"syntology":null},{"paper":"/paper/fine-tuning-pre-trained-language-models-to","slug":"fine-tuning-pre-trained-language-models-to","title":"Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks","date":"2024-03-19","arxiv_id":"2403.15458","n_code_links":0,"syntology":null},{"paper":"/paper/instructing-large-language-models-to-identify","slug":"instructing-large-language-models-to-identify","title":"Instructing Large Language Models to Identify and Ignore Irrelevant Conditions","date":"2024-03-19","arxiv_id":"2403.12744","n_code_links":1,"syntology":null},{"paper":null,"slug":"pipelined-biomedical-event-extraction","title":"Pipelined Biomedical Event Extraction Rivaling Joint Learning","date":"2024-03-19","arxiv_id":"2403.12386","n_code_links":0,"syntology":null},{"paper":null,"slug":"tt-blip-enhancing-fake-news-detection-using","title":"TT-BLIP: Enhancing Fake News Detection Using BLIP and Tri-Transformer","date":"2024-03-19","arxiv_id":"2403.12481","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-disease-labeler-for-chinese-chest-x-ray","title":"A Disease Labeler for Chinese Chest X-Ray Report Generation","date":"2024-03-18","arxiv_id":"2404.16852","n_code_links":0,"syntology":null},{"paper":"/paper/cicle-conformal-in-context-learning-for","slug":"cicle-conformal-in-context-learning-for","title":"CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification","date":"2024-03-18","arxiv_id":"2403.11904","n_code_links":1,"syntology":null},{"paper":null,"slug":"construction-of-hyper-relational-knowledge","title":"Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models","date":"2024-03-18","arxiv_id":"2403.11786","n_code_links":0,"syntology":null},{"paper":"/paper/easyjailbreak-a-unified-framework-for","slug":"easyjailbreak-a-unified-framework-for","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","date":"2024-03-18","arxiv_id":"2403.12171","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":["easyjailbreak/easyjailbreak"],"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":"/paper/embedded-named-entity-recognition-using","slug":"embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","date":"2024-03-18","arxiv_id":"2403.11747","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nicpopovic/stoke","nicpopovic/ember"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"embracing-the-generative-ai-revolution","title":"Embracing the Generative AI Revolution: Advancing Tertiary Education in Cybersecurity with GPT","date":"2024-03-18","arxiv_id":"2403.11402","n_code_links":0,"syntology":null},{"paper":"/paper/ensuring-safe-and-high-quality-outputs-a","slug":"ensuring-safe-and-high-quality-outputs-a","title":"Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models","date":"2024-03-18","arxiv_id":"2403.11838","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-named-entity-recognition","slug":"evaluating-named-entity-recognition","title":"Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset","date":"2024-03-18","arxiv_id":"2403.12212","n_code_links":2,"syntology":null},{"paper":null,"slug":"gpt-4-as-evaluator-evaluating-large-language","title":"GPT-4 as Evaluator: Evaluating Large Language Models on Pest Management in Agriculture","date":"2024-03-18","arxiv_id":"2403.11858","n_code_links":0,"syntology":null},{"paper":"/paper/hatecot-an-explanation-enhanced-dataset-for","slug":"hatecot-an-explanation-enhanced-dataset-for","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","date":"2024-03-18","arxiv_id":"2403.11456","n_code_links":1,"syntology":null},{"paper":"/paper/how-far-are-we-on-the-decision-making-of-llms","slug":"how-far-are-we-on-the-decision-making-of-llms","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","date":"2024-03-18","arxiv_id":"2403.11807","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cuhk-arise/gamabench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/meta-prompting-for-automating-zero-shot","slug":"meta-prompting-for-automating-zero-shot","title":"Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs","date":"2024-03-18","arxiv_id":"2403.11755","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jmiemirza/meta-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"metaphor-understanding-challenge-dataset-for","title":"Metaphor Understanding Challenge Dataset for LLMs","date":"2024-03-18","arxiv_id":"2403.11810","n_code_links":0,"syntology":null},{"paper":"/paper/narrative-feature-or-structured-feature-a","slug":"narrative-feature-or-structured-feature-a","title":"Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure","date":"2024-03-18","arxiv_id":"2403.11425","n_code_links":1,"syntology":null},{"paper":null,"slug":"shifting-the-lens-detecting-malware-in-npm","title":"Leveraging Large Language Models to Detect npm Malicious Packages","date":"2024-03-18","arxiv_id":"2403.12196","n_code_links":0,"syntology":null},{"paper":"/paper/data-is-all-you-need-finetuning-llms-for-chip","slug":"data-is-all-you-need-finetuning-llms-for-chip","title":"Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework","date":"2024-03-17","arxiv_id":"2403.11202","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["aichipdesign/chipgptft"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"forging-the-forger-an-attempt-to-improve","title":"Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation","date":"2024-03-17","arxiv_id":"2403.11265","n_code_links":0,"syntology":null},{"paper":"/paper/jora-jax-tensor-parallel-lora-library-for","slug":"jora-jax-tensor-parallel-lora-library-for","title":"JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning","date":"2024-03-17","arxiv_id":"2403.11366","n_code_links":1,"syntology":null},{"paper":null,"slug":"do-large-language-models-understand-medical","title":"Can Large Language Models abstract Medical Coded Language?","date":"2024-03-16","arxiv_id":"2403.10822","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-studies-of-parameter-efficient","slug":"empirical-studies-of-parameter-efficient","title":"Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R","date":"2024-03-16","arxiv_id":"2405.01553","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-melting-pots-to-misrepresentations","title":"From Melting Pots to Misrepresentations: Exploring Harms in Generative AI","date":"2024-03-16","arxiv_id":"2403.10776","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-powered-chatbots-for","title":"Large language model-powered chatbots for internationalizing student support in higher education","date":"2024-03-16","arxiv_id":"2403.14702","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-gpt-language-models-for","title":"Application of GPT Language Models for Innovation in Activities in University Teaching","date":"2024-03-15","arxiv_id":"2403.14694","n_code_links":0,"syntology":null},{"paper":"/paper/dragin-dynamic-retrieval-augmented-generation","slug":"dragin-dynamic-retrieval-augmented-generation","title":"DRAGIN: Dynamic Retrieval Augmented Generation based on the Information Needs of Large Language Models","date":"2024-03-15","arxiv_id":"2403.10081","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["oneal2000/dragin"],"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":"/paper/enhancing-llm-factual-accuracy-with-rag-to","slug":"enhancing-llm-factual-accuracy-with-rag-to","title":"Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases","date":"2024-03-15","arxiv_id":"2403.10446","n_code_links":1,"syntology":{"ran":12,"of":13,"n_ran_checked":12,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["anlp-team/LTI_Neural_Navigator"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exegpt-constraint-aware-resource-scheduling","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","date":"2024-03-15","arxiv_id":"2404.07947","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-condensation-and-reasoning-for","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","date":"2024-03-15","arxiv_id":"2403.10037","n_code_links":0,"syntology":null},{"paper":"/paper/raft-adapting-language-model-to-domain","slug":"raft-adapting-language-model-to-domain","title":"RAFT: Adapting Language Model to Domain Specific RAG","date":"2024-03-15","arxiv_id":"2403.10131","n_code_links":1,"syntology":null},{"paper":null,"slug":"repoformer-selective-retrieval-for-repository","title":"Repoformer: Selective Retrieval for Repository-Level Code Completion","date":"2024-03-15","arxiv_id":"2403.10059","n_code_links":0,"syntology":null},{"paper":null,"slug":"vitcn-vision-transformer-contrastive-network","title":"ViTCN: Vision Transformer Contrastive Network For Reasoning","date":"2024-03-15","arxiv_id":"2403.09962","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-on-ai-exploring-the-utility-of-gpt-as-an","title":"AI on AI: Exploring the Utility of GPT as an Expert Annotator of AI Publications","date":"2024-03-14","arxiv_id":"2403.09097","n_code_links":0,"syntology":null},{"paper":null,"slug":"basque-and-spanish-counter-narrative","title":"Basque and Spanish Counter Narrative Generation: Data Creation and Evaluation","date":"2024-03-14","arxiv_id":"2403.09159","n_code_links":0,"syntology":null},{"paper":"/paper/codeultrafeedback-an-llm-as-a-judge-dataset","slug":"codeultrafeedback-an-llm-as-a-judge-dataset","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","date":"2024-03-14","arxiv_id":"2403.09032","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["martin-wey/codeultrafeedback"],"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":"evaluating-llms-for-gender-disparities-in","title":"Evaluating LLMs for Gender Disparities in Notable Persons","date":"2024-03-14","arxiv_id":"2403.09148","n_code_links":0,"syntology":null},{"paper":"/paper/fisher-mask-nodes-for-language-model-merging","slug":"fisher-mask-nodes-for-language-model-merging","title":"Fisher Mask Nodes for Language Model Merging","date":"2024-03-14","arxiv_id":"2403.09891","n_code_links":1,"syntology":null},{"paper":"/paper/incorporating-graph-attention-mechanism-into-1","slug":"incorporating-graph-attention-mechanism-into-1","title":"Incorporating Graph Attention Mechanism into Geometric Problem Solving Based on Deep Reinforcement Learning","date":"2024-03-14","arxiv_id":"2403.14690","n_code_links":1,"syntology":null},{"paper":null,"slug":"information-extraction-an-application-to-the","title":"Information Extraction: An application to the domain of hyper-local financial data on developing countries","date":"2024-03-14","arxiv_id":"2403.09077","n_code_links":0,"syntology":null},{"paper":null,"slug":"komodo-a-linguistic-expedition-into-indonesia","title":"Komodo: A Linguistic Expedition into Indonesia's Regional Languages","date":"2024-03-14","arxiv_id":"2403.09362","n_code_links":0,"syntology":null},{"paper":null,"slug":"leap-molecular-synthesisability-scoring-with","title":"Leap: molecular synthesisability scoring with intermediates","date":"2024-03-14","arxiv_id":"2403.13005","n_code_links":0,"syntology":null},{"paper":"/paper/optimistic-verifiable-training-by-controlling","slug":"optimistic-verifiable-training-by-controlling","title":"Optimistic Verifiable Training by Controlling Hardware Nondeterminism","date":"2024-03-14","arxiv_id":"2403.09603","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":4,"n_instrument":5,"unverified":0,"pointer_only":9,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["meghabyte/verifiable-training"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ragged-towards-informed-design-of-retrieval","slug":"ragged-towards-informed-design-of-retrieval","title":"RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems","date":"2024-03-14","arxiv_id":"2403.09040","n_code_links":1,"syntology":{"ran":13,"of":14,"n_ran_checked":12,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"13 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["neulab/ragged"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/rectifying-demonstration-shortcut-in-in","slug":"rectifying-demonstration-shortcut-in-in","title":"Rectifying Demonstration Shortcut in In-Context Learning","date":"2024-03-14","arxiv_id":"2403.09488","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":1,"n_instrument":2,"unverified":6,"pointer_only":9,"phrase":"3 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; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["lainshower/in-context-calibration"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/retrieval-augmented-text-to-sql-generation","slug":"retrieval-augmented-text-to-sql-generation","title":"Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records","date":"2024-03-14","arxiv_id":"2403.09226","n_code_links":1,"syntology":null},{"paper":null,"slug":"sabia-2-a-new-generation-of-portuguese-large","title":"Sabiá-2: A New Generation of Portuguese Large Language Models","date":"2024-03-14","arxiv_id":"2403.09887","n_code_links":0,"syntology":null},{"paper":"/paper/autoregressive-score-generation-for-multi","slug":"autoregressive-score-generation-for-multi","title":"Autoregressive Score Generation for Multi-trait Essay Scoring","date":"2024-03-13","arxiv_id":"2403.08332","n_code_links":1,"syntology":null},{"paper":null,"slug":"distilling-named-entity-recognition-models","title":"Distilling Named Entity Recognition Models for Endangered Species from Large Language Models","date":"2024-03-13","arxiv_id":"2403.15430","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-care-about-text-quality","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","date":"2024-03-13","arxiv_id":"2403.08693","n_code_links":0,"syntology":null},{"paper":null,"slug":"embedded-translations-for-low-resource","title":"Embedded Translations for Low-resource Automated Glossing","date":"2024-03-13","arxiv_id":"2403.08189","n_code_links":0,"syntology":null},{"paper":"/paper/generative-pretrained-structured-transformers","slug":"generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","n_code_links":2,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 2 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) · 3 unverified","official":{"repos":["ant-research/structuredlm_rtdt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"research-on-the-application-of-deep-learning","title":"Research on the Application of Deep Learning-based BERT Model in Sentiment Analysis","date":"2024-03-13","arxiv_id":"2403.08217","n_code_links":0,"syntology":null},{"paper":null,"slug":"rich-semantic-knowledge-enhanced-large","title":"Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking","date":"2024-03-13","arxiv_id":"2403.08492","n_code_links":0,"syntology":null},{"paper":"/paper/chronos-learning-the-language-of-time-series","slug":"chronos-learning-the-language-of-time-series","title":"Chronos: Learning the Language of Time Series","date":"2024-03-12","arxiv_id":"2403.07815","n_code_links":6,"syntology":{"ran":23,"of":28,"n_ran_checked":22,"n_instrument":1,"unverified":5,"pointer_only":5,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 3 honoured, 1 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["SalesforceAIResearch/uni2ts","amazon-science/chronos-forecasting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/contextual-clarity-generating-sentences-with","slug":"contextual-clarity-generating-sentences-with","title":"Contextual Clarity: Generating Sentences with Transformer Models using Context-Reverso Data","date":"2024-03-12","arxiv_id":"2403.08103","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-readmission-prediction-with-deep","title":"Enhancing Readmission Prediction with Deep Learning: Extracting Biomedical Concepts from Clinical Texts","date":"2024-03-12","arxiv_id":"2403.09722","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-generated-text-detection-benchmark","slug":"gpt-generated-text-detection-benchmark","title":"GPT-generated Text Detection: Benchmark Dataset and Tensor-based Detection Method","date":"2024-03-12","arxiv_id":"2403.07321","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"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":["madlab-ucr/grid"],"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":"/paper/investigating-the-performance-of-retrieval","slug":"investigating-the-performance-of-retrieval","title":"Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems","date":"2024-03-12","arxiv_id":"2403.09727","n_code_links":1,"syntology":null},{"paper":"/paper/lookupffn-making-transformers-compute-lite","slug":"lookupffn-making-transformers-compute-lite","title":"LookupFFN: Making Transformers Compute-lite for CPU inference","date":"2024-03-12","arxiv_id":"2403.07221","n_code_links":1,"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":{"repos":["mlpen/lookupffn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/moralbert-detecting-moral-values-in-social","slug":"moralbert-detecting-moral-values-in-social","title":"MoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social Discussions","date":"2024-03-12","arxiv_id":"2403.07678","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-aste-a-minimalist-tagging-scheme","title":"Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning","date":"2024-03-12","arxiv_id":"2403.07342","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-generative-large-language-model","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","date":"2024-03-12","arxiv_id":"2403.07872","n_code_links":0,"syntology":null},{"paper":null,"slug":"sifid-reassess-summary-factual-inconsistency","title":"SIFiD: Reassess Summary Factual Inconsistency Detection with LLM","date":"2024-03-12","arxiv_id":"2403.07557","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-future-of-document-indexing-gpt-and-donut","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","date":"2024-03-12","arxiv_id":"2403.07553","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-cohort-study-on-prediction-of-acute","title":"A multi-cohort study on prediction of acute brain dysfunction states using selective state space models","date":"2024-03-11","arxiv_id":"2403.07201","n_code_links":0,"syntology":null},{"paper":null,"slug":"development-of-a-reliable-and-accessible","title":"Development of a Reliable and Accessible Caregiving Language Model (CaLM)","date":"2024-03-11","arxiv_id":"2403.06857","n_code_links":0,"syntology":null}],"record_sha256":"59f1d83492339f86688574533fc1c279480ca2b95ddbb102906ad71908fa12c8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}