{"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/weight-decay/papers/30","list_of":"/method/weight-decay","method":"Weight Decay","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":30,"pages_in_order":108,"rows_per_page":100,"rows":[2901,3000],"of":10713,"counts":{"archive_papers_tagged":10713,"with_a_code_link":4533,"where_syntology_ran_a_sample":1291,"not_listed_spam_title":0,"listed":10713,"listed_where_code_ran":1291,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1064,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1064,"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/weight-decay","prev":"/method/weight-decay/papers/29","next":"/method/weight-decay/papers/31","papers":[{"paper":null,"slug":"gpt-4-passes-most-of-the-297-written-polish","title":"GPT-4 passes most of the 297 written Polish Board Certification Examinations","date":"2024-04-29","arxiv_id":"2405.01589","n_code_links":0,"syntology":null},{"paper":"/paper/pecc-problem-extraction-and-coding-challenges","slug":"pecc-problem-extraction-and-coding-challenges","title":"PECC: Problem Extraction and Coding Challenges","date":"2024-04-29","arxiv_id":"2404.18766","n_code_links":1,"syntology":null},{"paper":null,"slug":"time-machine-gpt","title":"Time Machine GPT","date":"2024-04-29","arxiv_id":"2404.18543","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-perplexity-predict-fine-tuning","title":"Can Perplexity Predict Fine-Tuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali","date":"2024-04-28","arxiv_id":"2404.18071","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahanews-news-based-short-text-and","slug":"l3cube-mahanews-news-based-short-text-and","title":"L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi","date":"2024-04-28","arxiv_id":"2404.18216","n_code_links":1,"syntology":null},{"paper":null,"slug":"tabular-embedding-model-tem-finetuning","title":"Tabular Embedding Model (TEM): Finetuning Embedding Models For Tabular RAG Applications","date":"2024-04-28","arxiv_id":"2405.01585","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-of-conspiracy-theories-beyond","title":"Detection of Conspiracy Theories Beyond Keyword Bias in German-Language Telegram Using Large Language Models","date":"2024-04-27","arxiv_id":"2404.17985","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pre-trained-generative-language","title":"Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension","date":"2024-04-27","arxiv_id":"2404.17991","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-few-shot-learning-for","title":"Evaluation of Few-Shot Learning for Classification Tasks in the Polish Language","date":"2024-04-27","arxiv_id":"2404.17832","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-for-games-a-scoping-review-2020-2023","title":"GPT for Games: A Scoping Review (2020-2023)","date":"2024-04-27","arxiv_id":"2404.17794","n_code_links":0,"syntology":null},{"paper":null,"slug":"mrscore-evaluating-radiology-report","title":"MRScore: Evaluating Radiology Report Generation with LLM-based Reward System","date":"2024-04-27","arxiv_id":"2404.17778","n_code_links":0,"syntology":null},{"paper":null,"slug":"tool-calling-enhancing-medication","title":"Tool Calling: Enhancing Medication Consultation via Retrieval-Augmented Large Language Models","date":"2024-04-27","arxiv_id":"2404.17897","n_code_links":0,"syntology":null},{"paper":"/paper/automated-data-visualization-from-natural","slug":"automated-data-visualization-from-natural","title":"Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study","date":"2024-04-26","arxiv_id":"2404.17136","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-is-here-to-help-not-to-replace","title":"\"ChatGPT Is Here to Help, Not to Replace Anybody\" -- An Evaluation of Students' Opinions On Integrating ChatGPT In CS Courses","date":"2024-04-26","arxiv_id":"2404.17443","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-legal-compliance-and-regulation","title":"Enhancing Legal Compliance and Regulation Analysis with Large Language Models","date":"2024-04-26","arxiv_id":"2404.17522","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-imperceptible-retrieval-poisoning","title":"Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications","date":"2024-04-26","arxiv_id":"2404.17196","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompting-towards-alleviating-code-switched","title":"Prompting Towards Alleviating Code-Switched Data Scarcity in Under-Resourced Languages with GPT as a Pivot","date":"2024-04-26","arxiv_id":"2404.17216","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-memorization-of-domain-specific","title":"Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper","date":"2024-04-26","arxiv_id":"2404.17143","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-generation-with-knowledge","title":"Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering","date":"2024-04-26","arxiv_id":"2404.17723","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-short-survey-of-human-mobility-prediction","title":"A Short Survey of Human Mobility Prediction in Epidemic Modeling from Transformers to LLMs","date":"2024-04-25","arxiv_id":"2404.16921","n_code_links":0,"syntology":null},{"paper":null,"slug":"analise-de-ambiguidade-linguistica-em-modelos","title":"Análise de ambiguidade linguística em modelos de linguagem de grande escala (LLMs)","date":"2024-04-25","arxiv_id":"2404.16653","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-consistency-and-reasoning","title":"Evaluating Consistency and Reasoning Capabilities of Large Language Models","date":"2024-04-25","arxiv_id":"2404.16478","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-lexical-and-syntactic-knowledge","slug":"incorporating-lexical-and-syntactic-knowledge","title":"Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer","date":"2024-04-25","arxiv_id":"2404.16627","n_code_links":1,"syntology":null},{"paper":"/paper/indicgenbench-a-multilingual-benchmark-to","slug":"indicgenbench-a-multilingual-benchmark-to","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","date":"2024-04-25","arxiv_id":"2404.16816","n_code_links":1,"syntology":null},{"paper":null,"slug":"influence-of-solution-efficiency-and-valence","title":"Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4","date":"2024-04-25","arxiv_id":"2404.16692","n_code_links":0,"syntology":null},{"paper":"/paper/worldvaluesbench-a-large-scale-benchmark","slug":"worldvaluesbench-a-large-scale-benchmark","title":"WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Models","date":"2024-04-25","arxiv_id":"2404.16308","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":5,"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":["demon702/worldvaluesbench"],"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":"a-comprehensive-survey-on-evaluating-large","title":"A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry","date":"2024-04-24","arxiv_id":"2404.15777","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-creation-of-source-code-variants-of","title":"Automated Creation of Source Code Variants of a Cryptographic Hash Function Implementation Using Generative Pre-Trained Transformer Models","date":"2024-04-24","arxiv_id":"2404.15681","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-vs-gpt-for-financial-engineering","title":"BERT vs GPT for financial engineering","date":"2024-04-24","arxiv_id":"2405.12990","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-conceptual-abstraction-in-llms","title":"Detecting Conceptual Abstraction in LLMs","date":"2024-04-24","arxiv_id":"2404.15848","n_code_links":0,"syntology":null},{"paper":"/paper/from-local-to-global-a-graph-rag-approach-to","slug":"from-local-to-global-a-graph-rag-approach-to","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","date":"2024-04-24","arxiv_id":"2404.16130","n_code_links":3,"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":null}},{"paper":null,"slug":"investigating-the-prompt-leakage-effect-and","title":"Prompt Leakage effect and defense strategies for multi-turn LLM interactions","date":"2024-04-24","arxiv_id":"2404.16251","n_code_links":0,"syntology":null},{"paper":"/paper/learning-long-form-video-prior-via-generative","slug":"learning-long-form-video-prior-via-generative","title":"Learning Long-form Video Prior via Generative Pre-Training","date":"2024-04-24","arxiv_id":"2404.15909","n_code_links":1,"syntology":null},{"paper":"/paper/studying-large-language-model-behaviors-under","slug":"studying-large-language-model-behaviors-under","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","date":"2024-04-24","arxiv_id":"2404.16032","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kortukov/realistic_knowledge_conflicts"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/telco-rag-navigating-the-challenges-of","slug":"telco-rag-navigating-the-challenges-of","title":"Telco-RAG: Navigating the Challenges of Retrieval-Augmented Language Models for Telecommunications","date":"2024-04-24","arxiv_id":"2404.15939","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-promise-and-challenges-of-using-llms-to","title":"The Promise and Challenges of Using LLMs to Accelerate the Screening Process of Systematic Reviews","date":"2024-04-24","arxiv_id":"2404.15667","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-and-machine-learning-for-next-generation","title":"AI and Machine Learning for Next Generation Science Assessments","date":"2024-04-23","arxiv_id":"2405.06660","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-multi-language-to-english-machine","title":"Automated Multi-Language to English Machine Translation Using Generative Pre-Trained Transformers","date":"2024-04-23","arxiv_id":"2404.14680","n_code_links":0,"syntology":null},{"paper":null,"slug":"iryonlp-at-mediqa-corr-2024-tackling-the","title":"IryoNLP at MEDIQA-CORR 2024: Tackling the Medical Error Detection & Correction Task On the Shoulders of Medical Agents","date":"2024-04-23","arxiv_id":"2404.15488","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-spot-phishing-emails","title":"Evaluating the Efficacy of Large Language Models in Identifying Phishing Attempts","date":"2024-04-23","arxiv_id":"2404.15485","n_code_links":0,"syntology":null},{"paper":null,"slug":"prism-patient-records-interpretation-for","title":"PRISM: Patient Records Interpretation for Semantic Clinical Trial Matching using Large Language Models","date":"2024-04-23","arxiv_id":"2404.15549","n_code_links":0,"syntology":null},{"paper":null,"slug":"science-written-by-generative-ai-is-perceived","title":"From Complexity to Clarity: How AI Enhances Perceptions of Scientists and the Public's Understanding of Science","date":"2024-04-23","arxiv_id":"2405.00706","n_code_links":0,"syntology":null},{"paper":null,"slug":"talk-too-much-poisoning-large-language-models","title":"Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models","date":"2024-04-23","arxiv_id":"2404.14795","n_code_links":0,"syntology":null},{"paper":"/paper/the-power-of-the-noisy-channel-unsupervised","slug":"the-power-of-the-noisy-channel-unsupervised","title":"Unsupervised End-to-End Task-Oriented Dialogue with LLMs: The Power of the Noisy Channel","date":"2024-04-23","arxiv_id":"2404.15219","n_code_links":1,"syntology":null},{"paper":"/paper/automated-long-answer-grading-with-ricechem","slug":"automated-long-answer-grading-with-ricechem","title":"Automated Long Answer Grading with RiceChem Dataset","date":"2024-04-22","arxiv_id":"2404.14316","n_code_links":1,"syntology":null},{"paper":"/paper/calc-cmu-at-semeval-2024-task-7-pre-calc","slug":"calc-cmu-at-semeval-2024-task-7-pre-calc","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","date":"2024-04-22","arxiv_id":"2404.14355","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["calc-cmu/pre-calc"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-attractive-and-authentic","title":"Generating Attractive and Authentic Copywriting from Customer Reviews","date":"2024-04-22","arxiv_id":"2404.13906","n_code_links":0,"syntology":null},{"paper":"/paper/how-well-can-llms-echo-us-evaluating-ai","slug":"how-well-can-llms-echo-us-evaluating-ai","title":"How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO","date":"2024-04-22","arxiv_id":"2404.13957","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":6,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cuhk-arise/echo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"information-re-organization-improves","title":"Information Re-Organization Improves Reasoning in Large Language Models","date":"2024-04-22","arxiv_id":"2404.13985","n_code_links":0,"syntology":null},{"paper":"/paper/llms-know-what-they-need-leveraging-a-missing","slug":"llms-know-what-they-need-leveraging-a-missing","title":"LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation","date":"2024-04-22","arxiv_id":"2404.14043","n_code_links":1,"syntology":null},{"paper":null,"slug":"marking-visual-grading-with-highlighting","title":"Marking: Visual Grading with Highlighting Errors and Annotating Missing Bits","date":"2024-04-22","arxiv_id":"2404.14301","n_code_links":0,"syntology":null},{"paper":null,"slug":"navigating-the-path-of-writing-outline-guided","title":"Navigating the Path of Writing: Outline-guided Text Generation with Large Language Models","date":"2024-04-22","arxiv_id":"2404.13919","n_code_links":0,"syntology":null},{"paper":"/paper/phi-3-technical-report-a-highly-capable","slug":"phi-3-technical-report-a-highly-capable","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","date":"2024-04-22","arxiv_id":"2404.14219","n_code_links":0,"syntology":null},{"paper":"/paper/typos-that-broke-the-rag-s-back-genetic","slug":"typos-that-broke-the-rag-s-back-genetic","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","date":"2024-04-22","arxiv_id":"2404.13948","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["zomss/garag"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-do-transformers-know-about-government","slug":"what-do-transformers-know-about-government","title":"What do Transformers Know about Government?","date":"2024-04-22","arxiv_id":"2404.14270","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-cross-lingual-stance-detection-via","slug":"zero-shot-cross-lingual-stance-detection-via","title":"Zero-shot Cross-lingual Stance Detection via Adversarial Language Adaptation","date":"2024-04-22","arxiv_id":"2404.14339","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-text-mining-of-experimental","title":"Automated Text Mining of Experimental Methodologies from Biomedical Literature","date":"2024-04-21","arxiv_id":"2404.13779","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-retrieval-quality-in-retrieval","slug":"evaluating-retrieval-quality-in-retrieval","title":"Evaluating Retrieval Quality in Retrieval-Augmented Generation","date":"2024-04-21","arxiv_id":"2404.13781","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["alirezasalemi7/erag"],"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":"/paper/svgeditbench-a-benchmark-dataset-for","slug":"svgeditbench-a-benchmark-dataset-for","title":"SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities","date":"2024-04-21","arxiv_id":"2404.13710","n_code_links":1,"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":["mti-lab/svgeditbench"],"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":"bert-accelerating-vital-signs-measurement-for","title":"BERT: Accelerating Vital Signs Measurement for Bioradar with An Efficient Recursive Technique","date":"2024-04-20","arxiv_id":"2404.13315","n_code_links":0,"syntology":null},{"paper":"/paper/do-english-named-entity-recognizers-work-well","slug":"do-english-named-entity-recognizers-work-well","title":"Do \"English\" Named Entity Recognizers Work Well on Global Englishes?","date":"2024-04-20","arxiv_id":"2404.13465","n_code_links":2,"syntology":null},{"paper":"/paper/evaluating-subword-tokenization-alien-subword","slug":"evaluating-subword-tokenization-alien-subword","title":"Evaluating Subword Tokenization: Alien Subword Composition and OOV Generalization Challenge","date":"2024-04-20","arxiv_id":"2404.13292","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-alignment-for-zero-shot-concept","title":"Data Alignment for Zero-Shot Concept Generation in Dermatology AI","date":"2024-04-19","arxiv_id":"2404.13043","n_code_links":0,"syntology":null},{"paper":"/paper/dubo-sql-diverse-retrieval-augmented","slug":"dubo-sql-diverse-retrieval-augmented","title":"Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL","date":"2024-04-19","arxiv_id":"2404.12560","n_code_links":1,"syntology":null},{"paper":null,"slug":"enabling-natural-zero-shot-prompting-on","title":"Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning","date":"2024-04-19","arxiv_id":"2404.12897","n_code_links":0,"syntology":null},{"paper":"/paper/multi-class-depression-detection-through","slug":"multi-class-depression-detection-through","title":"Multi Class Depression Detection Through Tweets using Artificial Intelligence","date":"2024-04-19","arxiv_id":"2404.13104","n_code_links":1,"syntology":null},{"paper":"/paper/the-instruction-hierarchy-training-llms-to","slug":"the-instruction-hierarchy-training-llms-to","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","date":"2024-04-19","arxiv_id":"2404.13208","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-multi-view-insights-in-knowledge","title":"Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation","date":"2024-04-19","arxiv_id":"2404.12879","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-emotion-features-in-irony","title":"Augmenting emotion features in irony detection with Large language modeling","date":"2024-04-18","arxiv_id":"2404.12291","n_code_links":0,"syntology":null},{"paper":null,"slug":"emrqa-msquad-a-medical-dataset-structured","title":"emrQA-msquad: A Medical Dataset Structured with the SQuAD V2.0 Framework, Enriched with emrQA Medical Information","date":"2024-04-18","arxiv_id":"2404.12050","n_code_links":0,"syntology":null},{"paper":"/paper/from-form-s-to-meaning-probing-the-semantic","slug":"from-form-s-to-meaning-probing-the-semantic","title":"From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency","date":"2024-04-18","arxiv_id":"2404.12145","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facebookresearch/multisense_consistency"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"irag-an-incremental-retrieval-augmented","title":"iRAG: Advancing RAG for Videos with an Incremental Approach","date":"2024-04-18","arxiv_id":"2404.12309","n_code_links":0,"syntology":null},{"paper":"/paper/longembed-extending-embedding-models-for-long","slug":"longembed-extending-embedding-models-for-long","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","date":"2024-04-18","arxiv_id":"2404.12096","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":6,"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) · 1 unverified","official":{"repos":["dwzhu-pku/longembed"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"midget-music-conditioned-3d-dance-generation","title":"MIDGET: Music Conditioned 3D Dance Generation","date":"2024-04-18","arxiv_id":"2404.12062","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragar-your-falsehood-radar-rag-augmented","title":"RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models","date":"2024-04-18","arxiv_id":"2404.12065","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragcache-efficient-knowledge-caching-for","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","date":"2024-04-18","arxiv_id":"2404.12457","n_code_links":0,"syntology":null},{"paper":null,"slug":"ram-towards-an-ever-improving-memory-system","title":"RAM: Towards an Ever-Improving Memory System by Learning from Communications","date":"2024-04-18","arxiv_id":"2404.12045","n_code_links":0,"syntology":null},{"paper":null,"slug":"stance-detection-on-social-media-with-fine","title":"Stance Detection on Social Media with Fine-Tuned Large Language Models","date":"2024-04-18","arxiv_id":"2404.12171","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-retrieval-augmented-text-1","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","date":"2024-04-17","arxiv_id":"2404.10981","n_code_links":0,"syntology":null},{"paper":"/paper/comparative-analysis-of-deep-natural-networks","slug":"comparative-analysis-of-deep-natural-networks","title":"Comparative Analysis of Deep Natural Networks and Large Language Models for Aspect-Based Sentiment Analysis","date":"2024-04-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"demystifying-legalese-an-automated-approach","title":"Demystifying Legalese: An Automated Approach for Summarizing and Analyzing Overlaps in Privacy Policies and Terms of Service","date":"2024-04-17","arxiv_id":"2404.13087","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-q-a-with-domain-specific-fine","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","date":"2024-04-17","arxiv_id":"2404.11792","n_code_links":0,"syntology":null},{"paper":null,"slug":"improvement-in-semantic-address-matching","title":"Improvement in Semantic Address Matching using Natural Language Processing","date":"2024-04-17","arxiv_id":"2404.11691","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sentiment-analysis-of-medical-text-based-on","title":"A Sentiment Analysis of Medical Text Based on Deep Learning","date":"2024-04-16","arxiv_id":"2404.10503","n_code_links":0,"syntology":null},{"paper":null,"slug":"bayesjudge-bayesian-kernel-language-modelling","title":"BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction","date":"2024-04-16","arxiv_id":"2404.10481","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-control-reinforcement-learning","title":"Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms","date":"2024-04-16","arxiv_id":"2404.10645","n_code_links":0,"syntology":null},{"paper":"/paper/decoupled-weight-decay-for-any-p-norm","slug":"decoupled-weight-decay-for-any-p-norm","title":"Decoupled Weight Decay for Any $p$ Norm","date":"2024-04-16","arxiv_id":"2404.10824","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nadav-out/padam"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"empowering-interdisciplinary-research-with","title":"Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling","date":"2024-04-16","arxiv_id":"2404.13078","n_code_links":0,"syntology":null},{"paper":"/paper/ladic-are-diffusion-models-really-inferior-to","slug":"ladic-are-diffusion-models-really-inferior-to","title":"LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?","date":"2024-04-16","arxiv_id":"2404.10763","n_code_links":1,"syntology":null},{"paper":null,"slug":"relational-graph-convolutional-networks-for-1","title":"Relational Graph Convolutional Networks for Sentiment Analysis","date":"2024-04-16","arxiv_id":"2404.13079","n_code_links":0,"syntology":null},{"paper":"/paper/spiral-of-silences-how-is-large-language","slug":"spiral-of-silences-how-is-large-language","title":"Spiral of Silence: How is Large Language Model Killing Information Retrieval? -- A Case Study on Open Domain Question Answering","date":"2024-04-16","arxiv_id":"2404.10496","n_code_links":1,"syntology":null},{"paper":"/paper/aesexpert-towards-multi-modality-foundation","slug":"aesexpert-towards-multi-modality-foundation","title":"AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception","date":"2024-04-15","arxiv_id":"2404.09624","n_code_links":1,"syntology":null},{"paper":null,"slug":"deceiving-to-enlighten-coaxing-llms-to-self","title":"Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs","date":"2024-04-15","arxiv_id":"2404.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-ai-generated-text-based-on-nlp-and","title":"Detecting AI Generated Text Based on NLP and Machine Learning Approaches","date":"2024-04-15","arxiv_id":"2404.10032","n_code_links":0,"syntology":null},{"paper":null,"slug":"quality-assessment-of-prompts-used-in-code","title":"The Fault in our Stars: Quality Assessment of Code Generation Benchmarks","date":"2024-04-15","arxiv_id":"2404.10155","n_code_links":0,"syntology":null},{"paper":"/paper/s-gpts-a-new-approach-to-autoregressive","slug":"s-gpts-a-new-approach-to-autoregressive","title":"σ-GPTs: A New Approach to Autoregressive Models","date":"2024-04-15","arxiv_id":"2404.09562","n_code_links":1,"syntology":null},{"paper":"/paper/bert-lsh-reducing-absolute-compute-for","slug":"bert-lsh-reducing-absolute-compute-for","title":"BERT-LSH: Reducing Absolute Compute For Attention","date":"2024-04-12","arxiv_id":"2404.08836","n_code_links":1,"syntology":null},{"paper":null,"slug":"creativeval-evaluating-creativity-of-llm","title":"CreativEval: Evaluating Creativity of LLM-Based Hardware Code Generation","date":"2024-04-12","arxiv_id":"2404.08806","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-chatgpt-transforming-academics-writing","title":"Is ChatGPT Transforming Academics' Writing Style?","date":"2024-04-12","arxiv_id":"2404.08627","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-small-base-lms-with-fewer-tokens","slug":"pre-training-small-base-lms-with-fewer-tokens","title":"Inheritune: Training Smaller Yet More Attentive Language Models","date":"2024-04-12","arxiv_id":"2404.08634","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: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sanyalsunny111/llm-inheritune"],"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"]}}}],"record_sha256":"6d09173e1561554d5ec8da3d9e750b851a3fb1cdb32fd313dd554969f8f92bae","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}