{"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/39","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":39,"pages_in_order":108,"rows_per_page":100,"rows":[3801,3900],"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/38","next":"/method/weight-decay/papers/40","papers":[{"paper":"/paper/weaving-pathways-for-justice-with-gpt-llm","slug":"weaving-pathways-for-justice-with-gpt-llm","title":"Weaving Pathways for Justice with GPT: LLM-driven automated drafting of interactive legal applications","date":"2023-12-14","arxiv_id":"2312.09198","n_code_links":1,"syntology":null},{"paper":"/paper/causality-analysis-for-evaluating-the","slug":"causality-analysis-for-evaluating-the","title":"Causality Analysis for Evaluating the Security of Large Language Models","date":"2023-12-13","arxiv_id":"2312.07876","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":6,"n_instrument":1,"unverified":2,"pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["casperllm/casper"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-robotic-navigation-an-evaluation-of","title":"Enhancing Robotic Navigation: An Evaluation of Single and Multi-Objective Reinforcement Learning Strategies","date":"2023-12-13","arxiv_id":"2312.07953","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-are-complex-table","title":"Large Language Models are Complex Table Parsers","date":"2023-12-13","arxiv_id":"2312.11521","n_code_links":0,"syntology":null},{"paper":"/paper/mono3dvg-3d-visual-grounding-in-monocular","slug":"mono3dvg-3d-visual-grounding-in-monocular","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","date":"2023-12-13","arxiv_id":"2312.08022","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhanyang-nwpu/mono3dvg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"native-language-identification-with-large","title":"Native Language Identification with Large Language Models","date":"2023-12-13","arxiv_id":"2312.07819","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-engineering-assisted-malware-dynamic","slug":"prompt-engineering-assisted-malware-dynamic","title":"Prompt Engineering-assisted Malware Dynamic Analysis Using GPT-4","date":"2023-12-13","arxiv_id":"2312.08317","n_code_links":1,"syntology":null},{"paper":"/paper/ai-control-improving-safety-despite","slug":"ai-control-improving-safety-despite","title":"AI Control: Improving Safety Despite Intentional Subversion","date":"2023-12-12","arxiv_id":"2312.06942","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["rgreenblatt/control-evaluations"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"exploring-large-language-models-to-facilitate","title":"Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming","date":"2023-12-12","arxiv_id":"2312.07214","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-retrieval-augmented-generation-rag","slug":"harnessing-retrieval-augmented-generation-rag","title":"Harnessing Retrieval-Augmented Generation (RAG) for Uncovering Knowledge Gaps","date":"2023-12-12","arxiv_id":"2312.07796","n_code_links":1,"syntology":null},{"paper":"/paper/image-content-generation-with-causal","slug":"image-content-generation-with-causal","title":"Image Content Generation with Causal Reasoning","date":"2023-12-12","arxiv_id":"2312.07132","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ieit-agi/mix-shannon"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/multilingual-large-language-models-leak-human","slug":"multilingual-large-language-models-leak-human","title":"Multilingual large language models leak human stereotypes across language boundaries","date":"2023-12-12","arxiv_id":"2312.07141","n_code_links":1,"syntology":null},{"paper":"/paper/perseus-removing-energy-bloat-from-large","slug":"perseus-removing-energy-bloat-from-large","title":"Reducing Energy Bloat in Large Model Training","date":"2023-12-12","arxiv_id":"2312.06902","n_code_links":2,"syntology":null},{"paper":null,"slug":"seopinion-summarization-and-exploration","title":"SEOpinion: Summarization and Exploration Opinion of E-Commerce Websites","date":"2023-12-12","arxiv_id":"2312.14171","n_code_links":0,"syntology":null},{"paper":null,"slug":"sm70-a-large-language-model-for-medical","title":"SM70: A Large Language Model for Medical Devices","date":"2023-12-12","arxiv_id":"2312.06974","n_code_links":0,"syntology":null},{"paper":"/paper/towards-equipping-transformer-with-the","slug":"towards-equipping-transformer-with-the","title":"Towards Equipping Transformer with the Ability of Systematic Compositionality","date":"2023-12-12","arxiv_id":"2312.07280","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-musculoskeletal-disorder-risk","title":"A Natural Language Processing-Based Classification and Mode-Based Ranking of Musculoskeletal Disorder Risk Factors","date":"2023-12-12","arxiv_id":"2312.11517","n_code_links":0,"syntology":null},{"paper":"/paper/can-it-edit-evaluating-the-ability-of-large","slug":"can-it-edit-evaluating-the-ability-of-large","title":"Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions","date":"2023-12-11","arxiv_id":"2312.12450","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nuprl/canitedit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"contrastive-news-and-social-media-linking","title":"Contrastive News and Social Media Linking using BERT for Articles and Tweets across Dual Platforms","date":"2023-12-11","arxiv_id":"2312.07599","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-chatgpt-as-a-question-answering","title":"Evaluating ChatGPT as a Question Answering System: A Comprehensive Analysis and Comparison with Existing Models","date":"2023-12-11","arxiv_id":"2312.07592","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-large-language-models-are-all","title":"Generative Large Language Models Are All-purpose Text Analytics Engines: Text-to-text Learning Is All Your Need","date":"2023-12-11","arxiv_id":"2312.06099","n_code_links":0,"syntology":null},{"paper":null,"slug":"label-smoothing-for-enhanced-text-sentiment","title":"Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification","date":"2023-12-11","arxiv_id":"2312.06522","n_code_links":0,"syntology":null},{"paper":null,"slug":"survey-on-foundation-models-for-prognostics","title":"Survey on Foundation Models for Prognostics and Health Management in Industrial Cyber-Physical Systems","date":"2023-12-11","arxiv_id":"2312.06261","n_code_links":0,"syntology":null},{"paper":"/paper/textual-prompt-guided-image-restoration","slug":"textual-prompt-guided-image-restoration","title":"Textual Prompt Guided Image Restoration","date":"2023-12-11","arxiv_id":"2312.06162","n_code_links":1,"syntology":null},{"paper":null,"slug":"where-exactly-does-contextualization-in-a-plm","title":"Where exactly does contextualization in a PLM happen?","date":"2023-12-11","arxiv_id":"2312.06514","n_code_links":0,"syntology":null},{"paper":null,"slug":"early-chatgpt-user-portrait-through-the-lens","title":"Early ChatGPT User Portrait through the Lens of Data","date":"2023-12-10","arxiv_id":"2312.10078","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-or-retrieval-comparing-knowledge","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","date":"2023-12-10","arxiv_id":"2312.05934","n_code_links":0,"syntology":null},{"paper":null,"slug":"fp8-bert-post-training-quantization-for","title":"FP8-BERT: Post-Training Quantization for Transformer","date":"2023-12-10","arxiv_id":"2312.05725","n_code_links":0,"syntology":null},{"paper":"/paper/gamc-an-unsupervised-method-for-fake-news","slug":"gamc-an-unsupervised-method-for-fake-news","title":"GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking","date":"2023-12-10","arxiv_id":"2312.05739","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-review-of-hybrid-and-ensemble-in-deep","title":"A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processing","date":"2023-12-09","arxiv_id":"2312.05589","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-tuning-for-retrieval-augmented","title":"Context Tuning for Retrieval Augmented Generation","date":"2023-12-09","arxiv_id":"2312.05708","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhanced-e-commerce-attribute-extraction","title":"Enhanced E-Commerce Attribute Extraction: Innovating with Decorative Relation Correction and LLAMA 2.0-Based Annotation","date":"2023-12-09","arxiv_id":"2312.06684","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-medical-specialty-assignment-to","title":"Enhancing Medical Specialty Assignment to Patients using NLP Techniques","date":"2023-12-09","arxiv_id":"2312.05585","n_code_links":0,"syntology":null},{"paper":null,"slug":"hate-speech-and-offensive-content-detection","title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","date":"2023-12-09","arxiv_id":"2312.05671","n_code_links":0,"syntology":null},{"paper":"/paper/labrador-exploring-the-limits-of-masked","slug":"labrador-exploring-the-limits-of-masked","title":"Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data","date":"2023-12-09","arxiv_id":"2312.11502","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["davidbellamy/labrador"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"privacy-preserving-multi-agent-reinforcement","title":"Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chains","date":"2023-12-09","arxiv_id":"2312.05686","n_code_links":0,"syntology":null},{"paper":"/paper/sim-gpt-text-similarity-via-gpt-annotated","slug":"sim-gpt-text-similarity-via-gpt-annotated","title":"Sim-GPT: Text Similarity via GPT Annotated Data","date":"2023-12-09","arxiv_id":"2312.05603","n_code_links":1,"syntology":null},{"paper":null,"slug":"teamwork-dimensions-classification-using-bert","title":"Teamwork Dimensions Classification Using BERT","date":"2023-12-09","arxiv_id":"2312.05483","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-bert-for-point-cloud-pretraining","title":"Cross-BERT for Point Cloud Pretraining","date":"2023-12-08","arxiv_id":"2312.04891","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-limits-of-chatgpt-in-software","title":"Exploring the Limits of ChatGPT in Software Security Applications","date":"2023-12-08","arxiv_id":"2312.05275","n_code_links":0,"syntology":null},{"paper":null,"slug":"finite-horizon-reinforcement-learning-in","title":"Finite Horizon Multi-Agent Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems","date":"2023-12-08","arxiv_id":"2312.04767","n_code_links":0,"syntology":null},{"paper":null,"slug":"illicit-darkweb-classification-via-natural","title":"Illicit Darkweb Classification via Natural-language Processing: Classifying Illicit Content of Webpages based on Textual Information","date":"2023-12-08","arxiv_id":"2312.04944","n_code_links":0,"syntology":null},{"paper":"/paper/inspect-intrinsic-and-systematic-probing","slug":"inspect-intrinsic-and-systematic-probing","title":"INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers","date":"2023-12-08","arxiv_id":"2312.05092","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-interactive-optimization-of-open-source","title":"LLM Interactive Optimization of Open Source Python Libraries -- Case Studies and Generalization","date":"2023-12-08","arxiv_id":"2312.14949","n_code_links":0,"syntology":null},{"paper":null,"slug":"make-them-spill-the-beans-coercive-knowledge","title":"Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs","date":"2023-12-08","arxiv_id":"2312.04782","n_code_links":0,"syntology":null},{"paper":null,"slug":"paperqa-retrieval-augmented-generative-agent","title":"PaperQA: Retrieval-Augmented Generative Agent for Scientific Research","date":"2023-12-08","arxiv_id":"2312.07559","n_code_links":0,"syntology":null},{"paper":null,"slug":"prospective-role-of-foundation-models-in","title":"Prospective Role of Foundation Models in Advancing Autonomous Vehicles","date":"2023-12-08","arxiv_id":"2405.02288","n_code_links":0,"syntology":null},{"paper":null,"slug":"user-aware-prefix-tuning-is-a-good-learner","title":"User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning","date":"2023-12-08","arxiv_id":"2312.04793","n_code_links":0,"syntology":null},{"paper":"/paper/fortify-the-shortest-stave-in-attention","slug":"fortify-the-shortest-stave-in-attention","title":"Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use","date":"2023-12-07","arxiv_id":"2312.04455","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fiorina1212/attention-buckets"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","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":["adrianbzg/tinyroberta-distillation-qa-es"],"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":"on-sarcasm-detection-with-openai-gpt-based","title":"On Sarcasm Detection with OpenAI GPT-based Models","date":"2023-12-07","arxiv_id":"2312.04642","n_code_links":0,"syntology":null},{"paper":null,"slug":"purple-llama-cyberseceval-a-secure-coding","title":"Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models","date":"2023-12-07","arxiv_id":"2312.04724","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-text-to-text-model-for-multilingual","title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-transcription-of-handwritten-old","slug":"automatic-transcription-of-handwritten-old","title":"Automatic Transcription of Handwritten Old Occitan Language","date":"2023-12-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"corporate-bankruptcy-prediction-with-domain","title":"Corporate Bankruptcy Prediction with Domain-Adapted BERT","date":"2023-12-06","arxiv_id":"2312.03194","n_code_links":0,"syntology":null},{"paper":null,"slug":"holmes-towards-distributed-training-across","title":"Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment","date":"2023-12-06","arxiv_id":"2312.03549","n_code_links":0,"syntology":null},{"paper":"/paper/not-all-large-language-models-llms-succumb-to","slug":"not-all-large-language-models-llms-succumb-to","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","date":"2023-12-06","arxiv_id":"2312.03633","n_code_links":1,"syntology":null},{"paper":null,"slug":"understanding-the-role-of-optimization-in","title":"Understanding the Role of Optimization in Double Descent","date":"2023-12-06","arxiv_id":"2312.03951","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hardware-evaluation-framework-for-large","title":"A Hardware Evaluation Framework for Large Language Model Inference","date":"2023-12-05","arxiv_id":"2312.03134","n_code_links":0,"syntology":null},{"paper":"/paper/draft-dense-retrieval-augmented-few-shot","slug":"draft-dense-retrieval-augmented-few-shot","title":"DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework","date":"2023-12-05","arxiv_id":"2312.02532","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-vs-human-for-scientific-reviews-a-dual","title":"GPT vs Human for Scientific Reviews: A Dual Source Review on Applications of ChatGPT in Science","date":"2023-12-05","arxiv_id":"2312.03769","n_code_links":0,"syntology":null},{"paper":null,"slug":"rank-without-gpt-building-gpt-independent","title":"Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models","date":"2023-12-05","arxiv_id":"2312.02969","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-more-unified-in-context-visual","title":"Towards More Unified In-context Visual Understanding","date":"2023-12-05","arxiv_id":"2312.02520","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-large-language-model-llm-security","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","date":"2023-12-04","arxiv_id":"2312.02003","n_code_links":0,"syntology":null},{"paper":null,"slug":"expand-bert-representation-with-visual","title":"Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment","date":"2023-12-04","arxiv_id":"2312.01592","n_code_links":0,"syntology":null},{"paper":null,"slug":"jellyfish-a-large-language-model-for-data","title":"Jellyfish: A Large Language Model for Data Preprocessing","date":"2023-12-04","arxiv_id":"2312.01678","n_code_links":0,"syntology":null},{"paper":"/paper/prompting-disentangled-embeddings-for","slug":"prompting-disentangled-embeddings-for","title":"Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model","date":"2023-12-04","arxiv_id":"2312.01837","n_code_links":1,"syntology":null},{"paper":"/paper/tree-of-attacks-jailbreaking-black-box-llms","slug":"tree-of-attacks-jailbreaking-black-box-llms","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","date":"2023-12-04","arxiv_id":"2312.02119","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":["ricommunity/tap"],"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":"ai-powered-arabic-crossword-puzzle-generation","title":"ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications","date":"2023-12-03","arxiv_id":"2312.01339","n_code_links":0,"syntology":null},{"paper":"/paper/nlebench-norglm-a-comprehensive-empirical","slug":"nlebench-norglm-a-comprehensive-empirical","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","date":"2023-12-03","arxiv_id":"2312.01314","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"0 ran · 4 unverified","official":{"repos":["smartmedia-ai/norglm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"paper":null,"slug":"on-significance-of-subword-tokenization-for","title":"On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi","date":"2023-12-03","arxiv_id":"2312.01306","n_code_links":0,"syntology":null},{"paper":"/paper/a-ripple-in-time-a-discontinuity-in-american","slug":"a-ripple-in-time-a-discontinuity-in-american","title":"A ripple in time: a discontinuity in American history","date":"2023-12-02","arxiv_id":"2312.01185","n_code_links":1,"syntology":null},{"paper":null,"slug":"aspect-level-sentiment-analysis-based-on","title":"Knowledge Graph Enhanced Aspect-Level Sentiment Analysis","date":"2023-12-02","arxiv_id":"2312.10048","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-scoring-of-students-science-writing","title":"Automatic Scoring of Students' Science Writing Using Hybrid Neural Network","date":"2023-12-02","arxiv_id":"2312.03752","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-the-power-of-prompt-based","slug":"harnessing-the-power-of-prompt-based","title":"Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Models","date":"2023-12-02","arxiv_id":"2312.01032","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-zero-shot-text","slug":"large-language-models-are-zero-shot-text","title":"Large Language Models Are Zero-Shot Text Classifiers","date":"2023-12-02","arxiv_id":"2312.01044","n_code_links":1,"syntology":null},{"paper":"/paper/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"applying-large-language-models-and-chain-of","title":"Applying Large Language Models and Chain-of-Thought for Automatic Scoring","date":"2023-11-30","arxiv_id":"2312.03748","n_code_links":0,"syntology":null},{"paper":"/paper/dichotomy-of-early-and-late-phase-implicit","slug":"dichotomy-of-early-and-late-phase-implicit","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","date":"2023-11-30","arxiv_id":"2311.18817","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vfleaking/grokking-dichotomy"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"iag-induction-augmented-generation-framework","title":"IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions","date":"2023-11-30","arxiv_id":"2311.18397","n_code_links":0,"syntology":null},{"paper":"/paper/llvms4protest-harnessing-the-power-of-large","slug":"llvms4protest-harnessing-the-power-of-large","title":"LLVMs4Protest: Harnessing the Power of Large Language and Vision Models for Deciphering Protests in the News","date":"2023-11-30","arxiv_id":"2311.18241","n_code_links":1,"syntology":null},{"paper":"/paper/robust-concept-erasure-via-kernelized-rate-1","slug":"robust-concept-erasure-via-kernelized-rate-1","title":"Robust Concept Erasure via Kernelized Rate-Distortion Maximization","date":"2023-11-30","arxiv_id":"2312.00194","n_code_links":1,"syntology":{"ran":20,"of":21,"n_ran_checked":18,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brcsomnath/kram"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":18,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transfer-learning-across-different-chemical","title":"Transfer Learning across Different Chemical Domains: Virtual Screening of Organic Materials with Deep Learning Models Pretrained on Small Molecule and Chemical Reaction Data","date":"2023-11-30","arxiv_id":"2311.18377","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-natural-language-processing-based-approach","title":"A natural language processing-based approach: mapping human perception by understanding deep semantic features in street view images","date":"2023-11-29","arxiv_id":"2311.17354","n_code_links":0,"syntology":null},{"paper":"/paper/biomedical-knowledge-graph-enhanced-prompt","slug":"biomedical-knowledge-graph-enhanced-prompt","title":"Biomedical knowledge graph-optimized prompt generation for large language models","date":"2023-11-29","arxiv_id":"2311.17330","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["BaranziniLab/KG_RAG"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"enhancing-answer-selection-in-community","title":"Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models","date":"2023-11-29","arxiv_id":"2311.17502","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-the-robustness-of-transformer-based","title":"Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention","date":"2023-11-29","arxiv_id":"2311.17400","n_code_links":0,"syntology":null},{"paper":null,"slug":"rokepg-roberta-and-knowledge-enhancement-for","title":"RoKEPG: RoBERTa and Knowledge Enhancement for Prescription Generation of Traditional Chinese Medicine","date":"2023-11-29","arxiv_id":"2311.17307","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-template-transferable-backdoor-attack","title":"TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4","date":"2023-11-29","arxiv_id":"2311.17429","n_code_links":0,"syntology":null},{"paper":null,"slug":"timelygpt-recurrent-convolutional-transformer","title":"TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare","date":"2023-11-29","arxiv_id":"2312.00817","n_code_links":0,"syntology":null},{"paper":"/paper/turkishbertweet-fast-and-reliable-large","slug":"turkishbertweet-fast-and-reliable-large","title":"TurkishBERTweet: Fast and Reliable Large Language Model for Social Media Analysis","date":"2023-11-29","arxiv_id":"2311.18063","n_code_links":2,"syntology":null},{"paper":"/paper/characterglm-customizing-chinese","slug":"characterglm-customizing-chinese","title":"CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models","date":"2023-11-28","arxiv_id":"2311.16832","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":["thu-coai/characterglm-6b"],"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/chatgpt-s-one-year-anniversary-are-open","slug":"chatgpt-s-one-year-anniversary-are-open","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","date":"2023-11-28","arxiv_id":"2311.16989","n_code_links":1,"syntology":null},{"paper":null,"slug":"cole-a-hierarchical-generation-framework-for","title":"COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design","date":"2023-11-28","arxiv_id":"2311.16974","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-generative-chatbots-based-on","title":"Comparing Generative Chatbots Based on Process Requirements","date":"2023-11-28","arxiv_id":"2312.03741","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-processing-through-transfer","title":"Natural Language Processing Through Transfer Learning: A Case Study on Sentiment Analysis","date":"2023-11-28","arxiv_id":"2311.16965","n_code_links":0,"syntology":null},{"paper":"/paper/seed-bench-2-benchmarking-multimodal-large","slug":"seed-bench-2-benchmarking-multimodal-large","title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models","date":"2023-11-28","arxiv_id":"2311.17092","n_code_links":2,"syntology":null},{"paper":null,"slug":"syntax-informed-interactive-model-for","title":"Syntax-Informed Interactive Model for Comprehensive Aspect-Based Sentiment Analysis","date":"2023-11-28","arxiv_id":"2312.03739","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-social-aware-gaussian-pre-trained-model-for","title":"A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation","date":"2023-11-27","arxiv_id":"2311.15790","n_code_links":0,"syntology":null},{"paper":"/paper/bert-goes-off-topic-investigating-the-domain","slug":"bert-goes-off-topic-investigating-the-domain","title":"BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification","date":"2023-11-27","arxiv_id":"2311.16083","n_code_links":1,"syntology":null}],"record_sha256":"d0ea00ff94c7ee5e9a5a0da63a4b56de5ec390eba04b825860e39337420b20b0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}