{"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/41","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":41,"pages_in_order":108,"rows_per_page":100,"rows":[4001,4100],"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/40","next":"/method/weight-decay/papers/42","papers":[{"paper":null,"slug":"teach-me-with-a-whisper-enhancing-large","title":"Teach me with a Whisper: Enhancing Large Language Models for Analyzing Spoken Transcripts using Speech Embeddings","date":"2023-11-13","arxiv_id":"2311.07014","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-complex-to-simple-unraveling-the","title":"From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models","date":"2023-11-12","arxiv_id":"2311.06754","n_code_links":0,"syntology":null},{"paper":null,"slug":"giellm-japanese-general-information","title":"GIELLM: Japanese General Information Extraction Large Language Model Utilizing Mutual Reinforcement Effect","date":"2023-11-12","arxiv_id":"2311.06838","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-and-generative-approaches-for-a","title":"Retrieval and Generative Approaches for a Pregnancy Chatbot in Nepali with Stemmed and Non-Stemmed Data : A Comparative Study","date":"2023-11-12","arxiv_id":"2311.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-explain-teaching-large-language-models","title":"Large Language Models are In-context Teachers for Knowledge Reasoning","date":"2023-11-12","arxiv_id":"2311.06985","n_code_links":0,"syntology":null},{"paper":"/paper/data-contamination-quiz-a-tool-to-detect-and","slug":"data-contamination-quiz-a-tool-to-detect-and","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","date":"2023-11-10","arxiv_id":"2311.06233","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shahriargolchin/dcq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"establishing-performance-baselines-in-fine","title":"Establishing Performance Baselines in Fine-Tuning, Retrieval-Augmented Generation and Soft-Prompting for Non-Specialist LLM Users","date":"2023-11-10","arxiv_id":"2311.05903","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-fine-tuning-chatgpt-for-news","title":"Exploring Fine-tuning ChatGPT for News Recommendation","date":"2023-11-10","arxiv_id":"2311.05850","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimum-norm-interpolation-by-perceptra","title":"Minimum norm interpolation by perceptra: Explicit regularization and implicit bias","date":"2023-11-10","arxiv_id":"2311.06138","n_code_links":0,"syntology":null},{"paper":"/paper/smart-agent-based-modeling-on-the-use-of","slug":"smart-agent-based-modeling-on-the-use-of","title":"Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations","date":"2023-11-10","arxiv_id":"2311.06330","n_code_links":4,"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":["roihn/sabm"],"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/deep-natural-language-feature-learning-for","slug":"deep-natural-language-feature-learning-for","title":"Deep Natural Language Feature Learning for Interpretable Prediction","date":"2023-11-09","arxiv_id":"2311.05754","n_code_links":1,"syntology":null},{"paper":null,"slug":"geoformer-predicting-human-mobility-using","title":"GeoFormer: Predicting Human Mobility using Generative Pre-trained Transformer (GPT)","date":"2023-11-09","arxiv_id":"2311.05092","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-and-prompt-engineering","title":"Large Language Models and Prompt Engineering for Biomedical Query Focused Multi-Document Summarisation","date":"2023-11-09","arxiv_id":"2311.05169","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-artificial-intelligence-technology","title":"Leveraging Artificial Intelligence Technology for Mapping Research to Sustainable Development Goals: A Case Study","date":"2023-11-09","arxiv_id":"2311.16162","n_code_links":0,"syntology":null},{"paper":null,"slug":"logshield-a-transformer-based-apt-detection","title":"LogShield: A Transformer-based APT Detection System Leveraging Self-Attention","date":"2023-11-09","arxiv_id":"2311.05733","n_code_links":0,"syntology":null},{"paper":"/paper/lumos-learning-agents-with-unified-data","slug":"lumos-learning-agents-with-unified-data","title":"Agent Lumos: Unified and Modular Training for Open-Source Language Agents","date":"2023-11-09","arxiv_id":"2311.05657","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["allenai/lumos"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-encoder-decoder-models-for-ai-coaching","slug":"vision-encoder-decoder-models-for-ai-coaching","title":"Vision Encoder-Decoder Models for AI Coaching","date":"2023-11-09","arxiv_id":"2311.16161","n_code_links":2,"syntology":null},{"paper":null,"slug":"dacbert-leveraging-dependency-agreement-for","title":"DACBERT: Leveraging Dependency Agreement for Cost-Efficient Bert Pretraining","date":"2023-11-08","arxiv_id":"2311.04799","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-brasil-at-absapt-2022","slug":"deep-learning-brasil-at-absapt-2022","title":"Deep Learning Brasil at ABSAPT 2022: Portuguese Transformer Ensemble Approaches","date":"2023-11-08","arxiv_id":"2311.05051","n_code_links":1,"syntology":null},{"paper":"/paper/deeplearningbrasil-lt-edi-2023-exploring-deep","slug":"deeplearningbrasil-lt-edi-2023-exploring-deep","title":"DeepLearningBrasil@LT-EDI-2023: Exploring Deep Learning Techniques for Detecting Depression in Social Media Text","date":"2023-11-08","arxiv_id":"2311.05047","n_code_links":1,"syntology":null},{"paper":"/paper/determination-of-toxic-comments-and","slug":"determination-of-toxic-comments-and","title":"Determination of toxic comments and unintended model bias minimization using Deep learning approach","date":"2023-11-08","arxiv_id":"2311.04789","n_code_links":1,"syntology":null},{"paper":"/paper/massive-editing-for-large-language-models-via","slug":"massive-editing-for-large-language-models-via","title":"Massive Editing for Large Language Models via Meta Learning","date":"2023-11-08","arxiv_id":"2311.04661","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["chenmientan/malmen"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pre-training-llms-using-human-like","title":"Pre-training LLMs using human-like development data corpus","date":"2023-11-08","arxiv_id":"2311.04666","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-benchmark-and-contamination-for","slug":"rethinking-benchmark-and-contamination-for","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","date":"2023-11-08","arxiv_id":"2311.04850","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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":["lm-sys/llm-decontaminator"],"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":"enhancing-llm-intelligence-with-arm-rag","title":"Enhancing LLM Intelligence with ARM-RAG: Auxiliary Rationale Memory for Retrieval Augmented Generation","date":"2023-11-07","arxiv_id":"2311.04177","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in","title":"Evaluating Large Language Models in Ophthalmology","date":"2023-11-07","arxiv_id":"2311.04933","n_code_links":0,"syntology":null},{"paper":null,"slug":"identifying-and-mitigating-vulnerabilities-in","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","date":"2023-11-07","arxiv_id":"2311.16153","n_code_links":0,"syntology":null},{"paper":"/paper/locating-cross-task-sequence-continuation","slug":"locating-cross-task-sequence-continuation","title":"Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models","date":"2023-11-07","arxiv_id":"2311.04131","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["apartresearch/seqcont_circuits"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/modelling-sentiment-analysis-llms-and-data","slug":"modelling-sentiment-analysis-llms-and-data","title":"Modelling Sentiment Analysis: LLMs and data augmentation techniques","date":"2023-11-07","arxiv_id":"2311.04139","n_code_links":1,"syntology":null},{"paper":"/paper/neuro-gpt-developing-a-foundation-model-for","slug":"neuro-gpt-developing-a-foundation-model-for","title":"Neuro-GPT: Towards A Foundation Model for EEG","date":"2023-11-07","arxiv_id":"2311.03764","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["wenhui0206/neurogpt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"personality-style-recognition-via-machine","title":"Personality Style Recognition via Machine Learning: Identifying Anaclitic and Introjective Personality Styles from Patients' Speech","date":"2023-11-07","arxiv_id":"2311.04088","n_code_links":0,"syntology":null},{"paper":"/paper/accumulating-word-representations-in-multi","slug":"accumulating-word-representations-in-multi","title":"Accumulating Word Representations in Multi-level Context Integration for ERC Task","date":"2023-11-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/deepinception-hypnotize-large-language-model","slug":"deepinception-hypnotize-large-language-model","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","date":"2023-11-06","arxiv_id":"2311.03191","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tmlr-group/deepinception"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"in-context-learning-for-knowledge-base","title":"In-Context Learning for Knowledge Base Question Answering for Unmanned Systems based on Large Language Models","date":"2023-11-06","arxiv_id":"2311.02956","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-super-mario-absorbing","slug":"language-models-are-super-mario-absorbing","title":"Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch","date":"2023-11-06","arxiv_id":"2311.03099","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yule-buaa/mergelm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unraveling-downstream-gender-bias-from-large","slug":"unraveling-downstream-gender-bias-from-large","title":"Unraveling Downstream Gender Bias from Large Language Models: A Study on AI Educational Writing Assistance","date":"2023-11-06","arxiv_id":"2311.03311","n_code_links":1,"syntology":null},{"paper":"/paper/chata-towards-an-intelligent-question-answer","slug":"chata-towards-an-intelligent-question-answer","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","date":"2023-11-05","arxiv_id":"2311.02775","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-the-potential-of-leading-large","title":"Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions","date":"2023-11-05","arxiv_id":"2311.07582","n_code_links":0,"syntology":null},{"paper":"/paper/extraction-of-atypical-aspects-from-customer","slug":"extraction-of-atypical-aspects-from-customer","title":"Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models","date":"2023-11-05","arxiv_id":"2311.02702","n_code_links":2,"syntology":null},{"paper":null,"slug":"robust-generalization-strategies-for-morpheme","title":"Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context","date":"2023-11-05","arxiv_id":"2311.02777","n_code_links":0,"syntology":null},{"paper":null,"slug":"uid-as-a-guiding-metric-for-automated","title":"UID as a Guiding Metric for Automated Authorship Obfuscation","date":"2023-11-05","arxiv_id":"2312.03709","n_code_links":0,"syntology":null},{"paper":null,"slug":"you-only-forward-once-prediction-and","title":"You Only Forward Once: Prediction and Rationalization in A Single Forward Pass","date":"2023-11-04","arxiv_id":"2311.02344","n_code_links":0,"syntology":null},{"paper":"/paper/automating-governing-knowledge-commons-and","slug":"automating-governing-knowledge-commons-and","title":"Automating Governing Knowledge Commons and Contextual Integrity (GKC-CI) Privacy Policy Annotations with Large Language Models","date":"2023-11-03","arxiv_id":"2311.02192","n_code_links":1,"syntology":null},{"paper":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-free-distillation-of-language-model-by","title":"Data-Free Distillation of Language Model by Text-to-Text Transfer","date":"2023-11-03","arxiv_id":"2311.01689","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-black-box-adversarial-attacks-on","slug":"efficient-black-box-adversarial-attacks-on","title":"Efficient Black-Box Adversarial Attacks on Neural Text Detectors","date":"2023-11-03","arxiv_id":"2311.01873","n_code_links":1,"syntology":null},{"paper":null,"slug":"epidemic-decision-making-system-based","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","date":"2023-11-03","arxiv_id":"2311.01749","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-numerical-reasoning","title":"Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data","date":"2023-11-03","arxiv_id":"2311.02216","n_code_links":0,"syntology":null},{"paper":"/paper/simplifying-transformer-blocks","slug":"simplifying-transformer-blocks","title":"Simplifying Transformer Blocks","date":"2023-11-03","arxiv_id":"2311.01906","n_code_links":1,"syntology":null},{"paper":"/paper/long-story-short-a-summarize-then-search","slug":"long-story-short-a-summarize-then-search","title":"Long Story Short: a Summarize-then-Search Method for Long Video Question Answering","date":"2023-11-02","arxiv_id":"2311.01233","n_code_links":1,"syntology":null},{"paper":null,"slug":"measuring-five-accountable-talk-moves-to","title":"Measuring Five Accountable Talk Moves to Improve Instruction at Scale","date":"2023-11-02","arxiv_id":"2311.10749","n_code_links":0,"syntology":null},{"paper":null,"slug":"server-side-rescoring-of-spoken-entity","title":"Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants","date":"2023-11-02","arxiv_id":"2311.01398","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-improved-transformer-based-model-for","title":"An Improved Transformer-based Model for Detecting Phishing, Spam, and Ham: A Large Language Model Approach","date":"2023-11-01","arxiv_id":"2311.04913","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-reliable-judges-a","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","date":"2023-11-01","arxiv_id":"2311.00681","n_code_links":0,"syntology":null},{"paper":null,"slug":"continuous-training-and-fine-tuning-for","title":"Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering","date":"2023-11-01","arxiv_id":"2311.00204","n_code_links":0,"syntology":null},{"paper":null,"slug":"entity-alignment-method-of-science-and","title":"Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion","date":"2023-11-01","arxiv_id":"2311.00300","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-gpt-powerful-enough-to-analyze-the","title":"Is GPT Powerful Enough to Analyze the Emotions of Memes?","date":"2023-11-01","arxiv_id":"2311.00223","n_code_links":0,"syntology":null},{"paper":"/paper/syntactic-inductive-bias-in-transformer","slug":"syntactic-inductive-bias-in-transformer","title":"Syntactic Inductive Bias in Transformer Language Models: Especially Helpful for Low-Resource Languages?","date":"2023-11-01","arxiv_id":"2311.00268","n_code_links":1,"syntology":null},{"paper":"/paper/unsupervised-lexical-simplification-with","slug":"unsupervised-lexical-simplification-with","title":"Unsupervised Lexical Simplification with Context Augmentation","date":"2023-11-01","arxiv_id":"2311.00310","n_code_links":1,"syntology":null},{"paper":null,"slug":"bertwich-extending-bert-s-capabilities-to","title":"BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text","date":"2023-10-31","arxiv_id":"2311.00116","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-the-token-barrier-chunking-and","title":"Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT","date":"2023-10-31","arxiv_id":"2310.20558","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-solve-verbal","title":"Do large language models solve verbal analogies like children do?","date":"2023-10-31","arxiv_id":"2310.20384","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-gpt-4-pass-the-turing-test","title":"Does GPT-4 pass the Turing test?","date":"2023-10-31","arxiv_id":"2310.20216","n_code_links":0,"syntology":null},{"paper":null,"slug":"eelbert-tiny-models-through-dynamic","title":"EELBERT: Tiny Models through Dynamic Embeddings","date":"2023-10-31","arxiv_id":"2310.20144","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-classification-of-student-help","title":"Efficient Classification of Student Help Requests in Programming Courses Using Large Language Models","date":"2023-10-31","arxiv_id":"2310.20105","n_code_links":0,"syntology":null},{"paper":null,"slug":"fa-team-at-the-ntcir-17-ufo-task","title":"FA Team at the NTCIR-17 UFO Task","date":"2023-10-31","arxiv_id":"2310.20322","n_code_links":0,"syntology":null},{"paper":null,"slug":"gar-meets-rag-paradigm-for-zero-shot","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","date":"2023-10-31","arxiv_id":"2310.20158","n_code_links":0,"syntology":null},{"paper":"/paper/increasing-the-performance-of-cognitively","slug":"increasing-the-performance-of-cognitively","title":"Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building","date":"2023-10-31","arxiv_id":"2310.20589","n_code_links":1,"syntology":null},{"paper":null,"slug":"interactive-multi-fidelity-learning-for-cost","title":"Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision","date":"2023-10-31","arxiv_id":"2310.20153","n_code_links":0,"syntology":null},{"paper":"/paper/psycot-psychological-questionnaire-as","slug":"psycot-psychological-questionnaire-as","title":"PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection","date":"2023-10-31","arxiv_id":"2310.20256","n_code_links":1,"syntology":null},{"paper":null,"slug":"theory-of-mind-in-large-language-models","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","date":"2023-10-31","arxiv_id":"2310.20320","n_code_links":0,"syntology":null},{"paper":"/paper/btrec-bert-based-trajectory-recommendation","slug":"btrec-bert-based-trajectory-recommendation","title":"BTRec: BERT-Based Trajectory Recommendation for Personalized Tours","date":"2023-10-30","arxiv_id":"2310.19886","n_code_links":1,"syntology":null},{"paper":null,"slug":"herd-using-multiple-smaller-llms-to-match-the","title":"Herd: Using multiple, smaller LLMs to match the performances of proprietary, large LLMs via an intelligent composer","date":"2023-10-30","arxiv_id":"2310.19902","n_code_links":0,"syntology":null},{"paper":"/paper/interpretable-by-design-text-classification","slug":"interpretable-by-design-text-classification","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","date":"2023-10-30","arxiv_id":"2310.19660","n_code_links":1,"syntology":null},{"paper":"/paper/jina-embeddings-2-8192-token-general-purpose","slug":"jina-embeddings-2-8192-token-general-purpose","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","date":"2023-10-30","arxiv_id":"2310.19923","n_code_links":2,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/litcab-lightweight-calibration-of-language","slug":"litcab-lightweight-calibration-of-language","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","date":"2023-10-30","arxiv_id":"2310.19208","n_code_links":1,"syntology":null},{"paper":null,"slug":"partial-tensorized-transformers-for-natural","title":"Partial Tensorized Transformers for Natural Language Processing","date":"2023-10-30","arxiv_id":"2310.20077","n_code_links":0,"syntology":null},{"paper":null,"slug":"remember-what-you-did-so-you-know-what-to-do","title":"Remember what you did so you know what to do next","date":"2023-10-30","arxiv_id":"2311.01468","n_code_links":0,"syntology":null},{"paper":"/paper/split-ner-named-entity-recognition-via-two","slug":"split-ner-named-entity-recognition-via-two","title":"Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications","date":"2023-10-30","arxiv_id":"2310.19942","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["c3sr/split-ner"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/synthetic-imitation-edit-feedback-for-factual","slug":"synthetic-imitation-edit-feedback-for-factual","title":"Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization","date":"2023-10-30","arxiv_id":"2310.20033","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 ran (of which 3 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) · 2 unverified","official":{"repos":["seasonyao/learnfromhumanedit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/eticor-corpus-for-analyzing-llms-for","slug":"eticor-corpus-for-analyzing-llms-for","title":"EtiCor: Corpus for Analyzing LLMs for Etiquettes","date":"2023-10-29","arxiv_id":"2310.18974","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-chatbots-to-phishbots-preventing","title":"From Chatbots to PhishBots? -- Preventing Phishing scams created using ChatGPT, Google Bard and Claude","date":"2023-10-29","arxiv_id":"2310.19181","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompt-engineering-and-transformer-based","title":"Prompt-Engineering and Transformer-based Question Generation and Evaluation","date":"2023-10-29","arxiv_id":"2310.18867","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrofitting-light-weight-language-models-for","title":"Retrofitting Light-weight Language Models for Emotions using Supervised Contrastive Learning","date":"2023-10-29","arxiv_id":"2310.18930","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-kernel-surrogates-for-neural","title":"Efficient kernel surrogates for neural network-based regression","date":"2023-10-28","arxiv_id":"2310.18612","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-synergy-of-speculative-decoding-and","title":"The Synergy of Speculative Decoding and Batching in Serving Large Language Models","date":"2023-10-28","arxiv_id":"2310.18813","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-aspect-based","slug":"large-language-models-for-aspect-based","title":"Large language models for aspect-based sentiment analysis","date":"2023-10-27","arxiv_id":"2310.18025","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":["qagentur/absa_llm"],"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/lost-in-translation-found-in-spans","slug":"lost-in-translation-found-in-spans","title":"Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media","date":"2023-10-27","arxiv_id":"2310.18205","n_code_links":1,"syntology":null},{"paper":"/paper/offmix-3l-a-novel-code-mixed-dataset-in","slug":"offmix-3l-a-novel-code-mixed-dataset-in","title":"OffMix-3L: A Novel Code-Mixed Dataset in Bangla-English-Hindi for Offensive Language Identification","date":"2023-10-27","arxiv_id":"2310.18387","n_code_links":1,"syntology":null},{"paper":"/paper/sentmix-3l-a-bangla-english-hindi-code-mixed","slug":"sentmix-3l-a-bangla-english-hindi-code-mixed","title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","date":"2023-10-27","arxiv_id":"2310.18023","n_code_links":1,"syntology":null},{"paper":null,"slug":"style-description-based-text-to-speech-with","title":"Style Description based Text-to-Speech with Conditional Prosodic Layer Normalization based Diffusion GAN","date":"2023-10-27","arxiv_id":"2310.18169","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-resource-management-for-edge-network","title":"Adaptive Resource Management for Edge Network Slicing using Incremental Multi-Agent Deep Reinforcement Learning","date":"2023-10-26","arxiv_id":"2310.17523","n_code_links":0,"syntology":null},{"paper":null,"slug":"arabic-fine-grained-entity-recognition","title":"Arabic Fine-Grained Entity Recognition","date":"2023-10-26","arxiv_id":"2310.17333","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-grade-short-answer-reading","title":"Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset","date":"2023-10-26","arxiv_id":"2310.18373","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedpeat-convergence-of-federated-learning","title":"FedPEAT: Convergence of Federated Learning, Parameter-Efficient Fine Tuning, and Emulator Assisted Tuning for Artificial Intelligence Foundation Models with Mobile Edge Computing","date":"2023-10-26","arxiv_id":"2310.17491","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-transcripts-to-insights-uncovering","title":"From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI","date":"2023-10-26","arxiv_id":"2310.17721","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-gpt-3-5-turbo-for-rhetorical-role","title":"Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases","date":"2023-10-26","arxiv_id":"2310.17413","n_code_links":0,"syntology":null},{"paper":"/paper/in-context-learning-dynamics-with-random","slug":"in-context-learning-dynamics-with-random","title":"In-Context Learning Dynamics with Random Binary Sequences","date":"2023-10-26","arxiv_id":"2310.17639","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":7,"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":["ebigelow/icl-random-binary"],"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":"/paper/lightlm-a-lightweight-deep-and-narrow","slug":"lightlm-a-lightweight-deep-and-narrow","title":"LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation","date":"2023-10-26","arxiv_id":"2310.17488","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongyuanjushi/lightlm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mo-yolo-end-to-end-multiple-object-tracking","title":"DecoderTracker: Decoder-Only Method for Multiple-Object Tracking","date":"2023-10-26","arxiv_id":"2310.17170","n_code_links":0,"syntology":null}],"record_sha256":"ec6331bdf76bc0a1dd1e5fbbf1f57fc922cfd09903f178bfc49ac64cf644f285","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}