{"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/52","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":52,"pages_in_order":108,"rows_per_page":100,"rows":[5101,5200],"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/51","next":"/method/weight-decay/papers/53","papers":[{"paper":null,"slug":"can-nlp-models-correctly-reason-over-contexts","title":"Can NLP Models Correctly Reason Over Contexts that Break the Common Assumptions?","date":"2023-05-20","arxiv_id":"2305.12096","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdjur-br-a-golden-collection-of-legal","title":"CDJUR-BR -- A Golden Collection of Legal Document from Brazilian Justice with Fine-Grained Named Entities","date":"2023-05-20","arxiv_id":"2305.18315","n_code_links":0,"syntology":null},{"paper":"/paper/logicot-logical-chain-of-thought-instruction","slug":"logicot-logical-chain-of-thought-instruction","title":"LogiCoT: Logical Chain-of-Thought Instruction-Tuning","date":"2023-05-20","arxiv_id":"2305.12147","n_code_links":1,"syntology":null},{"paper":null,"slug":"practical-pcg-through-large-language-models","title":"Practical PCG Through Large Language Models","date":"2023-05-20","arxiv_id":"2305.18243","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-the-architectures-like-pointer","slug":"revisiting-the-architectures-like-pointer","title":"Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond","date":"2023-05-20","arxiv_id":"2305.12289","n_code_links":1,"syntology":null},{"paper":null,"slug":"sentfin-1-0-entity-aware-sentiment-analysis","title":"SEntFiN 1.0: Entity-Aware Sentiment Analysis for Financial News","date":"2023-05-20","arxiv_id":"2305.12257","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-sequence-to-sequence-approach-for-arabic","title":"A Sequence-to-Sequence Approach for Arabic Pronoun Resolution","date":"2023-05-19","arxiv_id":"2305.11529","n_code_links":0,"syntology":null},{"paper":null,"slug":"autotrial-prompting-language-models-for","title":"AutoTrial: Prompting Language Models for Clinical Trial Design","date":"2023-05-19","arxiv_id":"2305.11366","n_code_links":0,"syntology":null},{"paper":"/paper/clinical-camel-an-open-source-expert-level","slug":"clinical-camel-an-open-source-expert-level","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","date":"2023-05-19","arxiv_id":"2305.12031","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["bowang-lab/clinical-camel"],"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":"exploring-the-upper-limits-of-text-based","title":"Exploring the Upper Limits of Text-Based Collaborative Filtering Using Large Language Models: Discoveries and Insights","date":"2023-05-19","arxiv_id":"2305.11700","n_code_links":0,"syntology":null},{"paper":null,"slug":"eye-spatialnet-spatial-information-extraction","title":"Eye-SpatialNet: Spatial Information Extraction from Ophthalmology Notes","date":"2023-05-19","arxiv_id":"2305.11948","n_code_links":0,"syntology":null},{"paper":null,"slug":"federated-foundation-models-privacy","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","date":"2023-05-19","arxiv_id":"2305.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-universal-phonetic-representation-in","title":"Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition","date":"2023-05-19","arxiv_id":"2305.11569","n_code_links":0,"syntology":null},{"paper":"/paper/pointgpt-auto-regressively-generative-pre-1","slug":"pointgpt-auto-regressively-generative-pre-1","title":"PointGPT: Auto-regressively Generative Pre-training from Point Clouds","date":"2023-05-19","arxiv_id":"2305.11487","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":6,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["CGuangyan-BIT/PointGPT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-laws-for-language-encoding-models-in","slug":"scaling-laws-for-language-encoding-models-in","title":"Scaling laws for language encoding models in fMRI","date":"2023-05-19","arxiv_id":"2305.11863","n_code_links":1,"syntology":null},{"paper":"/paper/seegull-a-stereotype-benchmark-with-broad-geo","slug":"seegull-a-stereotype-benchmark-with-broad-geo","title":"SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models","date":"2023-05-19","arxiv_id":"2305.11840","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-agreement-a-framework-for-fine-tuning","title":"Self-Agreement: A Framework for Fine-tuning Language Models to Find Agreement among Diverse Opinions","date":"2023-05-19","arxiv_id":"2305.11460","n_code_links":0,"syntology":null},{"paper":null,"slug":"selfzcot-a-self-prompt-zero-shot-cot-from","title":"Hint of Thought prompting: an explainable and zero-shot approach to reasoning tasks with LLMs","date":"2023-05-19","arxiv_id":"2305.11461","n_code_links":0,"syntology":null},{"paper":null,"slug":"ahead-of-time-p-tuning","title":"Ahead-of-Time P-Tuning","date":"2023-05-18","arxiv_id":"2305.10835","n_code_links":0,"syntology":null},{"paper":null,"slug":"aiwriting-relations-between-image-generation","title":"AIwriting: Relations Between Image Generation and Digital Writing","date":"2023-05-18","arxiv_id":"2305.10834","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-machines-and-children-using","title":"Comparing Machines and Children: Using Developmental Psychology Experiments to Assess the Strengths and Weaknesses of LaMDA Responses","date":"2023-05-18","arxiv_id":"2305.11243","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-methods-for-extracting","title":"Deep Learning Methods for Extracting Metaphorical Names of Flowers and Plants","date":"2023-05-18","arxiv_id":"2305.10833","n_code_links":0,"syntology":null},{"paper":"/paper/ditto-a-simple-and-efficient-approach-to","slug":"ditto-a-simple-and-efficient-approach-to","title":"Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings","date":"2023-05-18","arxiv_id":"2305.10786","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-multiple-intent-conditioned-slot","title":"Generalized Multiple Intent Conditioned Slot Filling","date":"2023-05-18","arxiv_id":"2305.11023","n_code_links":0,"syntology":null},{"paper":"/paper/generalized-planning-in-pddl-domains-with","slug":"generalized-planning-in-pddl-domains-with","title":"Generalized Planning in PDDL Domains with Pretrained Large Language Models","date":"2023-05-18","arxiv_id":"2305.11014","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["tomsilver/llm-genplan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/large-language-models-can-be-guided-to-evade","slug":"large-language-models-can-be-guided-to-evade","title":"Large Language Models can be Guided to Evade AI-Generated Text Detection","date":"2023-05-18","arxiv_id":"2305.10847","n_code_links":1,"syntology":null},{"paper":null,"slug":"pdp-parameter-free-differentiable-pruning-is","title":"PDP: Parameter-free Differentiable Pruning is All You Need","date":"2023-05-18","arxiv_id":"2305.11203","n_code_links":0,"syntology":null},{"paper":null,"slug":"trading-syntax-trees-for-wordpieces-target","title":"Trading Syntax Trees for Wordpieces: Target-oriented Opinion Words Extraction with Wordpieces and Aspect Enhancement","date":"2023-05-18","arxiv_id":"2305.11034","n_code_links":0,"syntology":null},{"paper":"/paper/a-quantitative-study-of-nlp-approaches-to","slug":"a-quantitative-study-of-nlp-approaches-to","title":"A quantitative study of NLP approaches to question difficulty estimation","date":"2023-05-17","arxiv_id":"2305.10236","n_code_links":1,"syntology":null},{"paper":"/paper/ad-kd-attribution-driven-knowledge","slug":"ad-kd-attribution-driven-knowledge","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","date":"2023-05-17","arxiv_id":"2305.10010","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brucewsy/ad-kd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/coedit-text-editing-by-task-specific","slug":"coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","n_code_links":1,"syntology":null},{"paper":"/paper/explaining-black-box-text-modules-in-natural","slug":"explaining-black-box-text-modules-in-natural","title":"Explaining black box text modules in natural language with language models","date":"2023-05-17","arxiv_id":"2305.09863","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["csinva/imodelsX","microsoft/automated-explanations"],"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":"from-chocolate-bunny-to-chocolate-crocodile","title":"From chocolate bunny to chocolate crocodile: Do Language Models Understand Noun Compounds?","date":"2023-05-17","arxiv_id":"2305.10568","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-learning-of-hierarchical-tasks","title":"Interactive Learning of Hierarchical Tasks from Dialog with GPT","date":"2023-05-17","arxiv_id":"2305.10349","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-graph-completion-models-are-few","title":"Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs","date":"2023-05-17","arxiv_id":"2305.09858","n_code_links":0,"syntology":null},{"paper":"/paper/m3ke-a-massive-multi-level-multi-subject","slug":"m3ke-a-massive-multi-level-multi-subject","title":"M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models","date":"2023-05-17","arxiv_id":"2305.10263","n_code_links":1,"syntology":null},{"paper":"/paper/smaller-language-models-are-better-black-box","slug":"smaller-language-models-are-better-black-box","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","date":"2023-05-17","arxiv_id":"2305.09859","n_code_links":1,"syntology":null},{"paper":"/paper/solving-cosine-similarity-underestimation","slug":"solving-cosine-similarity-underestimation","title":"Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting","date":"2023-05-17","arxiv_id":"2305.10610","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-gradient-descent-meets-derivative-free","title":"When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario","date":"2023-05-17","arxiv_id":"2305.10013","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-preliminary-analysis-on-the-code-generation","title":"A Preliminary Analysis on the Code Generation Capabilities of GPT-3.5 and Bard AI Models for Java Functions","date":"2023-05-16","arxiv_id":"2305.09402","n_code_links":0,"syntology":null},{"paper":"/paper/berttm-leveraging-contextualized-word","slug":"berttm-leveraging-contextualized-word","title":"CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling","date":"2023-05-16","arxiv_id":"2305.09329","n_code_links":1,"syntology":null},{"paper":"/paper/measuring-stereotypes-using-entity-centric","slug":"measuring-stereotypes-using-entity-centric","title":"Measuring Dimensions of Self-Presentation in Twitter Bios and their Links to Misinformation Sharing","date":"2023-05-16","arxiv_id":"2305.09548","n_code_links":1,"syntology":null},{"paper":"/paper/weight-inherited-distillation-for-task","slug":"weight-inherited-distillation-for-task","title":"Weight-Inherited Distillation for Task-Agnostic BERT Compression","date":"2023-05-16","arxiv_id":"2305.09098","n_code_links":1,"syntology":null},{"paper":"/paper/coreference-aware-double-channel-attention","slug":"coreference-aware-double-channel-attention","title":"Coreference-aware Double-channel Attention Network for Multi-party Dialogue Reading Comprehension","date":"2023-05-15","arxiv_id":"2305.08348","n_code_links":1,"syntology":null},{"paper":"/paper/keras-gpt-copilot-integrating-the-power-of","slug":"keras-gpt-copilot-integrating-the-power-of","title":"Keras GPT Copilot: Integrating the Power of Large Language Models in Deep Learning Model Development","date":"2023-05-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/knowledge-rumination-for-pre-trained-language","slug":"knowledge-rumination-for-pre-trained-language","title":"Knowledge Rumination for Pre-trained Language Models","date":"2023-05-15","arxiv_id":"2305.08732","n_code_links":1,"syntology":null},{"paper":null,"slug":"private-training-set-inspection-in-mlaas","title":"Private Training Set Inspection in MLaaS","date":"2023-05-15","arxiv_id":"2305.09058","n_code_links":0,"syntology":null},{"paper":"/paper/rl4f-generating-natural-language-feedback","slug":"rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","arxiv_id":"2305.08844","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["feyzaakyurek/rl4f"],"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":["found_in_text","official"]}}},{"paper":"/paper/schema-adaptable-knowledge-graph-construction","slug":"schema-adaptable-knowledge-graph-construction","title":"Schema-adaptable Knowledge Graph Construction","date":"2023-05-15","arxiv_id":"2305.08703","n_code_links":1,"syntology":null},{"paper":"/paper/similarity-weighted-construction-of","slug":"similarity-weighted-construction-of","title":"Similarity-weighted Construction of Contextualized Commonsense Knowledge Graphs for Knowledge-intense Argumentation Tasks","date":"2023-05-15","arxiv_id":"2305.08495","n_code_links":1,"syntology":null},{"paper":"/paper/small-models-are-valuable-plug-ins-for-large","slug":"small-models-are-valuable-plug-ins-for-large","title":"Small Models are Valuable Plug-ins for Large Language Models","date":"2023-05-15","arxiv_id":"2305.08848","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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) · 0 unverified","official":{"repos":["JetRunner/SuperICL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/text-classification-via-large-language-models","slug":"text-classification-via-large-language-models","title":"Text Classification via Large Language Models","date":"2023-05-15","arxiv_id":"2305.08377","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":["shannonai/gpt-cls-carp"],"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":"text2gender-a-deep-learning-architecture-for","title":"Text2Gender: A Deep Learning Architecture for Analysis of Blogger's Age and Gender","date":"2023-05-15","arxiv_id":"2305.08633","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-llm-assisted-annotation-for-corpus","title":"Assessing the potential of LLM-assisted annotation for corpus-based pragmatics and discourse analysis: The case of apology","date":"2023-05-15","arxiv_id":"2305.08339","n_code_links":0,"syntology":null},{"paper":"/paper/matsci-nlp-evaluating-scientific-language","slug":"matsci-nlp-evaluating-scientific-language","title":"MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling","date":"2023-05-14","arxiv_id":"2305.08264","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","official":{"repos":["banglab-udem-mila/nlp4matsci-acl23"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/mobile-env-a-universal-platform-for-training","slug":"mobile-env-a-universal-platform-for-training","title":"Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction","date":"2023-05-14","arxiv_id":"2305.08144","n_code_links":2,"syntology":{"ran":11,"of":17,"n_ran_checked":11,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["opendfm/mobile-env-expe","x-lance/mobile-env"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"bridging-history-with-ai-a-comparative","title":"Bridging History with AI A Comparative Evaluation of GPT 3.5, GPT4, and GoogleBARD in Predictive Accuracy and Fact Checking","date":"2023-05-13","arxiv_id":"2305.07868","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-sentinel-distinguishing-human-and-chatgpt","slug":"gpt-sentinel-distinguishing-human-and-chatgpt","title":"GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content","date":"2023-05-13","arxiv_id":"2305.07969","n_code_links":2,"syntology":null},{"paper":"/paper/investigating-emergent-goal-like-behaviour-in","slug":"investigating-emergent-goal-like-behaviour-in","title":"The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games?","date":"2023-05-13","arxiv_id":"2305.07970","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["phelps-sg/llm-cooperation","gitlab.com/sphelps/llm-cooperation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pests-persian-english-cross-lingual-corpus","title":"PESTS: Persian_English Cross Lingual Corpus for Semantic Textual Similarity","date":"2023-05-13","arxiv_id":"2305.07893","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-reason-over-scene-graphs-a-case","title":"Learning to Reason over Scene Graphs: A Case Study of Finetuning GPT-2 into a Robot Language Model for Grounded Task Planning","date":"2023-05-12","arxiv_id":"2305.07716","n_code_links":0,"syntology":null},{"paper":"/paper/tinystories-how-small-can-language-models-be","slug":"tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","arxiv_id":"2305.07759","n_code_links":8,"syntology":{"ran":10,"of":18,"n_ran_checked":8,"n_instrument":2,"unverified":8,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":null,"slug":"when-giant-language-brains-just-aren-t-enough","title":"When Giant Language Brains Just Aren't Enough! Domain Pizzazz with Knowledge Sparkle Dust","date":"2023-05-12","arxiv_id":"2305.07230","n_code_links":0,"syntology":null},{"paper":"/paper/a-general-purpose-multilingual-document","slug":"a-general-purpose-multilingual-document","title":"A General-Purpose Multilingual Document Encoder","date":"2023-05-11","arxiv_id":"2305.07016","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-a","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","date":"2023-05-11","arxiv_id":"2305.10435","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-can-be-used-to","title":"Spear Phishing With Large Language Models","date":"2023-05-11","arxiv_id":"2305.06972","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-practical-robust-reinforcement-learning","title":"On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm","date":"2023-05-11","arxiv_id":"2305.06657","n_code_links":0,"syntology":null},{"paper":null,"slug":"overinformative-question-answering-by-humans","title":"Overinformative Question Answering by Humans and Machines","date":"2023-05-11","arxiv_id":"2305.07151","n_code_links":0,"syntology":null},{"paper":null,"slug":"recommendation-as-instruction-following-a","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","date":"2023-05-11","arxiv_id":"2305.07001","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformers-for-ct-reconstruction-from","title":"Transformers for CT Reconstruction From Monoplanar and Biplanar Radiographs","date":"2023-05-11","arxiv_id":"2305.06965","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-method-to-automate-the-discharge-summary","title":"A Method to Automate the Discharge Summary Hospital Course for Neurology Patients","date":"2023-05-10","arxiv_id":"2305.06416","n_code_links":0,"syntology":null},{"paper":null,"slug":"bits-of-grass-does-gpt-already-know-how-to","title":"Bits of Grass: Does GPT already know how to write like Whitman?","date":"2023-05-10","arxiv_id":"2305.11064","n_code_links":0,"syntology":null},{"paper":null,"slug":"davinci-the-dualist-the-mind-body-divide-in","title":"Davinci the Dualist: the mind-body divide in large language models and in human learners","date":"2023-05-10","arxiv_id":"2305.07667","n_code_links":0,"syntology":null},{"paper":"/paper/enriching-language-models-with-graph-based","slug":"enriching-language-models-with-graph-based","title":"Enriching language models with graph-based context information to better understand textual data","date":"2023-05-10","arxiv_id":"2305.11070","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-medically-accurate-summaries-of","title":"Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models","date":"2023-05-10","arxiv_id":"2305.05982","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-in-biomedical-natural","slug":"large-language-models-in-biomedical-natural","title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","date":"2023-05-10","arxiv_id":"2305.16326","n_code_links":1,"syntology":null},{"paper":"/paper/summarizing-simplifying-and-synthesizing","slug":"summarizing-simplifying-and-synthesizing","title":"Summarizing, Simplifying, and Synthesizing Medical Evidence Using GPT-3 (with Varying Success)","date":"2023-05-10","arxiv_id":"2305.06299","n_code_links":1,"syntology":null},{"paper":"/paper/a-review-of-vision-language-models-and-their","slug":"a-review-of-vision-language-models-and-their","title":"A Review of Vision-Language Models and their Performance on the Hateful Memes Challenge","date":"2023-05-09","arxiv_id":"2305.06159","n_code_links":1,"syntology":null},{"paper":"/paper/alleviating-over-smoothing-for-unsupervised","slug":"alleviating-over-smoothing-for-unsupervised","title":"Alleviating Over-smoothing for Unsupervised Sentence Representation","date":"2023-05-09","arxiv_id":"2305.06154","n_code_links":1,"syntology":{"ran":0,"of":4,"n_ran_checked":0,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"0 ran · 4 unverified","official":{"repos":["nuochenpku/sscl"],"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":"attack-named-entity-recognition-by-entity","title":"Attack Named Entity Recognition by Entity Boundary Interference","date":"2023-05-09","arxiv_id":"2305.05253","n_code_links":0,"syntology":null},{"paper":"/paper/codeie-large-code-generation-models-are","slug":"codeie-large-code-generation-models-are","title":"CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors","date":"2023-05-09","arxiv_id":"2305.05711","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["dasepli/codeie"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/detection-of-depression-on-social-networks","slug":"detection-of-depression-on-social-networks","title":"Detection of depression on social networks using transformers and ensembles","date":"2023-05-09","arxiv_id":"2305.05325","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-agents-in-game-theory-experiments","title":"GPT in Game Theory Experiments","date":"2023-05-09","arxiv_id":"2305.05516","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-nas-neural-architecture-search-with-the","title":"GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model","date":"2023-05-09","arxiv_id":"2305.05351","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-the-effect-of-sub-word","title":"Effects of sub-word segmentation on performance of transformer language models","date":"2023-05-09","arxiv_id":"2305.05480","n_code_links":0,"syntology":null},{"paper":null,"slug":"strae-autoencoding-for-pre-trained-embeddings","title":"StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure","date":"2023-05-09","arxiv_id":"2305.05588","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-automatic-optimisation-model","title":"Towards an Automatic Optimisation Model Generator Assisted with Generative Pre-trained Transformer","date":"2023-05-09","arxiv_id":"2305.05811","n_code_links":0,"syntology":null},{"paper":null,"slug":"coherent-wave-dynamics-and-language","title":"Coherent Wave Dynamics and Language Generation of a Generative Pre-trained Transformer","date":"2023-05-08","arxiv_id":"2305.05061","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-show-decision","title":"Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5","date":"2023-05-08","arxiv_id":"2305.04400","n_code_links":0,"syntology":null},{"paper":"/paper/explanation-based-finetuning-makes-models","slug":"explanation-based-finetuning-makes-models","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","date":"2023-05-08","arxiv_id":"2305.04990","n_code_links":1,"syntology":null},{"paper":null,"slug":"gersteinlab-at-mediqa-chat-2023-clinical-note","title":"GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning","date":"2023-05-08","arxiv_id":"2305.05001","n_code_links":0,"syntology":null},{"paper":"/paper/neurocomparatives-neuro-symbolic-distillation","slug":"neurocomparatives-neuro-symbolic-distillation","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","date":"2023-05-08","arxiv_id":"2305.04978","n_code_links":1,"syntology":null},{"paper":null,"slug":"precog-exploring-the-relation-between","title":"PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models","date":"2023-05-08","arxiv_id":"2305.04673","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-relation-extraction-in-the-era-of","title":"Revisiting Relation Extraction in the era of Large Language Models","date":"2023-05-08","arxiv_id":"2305.05003","n_code_links":0,"syntology":null},{"paper":null,"slug":"unlocking-practical-applications-in-legal","title":"Unlocking Practical Applications in Legal Domain: Evaluation of GPT for Zero-Shot Semantic Annotation of Legal Texts","date":"2023-05-08","arxiv_id":"2305.04417","n_code_links":0,"syntology":null},{"paper":null,"slug":"vulnerability-detection-using-two-stage-deep","title":"Vulnerability Detection Using Two-Stage Deep Learning Models","date":"2023-05-08","arxiv_id":"2305.09673","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-don-t-always-say-what-they-1","slug":"language-models-don-t-always-say-what-they-1","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","date":"2023-05-07","arxiv_id":"2305.04388","n_code_links":2,"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":["milesaturpin/cot-unfaithfulness"],"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":"professional-certification-benchmark-dataset","title":"Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models","date":"2023-05-07","arxiv_id":"2305.05377","n_code_links":0,"syntology":null},{"paper":null,"slug":"stanford-mlab-at-semeval-2023-task-10","title":"Stanford MLab at SemEval-2023 Task 10: Exploring GloVe- and Transformer-Based Methods for the Explainable Detection of Online Sexism","date":"2023-05-07","arxiv_id":"2305.04356","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-neuropsychology-are-large-language","title":"Artificial Neuropsychology: Are Large Language Models Developing Executive Functions?","date":"2023-05-06","arxiv_id":"2305.04134","n_code_links":0,"syntology":null}],"record_sha256":"e07529642b67c8aa648648a1f6275afdbaed83f6b51a9f996674f3fcd125836b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}