{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/attention-dropout/papers/55","list_of":"/method/attention-dropout","method":"Attention Dropout","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":55,"pages_in_order":109,"rows_per_page":100,"rows":[5401,5500],"of":10892,"counts":{"archive_papers_tagged":10892,"with_a_code_link":4634,"where_syntology_ran_a_sample":1270,"not_listed_spam_title":0,"listed":10892,"listed_where_code_ran":1270,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1043,"every_run_a_failure_of_syntologys_instrument":227,"listed_with_a_run_with_no_instrument_failure":1043,"listed_every_run_a_failure_of_syntologys_instrument":227,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/attention-dropout","prev":"/method/attention-dropout/papers/54","next":"/method/attention-dropout/papers/56","papers":[{"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/nl2tl-transforming-natural-languages-to","slug":"nl2tl-transforming-natural-languages-to","title":"NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models","date":"2023-05-12","arxiv_id":"2305.07766","n_code_links":3,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yongchao98/nl2tl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"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":"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":null,"slug":"rnns-representation-nearest-neighbor-search","title":"A Black-Box Attack on Code Models via Representation Nearest Neighbor Search","date":"2023-05-10","arxiv_id":"2305.05896","n_code_links":0,"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":"/paper/an-exploration-of-encoder-decoder-approaches","slug":"an-exploration-of-encoder-decoder-approaches","title":"An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text","date":"2023-05-09","arxiv_id":"2305.05627","n_code_links":1,"syntology":null},{"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":null,"slug":"multi-task-end-to-end-training-improves-1","title":"Multi-Task End-to-End Training Improves Conversational Recommendation","date":"2023-05-08","arxiv_id":"2305.06218","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},{"paper":null,"slug":"on-the-usage-of-continual-learning-for-out-of","title":"On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code","date":"2023-05-06","arxiv_id":"2305.04106","n_code_links":0,"syntology":null},{"paper":"/paper/plan-and-solve-prompting-improving-zero-shot","slug":"plan-and-solve-prompting-improving-zero-shot","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","date":"2023-05-06","arxiv_id":"2305.04091","n_code_links":3,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"0 ran · 2 unverified","official":{"repos":["agi-edgerunners/plan-and-solve-prompting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"pre-training-language-model-as-a-multi","title":"Pre-training Language Model as a Multi-perspective Course Learner","date":"2023-05-06","arxiv_id":"2305.03981","n_code_links":0,"syntology":null},{"paper":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","n_code_links":1,"syntology":null},{"paper":null,"slug":"rhetorical-role-labeling-of-legal-documents","title":"Rhetorical Role Labeling of Legal Documents using Transformers and Graph Neural Networks","date":"2023-05-06","arxiv_id":"2305.04100","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-transformer-language-models-for","title":"Adapting Transformer Language Models for Predictive Typing in Brain-Computer Interfaces","date":"2023-05-05","arxiv_id":"2305.03819","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-the-label-and-noise-an-n-gram-masked","title":"Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking","date":"2023-05-05","arxiv_id":"2305.03314","n_code_links":0,"syntology":null},{"paper":null,"slug":"clac-at-semeval-2023-task-2-comparing-span","title":"CLaC at SemEval-2023 Task 2: Comparing Span-Prediction and Sequence-Labeling approaches for NER","date":"2023-05-05","arxiv_id":"2305.03845","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-the-power-of-bert-in-the-turkish","title":"Harnessing the Power of BERT in the Turkish Clinical Domain: Pretraining Approaches for Limited Data Scenarios","date":"2023-05-05","arxiv_id":"2305.03788","n_code_links":0,"syntology":null},{"paper":"/paper/otter-a-multi-modal-model-with-in-context","slug":"otter-a-multi-modal-model-with-in-context","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","date":"2023-05-05","arxiv_id":"2305.03726","n_code_links":1,"syntology":null},{"paper":null,"slug":"predicting-covid-19-and-pneumonia","title":"Predicting COVID-19 and pneumonia complications from admission texts","date":"2023-05-05","arxiv_id":"2305.03661","n_code_links":0,"syntology":null},{"paper":null,"slug":"simulating-h-p-lovecraft-horror-literature","title":"Simulating H.P. Lovecraft horror literature with the ChatGPT large language model","date":"2023-05-05","arxiv_id":"2305.03429","n_code_links":0,"syntology":null},{"paper":"/paper/using-chatgpt-for-entity-matching","slug":"using-chatgpt-for-entity-matching","title":"Using ChatGPT for Entity Matching","date":"2023-05-05","arxiv_id":"2305.03423","n_code_links":1,"syntology":null},{"paper":"/paper/verify-and-edit-a-knowledge-enhanced-chain-of","slug":"verify-and-edit-a-knowledge-enhanced-chain-of","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","date":"2023-05-05","arxiv_id":"2305.03268","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-automatically-discovered-chain-of-thought","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","date":"2023-05-04","arxiv_id":"2305.02897","n_code_links":0,"syntology":null},{"paper":null,"slug":"automl-gpt-automatic-machine-learning-with","title":"AutoML-GPT: Automatic Machine Learning with GPT","date":"2023-05-04","arxiv_id":"2305.02499","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-pashto-text-classification-using","title":"Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis","date":"2023-05-04","arxiv_id":"2305.03201","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-a-review-on-advancements-and","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","date":"2023-05-04","arxiv_id":"2305.03195","n_code_links":0,"syntology":null},{"paper":"/paper/improving-code-example-recommendations-on","slug":"improving-code-example-recommendations-on","title":"Improving Code Example Recommendations on Informal Documentation Using BERT and Query-Aware LSH: A Comparative Study","date":"2023-05-04","arxiv_id":"2305.03017","n_code_links":1,"syntology":null},{"paper":null,"slug":"language-time-preferences-and-consumer","title":"Can LLMs Capture Human Preferences?","date":"2023-05-04","arxiv_id":"2305.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"late-binding-scholarship-in-the-age-of-ai","title":"Late-Binding Scholarship in the Age of AI: Navigating Legal and Normative Challenges of a New Form of Knowledge Production","date":"2023-05-04","arxiv_id":"2305.11058","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-bert-language-model-for-arabic","title":"Leveraging BERT Language Model for Arabic Long Document Classification","date":"2023-05-04","arxiv_id":"2305.03519","n_code_links":0,"syntology":null},{"paper":"/paper/personallm-investigating-the-ability-of-gpt-3","slug":"personallm-investigating-the-ability-of-gpt-3","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","date":"2023-05-04","arxiv_id":"2305.02547","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":["hjian42/personallm"],"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":null,"slug":"a-novel-plagiarism-detection-approach","title":"A Novel Plagiarism Detection Approach Combining BERT-based Word Embedding, Attention-based LSTMs and an Improved Differential Evolution Algorithm","date":"2023-05-03","arxiv_id":"2305.02374","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-step-by-step-outperforming-larger","slug":"distilling-step-by-step-outperforming-larger","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","date":"2023-05-03","arxiv_id":"2305.02301","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":["google-research/distilling-step-by-step"],"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/entity-tracking-in-language-models","slug":"entity-tracking-in-language-models","title":"Entity Tracking in Language Models","date":"2023-05-03","arxiv_id":"2305.02363","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-bert-and-parsbert-for-analyzing","title":"evaluating bert and parsbert for analyzing persian advertisement data","date":"2023-05-03","arxiv_id":"2305.02426","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-bert-based-scientific-relation","title":"Evaluating BERT-based Scientific Relation Classifiers for Scholarly Knowledge Graph Construction on Digital Library Collections","date":"2023-05-03","arxiv_id":"2305.02291","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-linguistic-properties-of","title":"Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages","date":"2023-05-03","arxiv_id":"2305.02215","n_code_links":0,"syntology":null},{"paper":"/paper/gpt-re-in-context-learning-for-relation","slug":"gpt-re-in-context-learning-for-relation","title":"GPT-RE: In-context Learning for Relation Extraction using Large Language Models","date":"2023-05-03","arxiv_id":"2305.02105","n_code_links":1,"syntology":null},{"paper":null,"slug":"cancer-hallmark-classification-using","title":"Improving Cancer Hallmark Classification with BERT-based Deep Learning Approach","date":"2023-05-02","arxiv_id":"2305.03501","n_code_links":0,"syntology":null},{"paper":"/paper/discern-and-answer-mitigating-the-impact-of","slug":"discern-and-answer-mitigating-the-impact-of","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","date":"2023-05-02","arxiv_id":"2305.01579","n_code_links":1,"syntology":null},{"paper":null,"slug":"freelm-fine-tuning-free-language-model","title":"FreeLM: Fine-Tuning-Free Language Model","date":"2023-05-02","arxiv_id":"2305.01616","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-unleash-the-power-of-large-language","slug":"how-to-unleash-the-power-of-large-language","title":"How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?","date":"2023-05-02","arxiv_id":"2305.01555","n_code_links":2,"syntology":null},{"paper":null,"slug":"new-trends-in-machine-translation-using-large","title":"A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models","date":"2023-05-02","arxiv_id":"2305.01181","n_code_links":0,"syntology":null},{"paper":"/paper/unlimiformer-long-range-transformers-with","slug":"unlimiformer-long-range-transformers-with","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","date":"2023-05-02","arxiv_id":"2305.01625","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["abertsch72/unlimiformer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-meets-definitions-unsupervised-visual","slug":"vision-meets-definitions-unsupervised-visual","title":"Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information","date":"2023-05-02","arxiv_id":"2305.01788","n_code_links":1,"syntology":null},{"paper":null,"slug":"automated-paper-screening-for-clinical","title":"Automated Paper Screening for Clinical Reviews Using Large Language Models","date":"2023-05-01","arxiv_id":"2305.00844","n_code_links":0,"syntology":null},{"paper":null,"slug":"logion-machine-learning-for-greek-philology","title":"Logion: Machine Learning for Greek Philology","date":"2023-05-01","arxiv_id":"2305.01099","n_code_links":0,"syntology":null},{"paper":"/paper/neural-machine-translation-models-with","slug":"neural-machine-translation-models-with","title":"Neural Machine Translation Models with Attention-Based Dropout Layer","date":"2023-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"retrieving-comparative-arguments-using","title":"Retrieving Comparative Arguments using Ensemble Methods and Neural Information Retrieval","date":"2023-05-01","arxiv_id":"2305.01513","n_code_links":0,"syntology":null},{"paper":"/paper/safewebuh-at-semeval-2023-task-11-learning","slug":"safewebuh-at-semeval-2023-task-11-learning","title":"SafeWebUH at SemEval-2023 Task 11: Learning Annotator Disagreement in Derogatory Text: Comparison of Direct Training vs Aggregation","date":"2023-05-01","arxiv_id":"2305.01050","n_code_links":1,"syntology":null},{"paper":"/paper/beyond-classification-financial-reasoning-in","slug":"beyond-classification-financial-reasoning-in","title":"Beyond Classification: Financial Reasoning in State-of-the-Art Language Models","date":"2023-04-30","arxiv_id":"2305.01505","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-the-effectiveness-of-large-language","slug":"exploring-the-effectiveness-of-large-language","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","date":"2023-04-30","arxiv_id":"2305.00418","n_code_links":1,"syntology":null},{"paper":"/paper/how-does-gpt-2-compute-greater-than-1","slug":"how-does-gpt-2-compute-greater-than-1","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","date":"2023-04-30","arxiv_id":"2305.00586","n_code_links":3,"syntology":null},{"paper":"/paper/are-the-best-multilingual-document-embeddings","slug":"are-the-best-multilingual-document-embeddings","title":"Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?","date":"2023-04-28","arxiv_id":"2304.14796","n_code_links":1,"syntology":null},{"paper":"/paper/causal-reasoning-and-large-language-models","slug":"causal-reasoning-and-large-language-models","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","date":"2023-04-28","arxiv_id":"2305.00050","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":["py-why/pywhy-llm"],"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":"/paper/flowtransformer-a-transformer-framework-for","slug":"flowtransformer-a-transformer-framework-for","title":"FlowTransformer: A Transformer Framework for Flow-based Network Intrusion Detection Systems","date":"2023-04-28","arxiv_id":"2304.14746","n_code_links":1,"syntology":null},{"paper":"/paper/towards-automated-circuit-discovery-for-1","slug":"towards-automated-circuit-discovery-for-1","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","date":"2023-04-28","arxiv_id":"2304.14997","n_code_links":4,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["arthurconmy/automatic-circuit-discovery","neelnanda-io/transformerlens"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-better-domain-adaptation-for-self","slug":"towards-better-domain-adaptation-for-self","title":"Towards Better Domain Adaptation for Self-supervised Models: A Case Study of Child ASR","date":"2023-04-28","arxiv_id":"2305.00115","n_code_links":1,"syntology":null},{"paper":null,"slug":"assessing-text-mining-and-technical-analyses","title":"Assessing Text Mining and Technical Analyses on Forecasting Financial Time Series","date":"2023-04-27","arxiv_id":"2304.14544","n_code_links":0,"syntology":null},{"paper":null,"slug":"framing-the-news-from-human-perception-to","title":"Framing the News:From Human Perception to Large Language Model Inferences","date":"2023-04-27","arxiv_id":"2304.14456","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-are-state-of-the-art-1","slug":"large-language-models-are-state-of-the-art-1","title":"ICE-Score: Instructing Large Language Models to Evaluate Code","date":"2023-04-27","arxiv_id":"2304.14317","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["terryyz/llm-code-eval","terryyz/ice-score"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"b4a04eb095d20b5b510e85b670303e50064cba827c5436e4d89fbc1514f7a2b6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}