{"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/52","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":52,"pages_in_order":109,"rows_per_page":100,"rows":[5101,5200],"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/51","next":"/method/attention-dropout/papers/53","papers":[{"paper":null,"slug":"understanding-telecom-language-through-large","title":"Understanding Telecom Language Through Large Language Models","date":"2023-06-09","arxiv_id":"2306.07933","n_code_links":0,"syntology":null},{"paper":null,"slug":"augmenting-hessians-with-inter-layer","title":"Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization","date":"2023-06-08","arxiv_id":"2306.04879","n_code_links":0,"syntology":null},{"paper":"/paper/bias-against-93-stigmatized-groups-in-masked","slug":"bias-against-93-stigmatized-groups-in-masked","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","date":"2023-06-08","arxiv_id":"2306.05550","n_code_links":1,"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":["mooniem/mlms_bias_stigmas"],"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":"/paper/extensive-evaluation-of-transformer-based","slug":"extensive-evaluation-of-transformer-based","title":"Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extraction","date":"2023-06-08","arxiv_id":"2306.05276","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-language-identification-to-enhance","title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","date":"2023-06-08","arxiv_id":"2306.04964","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-supernets-improving-weight-sharing","slug":"mixture-of-supernets-improving-weight-sharing","title":"Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts","date":"2023-06-08","arxiv_id":"2306.04845","n_code_links":1,"syntology":null},{"paper":null,"slug":"nowj-at-coliee-2023-multi-task-and-ensemble","title":"NOWJ at COLIEE 2023 -- Multi-Task and Ensemble Approaches in Legal Information Processing","date":"2023-06-08","arxiv_id":"2306.04903","n_code_links":0,"syntology":null},{"paper":"/paper/pandalm-an-automatic-evaluation-benchmark-for","slug":"pandalm-an-automatic-evaluation-benchmark-for","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","date":"2023-06-08","arxiv_id":"2306.05087","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["weopenml/pandalm"],"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":["listed","official"]}}},{"paper":"/paper/prefer-to-classify-improving-text-classifiers","slug":"prefer-to-classify-improving-text-classifiers","title":"Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning","date":"2023-06-08","arxiv_id":"2306.04925","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":["minnesotanlp/p2c"],"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":null,"slug":"the-adaio-system-at-the-bea-2023-shared-task","title":"The ADAIO System at the BEA-2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-08","arxiv_id":"2306.05360","n_code_links":0,"syntology":null},{"paper":"/paper/toolalpaca-generalized-tool-learning-for","slug":"toolalpaca-generalized-tool-learning-for","title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","date":"2023-06-08","arxiv_id":"2306.05301","n_code_links":3,"syntology":{"ran":5,"of":8,"n_ran_checked":5,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["tangqiaoyu/ToolAlpaca"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/check-me-if-you-can-detecting-chatgpt","slug":"check-me-if-you-can-detecting-chatgpt","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","date":"2023-06-07","arxiv_id":"2306.05524","n_code_links":2,"syntology":null},{"paper":"/paper/good-data-large-data-or-no-data-comparing","slug":"good-data-large-data-or-no-data-comparing","title":"Good Data, Large Data, or No Data? Comparing Three Approaches in Developing Research Aspect Classifiers for Biomedical Papers","date":"2023-06-07","arxiv_id":"2306.04820","n_code_links":1,"syntology":null},{"paper":null,"slug":"gpt-self-supervision-for-a-better-data","title":"GPT Self-Supervision for a Better Data Annotator","date":"2023-06-07","arxiv_id":"2306.04349","n_code_links":0,"syntology":null},{"paper":null,"slug":"personality-testing-of-gpt-3-limited-temporal","title":"Personality testing of Large Language Models: Limited temporal stability, but highlighted prosociality","date":"2023-06-07","arxiv_id":"2306.04308","n_code_links":0,"syntology":null},{"paper":null,"slug":"sciencebenchmark-a-complex-real-world","title":"ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems","date":"2023-06-07","arxiv_id":"2306.04743","n_code_links":0,"syntology":null},{"paper":"/paper/the-two-word-test-a-semantic-benchmark-for","slug":"the-two-word-test-a-semantic-benchmark-for","title":"The Two Word Test: A Semantic Benchmark for Large Language Models","date":"2023-06-07","arxiv_id":"2306.04610","n_code_links":1,"syntology":null},{"paper":"/paper/an-empirical-analysis-of-parameter-efficient","slug":"an-empirical-analysis-of-parameter-efficient","title":"An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models","date":"2023-06-06","arxiv_id":"2306.04067","n_code_links":1,"syntology":null},{"paper":"/paper/certified-reasoning-with-language-models","slug":"certified-reasoning-with-language-models","title":"Certified Deductive Reasoning with Language Models","date":"2023-06-06","arxiv_id":"2306.04031","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":null}},{"paper":null,"slug":"detecting-human-rights-violations-on-social","title":"Detecting Human Rights Violations on Social Media during Russia-Ukraine War","date":"2023-06-06","arxiv_id":"2306.05370","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-translation-refinement-with-large","title":"Iterative Translation Refinement with Large Language Models","date":"2023-06-06","arxiv_id":"2306.03856","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-acquisition-do-children-and-language","title":"Language acquisition: do children and language models follow similar learning stages?","date":"2023-06-06","arxiv_id":"2306.03586","n_code_links":0,"syntology":null},{"paper":"/paper/leace-perfect-linear-concept-erasure-in","slug":"leace-perfect-linear-concept-erasure-in","title":"LEACE: Perfect linear concept erasure in closed form","date":"2023-06-06","arxiv_id":"2306.03819","n_code_links":2,"syntology":{"ran":12,"of":14,"n_ran_checked":10,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["eleutherai/concept-erasure"],"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":["listed","official"]}}},{"paper":"/paper/on-the-difference-of-bert-style-and-clip","slug":"on-the-difference-of-bert-style-and-clip","title":"On the Difference of BERT-style and CLIP-style Text Encoders","date":"2023-06-06","arxiv_id":"2306.03678","n_code_links":1,"syntology":null},{"paper":null,"slug":"triggering-multi-hop-reasoning-for-question","title":"Triggering Multi-Hop Reasoning for Question Answering in Language Models using Soft Prompts and Random Walks","date":"2023-06-06","arxiv_id":"2306.04009","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-syntactic-generalization-capacity","title":"Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion","date":"2023-06-05","arxiv_id":"2306.03055","n_code_links":0,"syntology":null},{"paper":null,"slug":"chatgpt-as-a-mapping-assistant-a-novel-method","title":"ChatGPT as a mapping assistant: A novel method to enrich maps with generative AI and content derived from street-level photographs","date":"2023-06-05","arxiv_id":"2306.03204","n_code_links":0,"syntology":null},{"paper":"/paper/comet-learning-cardinality-constrained","slug":"comet-learning-cardinality-constrained","title":"COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search","date":"2023-06-05","arxiv_id":"2306.02824","n_code_links":2,"syntology":null},{"paper":null,"slug":"efficient-gpt-model-pre-training-using-tensor","title":"Efficient GPT Model Pre-training using Tensor Train Matrix Representation","date":"2023-06-05","arxiv_id":"2306.02697","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-scientific-debt-in-nlp-a-case-for-more","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","date":"2023-06-05","arxiv_id":"2306.02870","n_code_links":0,"syntology":null},{"paper":null,"slug":"stack-over-flowing-with-results-the-case-for","title":"Skill over Scale: The Case for Medium, Domain-Specific Models for SE","date":"2023-06-05","arxiv_id":"2306.03268","n_code_links":0,"syntology":null},{"paper":"/paper/using-sequences-of-life-events-to-predict","slug":"using-sequences-of-life-events-to-predict","title":"Using Sequences of Life-events to Predict Human Lives","date":"2023-06-05","arxiv_id":"2306.03009","n_code_links":2,"syntology":null},{"paper":"/paper/auto-gpt-for-online-decision-making","slug":"auto-gpt-for-online-decision-making","title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","date":"2023-06-04","arxiv_id":"2306.02224","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":5,"n_instrument":1,"unverified":5,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["younghuman/llmagent"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/detector-guidance-for-multi-object-text-to","slug":"detector-guidance-for-multi-object-text-to","title":"Detector Guidance for Multi-Object Text-to-Image Generation","date":"2023-06-04","arxiv_id":"2306.02236","n_code_links":1,"syntology":null},{"paper":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","n_code_links":0,"syntology":null},{"paper":"/paper/spellmapper-a-non-autoregressive-neural","slug":"spellmapper-a-non-autoregressive-neural","title":"SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappings","date":"2023-06-04","arxiv_id":"2306.02317","n_code_links":1,"syntology":null},{"paper":null,"slug":"financial-sentiment-analysis-using-finbert","title":"Financial sentiment analysis using FinBERT with application in predicting stock movement","date":"2023-06-03","arxiv_id":"2306.02136","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilegalpile-a-689gb-multilingual-legal","title":"MultiLegalPile: A 689GB Multilingual Legal Corpus","date":"2023-06-03","arxiv_id":"2306.02069","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-coding-social-science-datasets-with-1","title":"Towards Coding Social Science Datasets with Language Models","date":"2023-06-03","arxiv_id":"2306.02177","n_code_links":0,"syntology":null},{"paper":null,"slug":"5ider-unified-query-rewriting-for-steering","title":"5IDER: Unified Query Rewriting for Steering, Intent Carryover, Disfluencies, Entity Carryover and Repair","date":"2023-06-02","arxiv_id":"2306.01855","n_code_links":0,"syntology":null},{"paper":"/paper/can-contextual-biasing-remain-effective-with","slug":"can-contextual-biasing-remain-effective-with","title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","date":"2023-06-02","arxiv_id":"2306.01942","n_code_links":1,"syntology":null},{"paper":null,"slug":"concurrent-classifier-error-detection-cced-in","title":"Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems","date":"2023-06-02","arxiv_id":"2306.01820","n_code_links":0,"syntology":null},{"paper":null,"slug":"establishment-of-nlp-based-greenwashing","title":"Establishment of NLP-Based Greenwashing Pattern Detection Service","date":"2023-06-02","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/gateon-an-unsupervised-method-for-large-scale","slug":"gateon-an-unsupervised-method-for-large-scale","title":"Context selectivity with dynamic availability enables lifelong continual learning","date":"2023-06-02","arxiv_id":"2306.01690","n_code_links":1,"syntology":null},{"paper":null,"slug":"word-embeddings-for-banking-industry","title":"Word Embeddings for Banking Industry","date":"2023-06-02","arxiv_id":"2306.01807","n_code_links":0,"syntology":null},{"paper":"/paper/adapting-pre-trained-language-models-to","slug":"adapting-pre-trained-language-models-to","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","date":"2023-06-01","arxiv_id":"2306.00409","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-glossary-of-clinical-terminology-a","title":"Automatic Glossary of Clinical Terminology: a Large-Scale Dictionary of Biomedical Definitions Generated from Ontological Knowledge","date":"2023-06-01","arxiv_id":"2306.00665","n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-the-performance-of-transformer","title":"Boosting the Performance of Transformer Architectures for Semantic Textual Similarity","date":"2023-06-01","arxiv_id":"2306.00708","n_code_links":0,"syntology":null},{"paper":"/paper/column-type-annotation-using-chatgpt","slug":"column-type-annotation-using-chatgpt","title":"Column Type Annotation using ChatGPT","date":"2023-06-01","arxiv_id":"2306.00745","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-programming-etextbooks-with-chatgpt","title":"Enhancing Programming eTextbooks with ChatGPT Generated Counterfactual-Thinking-Inspired Questions","date":"2023-06-01","arxiv_id":"2306.00551","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-engineering-based-detection-of-buffer","title":"Feature Engineering-Based Detection of Buffer Overflow Vulnerability in Source Code Using Neural Networks","date":"2023-06-01","arxiv_id":"2306.07981","n_code_links":0,"syntology":null},{"paper":"/paper/make-pre-trained-model-reversible-from-1","slug":"make-pre-trained-model-reversible-from-1","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","date":"2023-06-01","arxiv_id":"2306.00477","n_code_links":1,"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":["baohaoliao/mefts"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/multi-dimensional-evaluation-of-text","slug":"multi-dimensional-evaluation-of-text","title":"Multi-Dimensional Evaluation of Text Summarization with In-Context Learning","date":"2023-06-01","arxiv_id":"2306.01200","n_code_links":1,"syntology":null},{"paper":null,"slug":"systematic-evaluation-of-gpt-3-for-zero-shot","title":"Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation","date":"2023-06-01","arxiv_id":"2306.01183","n_code_links":0,"syntology":null},{"paper":null,"slug":"topex-topic-based-explanations-for-model","title":"TopEx: Topic-based Explanations for Model Comparison","date":"2023-06-01","arxiv_id":"2306.00976","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-neural-architecture-search-for","slug":"training-free-neural-architecture-search-for","title":"Training-free Neural Architecture Search for RNNs and Transformers","date":"2023-06-01","arxiv_id":"2306.00288","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aaronserianni/training-free-nas"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ucas-iie-nlp-at-semeval-2023-task-12","slug":"ucas-iie-nlp-at-semeval-2023-task-12","title":"UCAS-IIE-NLP at SemEval-2023 Task 12: Enhancing Generalization of Multilingual BERT for Low-resource Sentiment Analysis","date":"2023-06-01","arxiv_id":"2306.01093","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-extractive-question-answering-system","title":"Building Extractive Question Answering System to Support Human-AI Health Coaching Model for Sleep Domain","date":"2023-05-31","arxiv_id":"2305.19707","n_code_links":0,"syntology":null},{"paper":null,"slug":"catalysis-distillation-neural-network-for-the","title":"Catalysis distillation neural network for the few shot open catalyst challenge","date":"2023-05-31","arxiv_id":"2305.19545","n_code_links":0,"syntology":null},{"paper":"/paper/deepmerge-deep-learning-based-region-merging","slug":"deepmerge-deep-learning-based-region-merging","title":"DeepMerge: Deep-Learning-Based Region-Merging for Image Segmentation","date":"2023-05-31","arxiv_id":"2305.19787","n_code_links":1,"syntology":null},{"paper":null,"slug":"evaluating-gpt-s-programming-capability","title":"Evaluating GPT's Programming Capability through CodeWars' Katas","date":"2023-05-31","arxiv_id":"2306.01784","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-emergence-of-deductive","title":"Examining the Emergence of Deductive Reasoning in Generative Language Models","date":"2023-05-31","arxiv_id":"2306.01009","n_code_links":0,"syntology":null},{"paper":"/paper/explanations-as-features-llm-based-features","slug":"explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","n_code_links":3,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["XiaoxinHe/TAPE","xiaoxinhe/tape_arxiv_2023"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-base-question-answering-for-space","slug":"knowledge-base-question-answering-for-space","title":"Knowledge Base Question Answering for Space Debris Queries","date":"2023-05-31","arxiv_id":"2305.19734","n_code_links":1,"syntology":null},{"paper":"/paper/xphonebert-a-pre-trained-multilingual-model","slug":"xphonebert-a-pre-trained-multilingual-model","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","date":"2023-05-31","arxiv_id":"2305.19709","n_code_links":2,"syntology":{"ran":14,"of":18,"n_ran_checked":14,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vinairesearch/xphonebert"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"does-conceptual-representation-require","title":"Does Conceptual Representation Require Embodiment? Insights From Large Language Models","date":"2023-05-30","arxiv_id":"2305.19103","n_code_links":0,"syntology":null},{"paper":null,"slug":"explaining-hate-speech-classification-with","title":"Explaining Hate Speech Classification with Model Agnostic Methods","date":"2023-05-30","arxiv_id":"2306.00021","n_code_links":0,"syntology":null},{"paper":null,"slug":"generate-then-select-open-ended-visual","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","date":"2023-05-30","arxiv_id":"2305.18842","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-models-in-construction-industry","title":"GPT Models in Construction Industry: Opportunities, Limitations, and a Use Case Validation","date":"2023-05-30","arxiv_id":"2305.18997","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-learning-for-recognizing-stress-and","title":"Multitask learning for recognizing stress and depression in social media","date":"2023-05-30","arxiv_id":"2305.18907","n_code_links":0,"syntology":null},{"paper":null,"slug":"prequant-a-task-agnostic-quantization","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","date":"2023-05-30","arxiv_id":"2306.00014","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-multilingual-news-clustering","title":"Research on Multilingual News Clustering Based on Cross-Language Word Embeddings","date":"2023-05-30","arxiv_id":"2305.18880","n_code_links":0,"syntology":null},{"paper":"/paper/scone-benchmarking-negation-reasoning-in","slug":"scone-benchmarking-negation-reasoning-in","title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","date":"2023-05-30","arxiv_id":"2305.19426","n_code_links":1,"syntology":null},{"paper":null,"slug":"seeing-seeds-beyond-weeds-green-teaming","title":"Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses","date":"2023-05-30","arxiv_id":"2306.03097","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-summarization-as-augmentation-for","title":"Abstractive Summarization as Augmentation for Document-Level Event Detection","date":"2023-05-29","arxiv_id":"2305.18023","n_code_links":0,"syntology":null},{"paper":"/paper/check-covid-fact-checking-covid-19-news","slug":"check-covid-fact-checking-covid-19-news","title":"Check-COVID: Fact-Checking COVID-19 News Claims with Scientific Evidence","date":"2023-05-29","arxiv_id":"2305.18265","n_code_links":1,"syntology":null},{"paper":null,"slug":"coeditor-leveraging-contextual-changes-for","title":"Coeditor: Leveraging Contextual Changes for Multi-round Code Auto-editing","date":"2023-05-29","arxiv_id":"2305.18584","n_code_links":0,"syntology":null},{"paper":"/paper/do-large-language-models-know-what-they-don-t","slug":"do-large-language-models-know-what-they-don-t","title":"Do Large Language Models Know What They Don't Know?","date":"2023-05-29","arxiv_id":"2305.18153","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":["yinzhangyue/selfaware"],"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":"exploring-effectiveness-of-gpt-3-in","title":"Exploring Effectiveness of GPT-3 in Grammatical Error Correction: A Study on Performance and Controllability in Prompt-Based Methods","date":"2023-05-29","arxiv_id":"2305.18156","n_code_links":0,"syntology":null},{"paper":"/paper/from-adversarial-arms-race-to-model-centric","slug":"from-adversarial-arms-race-to-model-centric","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","date":"2023-05-29","arxiv_id":"2305.18503","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":["thunlp/robtest"],"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/how-effective-are-neural-networks-for-fixing","slug":"how-effective-are-neural-networks-for-fixing","title":"How Effective Are Neural Networks for Fixing Security Vulnerabilities","date":"2023-05-29","arxiv_id":"2305.18607","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lin-tan/llm-vul"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lm-cppf-paraphrasing-guided-data-augmentation","slug":"lm-cppf-paraphrasing-guided-data-augmentation","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","date":"2023-05-29","arxiv_id":"2305.18169","n_code_links":1,"syntology":null},{"paper":"/paper/marked-personas-using-natural-language","slug":"marked-personas-using-natural-language","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","date":"2023-05-29","arxiv_id":"2305.18189","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 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["myracheng/markedpersonas"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"processgpt-transforming-business-process","title":"ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence","date":"2023-05-29","arxiv_id":"2306.01771","n_code_links":0,"syntology":null},{"paper":null,"slug":"slimfit-memory-efficient-fine-tuning-of","title":"SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics","date":"2023-05-29","arxiv_id":"2305.18513","n_code_links":0,"syntology":null},{"paper":"/paper/syntax-and-semantics-meet-in-the-middle","slug":"syntax-and-semantics-meet-in-the-middle","title":"Syntax and Semantics Meet in the \"Middle\": Probing the Syntax-Semantics Interface of LMs Through Agentivity","date":"2023-05-29","arxiv_id":"2305.18185","n_code_links":1,"syntology":null},{"paper":"/paper/test-time-training-on-nearest-neighbors-for","slug":"test-time-training-on-nearest-neighbors-for","title":"Test-Time Training on Nearest Neighbors for Large Language Models","date":"2023-05-29","arxiv_id":"2305.18466","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["socialfoundations/tttlm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transformer-language-models-handle-word","title":"Transformer Language Models Handle Word Frequency in Prediction Head","date":"2023-05-29","arxiv_id":"2305.18294","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-language-barriers-with-a-leap","title":"Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs","date":"2023-05-28","arxiv_id":"2305.17740","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-gpt-3-generated-explanations-for","slug":"evaluating-gpt-3-generated-explanations-for","title":"Evaluating GPT-3 Generated Explanations for Hateful Content Moderation","date":"2023-05-28","arxiv_id":"2305.17680","n_code_links":1,"syntology":null},{"paper":"/paper/generating-edu-extracts-for-plan-guided","slug":"generating-edu-extracts-for-plan-guided","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","date":"2023-05-28","arxiv_id":"2305.17779","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":0,"n_instrument":6,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["griff4692/edu-sum"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/knowledge-augmented-reasoning-distillation-1","slug":"knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":3,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nardien/kard"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/kosbi-a-dataset-for-mitigating-social-bias","slug":"kosbi-a-dataset-for-mitigating-social-bias","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","date":"2023-05-28","arxiv_id":"2305.17701","n_code_links":1,"syntology":null},{"paper":"/paper/mitigating-label-biases-for-in-context","slug":"mitigating-label-biases-for-in-context","title":"Mitigating Label Biases for In-context Learning","date":"2023-05-28","arxiv_id":"2305.19148","n_code_links":1,"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":["fywalter/label-bias"],"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/rethinking-masked-language-modeling-for","slug":"rethinking-masked-language-modeling-for","title":"Rethinking Masked Language Modeling for Chinese Spelling Correction","date":"2023-05-28","arxiv_id":"2305.17721","n_code_links":1,"syntology":null},{"paper":"/paper/square-a-large-scale-dataset-of-sensitive","slug":"square-a-large-scale-dataset-of-sensitive","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","date":"2023-05-28","arxiv_id":"2305.17696","n_code_links":1,"syntology":null},{"paper":null,"slug":"transfer-learning-for-power-outage-detection","title":"Transfer Learning for Power Outage Detection Task with Limited Training Data","date":"2023-05-28","arxiv_id":"2305.17817","n_code_links":0,"syntology":null},{"paper":"/paper/an-investigation-into-the-effects-of-pre","slug":"an-investigation-into-the-effects-of-pre","title":"Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making","date":"2023-05-27","arxiv_id":"2305.17588","n_code_links":1,"syntology":null},{"paper":null,"slug":"complementary-and-integrative-health-lexicon","title":"Complementary and Integrative Health Lexicon (CIHLex) and Entity Recognition in the Literature","date":"2023-05-27","arxiv_id":"2305.17353","n_code_links":0,"syntology":null},{"paper":"/paper/dna-gpt-divergent-n-gram-analysis-for","slug":"dna-gpt-divergent-n-gram-analysis-for","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","date":"2023-05-27","arxiv_id":"2305.17359","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":["xianjun-yang/dna-gpt"],"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"]}}}],"record_sha256":"0049bbb14f17675b4541a65c05ce84aee5c0ae314c0b0a832d6bf20822b05841","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}