{"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/51","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":51,"pages_in_order":109,"rows_per_page":100,"rows":[5001,5100],"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/50","next":"/method/attention-dropout/papers/52","papers":[{"paper":null,"slug":"mat-mixed-strategy-game-of-adversarial","title":"MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning","date":"2023-06-27","arxiv_id":"2306.15826","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparseoptimizer-sparsify-language-models","title":"SparseOptimizer: Sparsify Language Models through Moreau-Yosida Regularization and Accelerate via Compiler Co-design","date":"2023-06-27","arxiv_id":"2306.15656","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-the-power-of-user-reviews","title":"Unleashing the Power of User Reviews: Exploring Airline Choices at Catania Airport, Italy","date":"2023-06-27","arxiv_id":"2306.15541","n_code_links":0,"syntology":null},{"paper":"/paper/constraint-aware-and-ranking-distilled-token","slug":"constraint-aware-and-ranking-distilled-token","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","date":"2023-06-26","arxiv_id":"2306.14393","n_code_links":1,"syntology":null},{"paper":null,"slug":"exploring-the-robustness-of-large-language","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","date":"2023-06-26","arxiv_id":"2306.14583","n_code_links":0,"syntology":null},{"paper":"/paper/longcoder-a-long-range-pre-trained-language","slug":"longcoder-a-long-range-pre-trained-language","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","date":"2023-06-26","arxiv_id":"2306.14893","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":["microsoft/CodeBERT"],"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":"addressing-cold-start-problem-for-end-to-end","title":"Addressing Cold Start Problem for End-to-end Automatic Speech Scoring","date":"2023-06-25","arxiv_id":"2306.14310","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-design-by-integrating-a-large-pre","title":"Interactive Design by Integrating a Large Pre-Trained Language Model and Building Information Modeling","date":"2023-06-25","arxiv_id":"2306.14165","n_code_links":0,"syntology":null},{"paper":null,"slug":"let-s-do-a-thought-experiment-using","title":"Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning","date":"2023-06-25","arxiv_id":"2306.14308","n_code_links":0,"syntology":null},{"paper":null,"slug":"revolutionizing-cyber-threat-detection-with","title":"Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices","date":"2023-06-25","arxiv_id":"2306.14263","n_code_links":0,"syntology":null},{"paper":null,"slug":"switch-bert-learning-to-model-multimodal","title":"Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input","date":"2023-06-25","arxiv_id":"2306.14182","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-pre-trained-language-models-for","title":"Comparison of Pre-trained Language Models for Turkish Address Parsing","date":"2023-06-24","arxiv_id":"2306.13947","n_code_links":0,"syntology":null},{"paper":null,"slug":"ierl-interpretable-ensemble-representation","title":"IERL: Interpretable Ensemble Representation Learning -- Combining CrowdSourced Knowledge and Distributed Semantic Representations","date":"2023-06-24","arxiv_id":"2306.13865","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-pre-training-truly-better-than-meta","title":"Is Pre-training Truly Better Than Meta-Learning?","date":"2023-06-24","arxiv_id":"2306.13841","n_code_links":0,"syntology":null},{"paper":"/paper/l3cube-mahasent-md-a-multi-domain-marathi","slug":"l3cube-mahasent-md-a-multi-domain-marathi","title":"L3Cube-MahaSent-MD: A Multi-domain Marathi Sentiment Analysis Dataset and Transformer Models","date":"2023-06-24","arxiv_id":"2306.13888","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-as-sous-chefs-revising","slug":"large-language-models-as-sous-chefs-revising","title":"Large Language Models as Sous Chefs: Revising Recipes with GPT-3","date":"2023-06-24","arxiv_id":"2306.13986","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-sequence-models-for-sequential-decision","title":"Large Sequence Models for Sequential Decision-Making: A Survey","date":"2023-06-24","arxiv_id":"2306.13945","n_code_links":0,"syntology":null},{"paper":"/paper/math-word-problem-solving-by-generating","slug":"math-word-problem-solving-by-generating","title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","date":"2023-06-24","arxiv_id":"2306.13899","n_code_links":1,"syntology":null},{"paper":"/paper/my-boli-code-mixed-marathi-english-corpora","slug":"my-boli-code-mixed-marathi-english-corpora","title":"My Boli: Code-mixed Marathi-English Corpora, Pretrained Language Models and Evaluation Benchmarks","date":"2023-06-24","arxiv_id":"2306.14030","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-uses-of-large-language-models-to","title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","date":"2023-06-24","arxiv_id":"2306.14062","n_code_links":0,"syntology":null},{"paper":null,"slug":"partitioning-guided-k-means-extreme-empty","title":"Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression","date":"2023-06-24","arxiv_id":"2306.14031","n_code_links":0,"syntology":null},{"paper":null,"slug":"abstractive-text-summarization-for-resumes","title":"Abstractive Text Summarization for Resumes With Cutting Edge NLP Transformers and LSTM","date":"2023-06-23","arxiv_id":"2306.13315","n_code_links":0,"syntology":null},{"paper":null,"slug":"gkd-generalized-knowledge-distillation-for","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","date":"2023-06-23","arxiv_id":"2306.13649","n_code_links":0,"syntology":null},{"paper":"/paper/incorporating-graph-information-in","slug":"incorporating-graph-information-in","title":"Incorporating Graph Information in Transformer-based AMR Parsing","date":"2023-06-23","arxiv_id":"2306.13467","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm-assisted-content-analysis-using-large","title":"LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding","date":"2023-06-23","arxiv_id":"2306.14924","n_code_links":0,"syntology":null},{"paper":null,"slug":"resume-information-extraction-via-post-ocr","title":"Resume Information Extraction via Post-OCR Text Processing","date":"2023-06-23","arxiv_id":"2306.13775","n_code_links":0,"syntology":null},{"paper":"/paper/system-level-natural-language-feedback","slug":"system-level-natural-language-feedback","title":"System-Level Natural Language Feedback","date":"2023-06-23","arxiv_id":"2306.13588","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":["yyy-apple/sys-nl-feedback"],"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/voicebox-text-guided-multilingual-universal","slug":"voicebox-text-guided-multilingual-universal","title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","date":"2023-06-23","arxiv_id":"2306.15687","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":9,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/cross-lingual-cross-temporal-summarization","slug":"cross-lingual-cross-temporal-summarization","title":"Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation","date":"2023-06-22","arxiv_id":"2306.12916","n_code_links":1,"syntology":null},{"paper":null,"slug":"named-entity-recognition-in-resumes","title":"Named entity recognition in resumes","date":"2023-06-22","arxiv_id":"2306.13062","n_code_links":0,"syntology":null},{"paper":"/paper/prompt-to-gpt-3-step-by-step-thinking","slug":"prompt-to-gpt-3-step-by-step-thinking","title":"Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation","date":"2023-06-22","arxiv_id":"2306.13195","n_code_links":1,"syntology":null},{"paper":null,"slug":"black-box-prediction-of-flaky-test-fix","title":"FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repair","date":"2023-06-21","arxiv_id":"2307.00012","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-pre-trained-language-models-on","title":"Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI","date":"2023-06-21","arxiv_id":"2306.12205","n_code_links":0,"syntology":null},{"paper":"/paper/solving-and-generating-npr-sunday-puzzles","slug":"solving-and-generating-npr-sunday-puzzles","title":"Solving and Generating NPR Sunday Puzzles with Large Language Models","date":"2023-06-21","arxiv_id":"2306.12255","n_code_links":1,"syntology":null},{"paper":null,"slug":"which-spurious-correlations-impact-reasoning","title":"Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals","date":"2023-06-21","arxiv_id":"2306.12146","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-counterfactual-method-for-aspect","title":"A Novel Counterfactual Data Augmentation Method for Aspect-Based Sentiment Analysis","date":"2023-06-20","arxiv_id":"2306.11260","n_code_links":0,"syntology":null},{"paper":null,"slug":"decodingtrust-a-comprehensive-assessment-of","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","date":"2023-06-20","arxiv_id":"2306.11698","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-fusion-efficient-network-training-via","title":"Deep Fusion: Efficient Network Training via Pre-trained Initializations","date":"2023-06-20","arxiv_id":"2306.11903","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-gpt-a-data-pre-processing-and-1","slug":"event-stream-gpt-a-data-pre-processing-and-1","title":"Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events","date":"2023-06-20","arxiv_id":"2306.11547","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["mmcdermott/eventstreamgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/inrank-incremental-low-rank-learning","slug":"inrank-incremental-low-rank-learning","title":"InRank: Incremental Low-Rank Learning","date":"2023-06-20","arxiv_id":"2306.11250","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-generate-better-than-your-llm","slug":"learning-to-generate-better-than-your-llm","title":"Learning to Generate Better Than Your LLM","date":"2023-06-20","arxiv_id":"2306.11816","n_code_links":1,"syntology":null},{"paper":null,"slug":"textbooks-are-all-you-need","title":"Textbooks Are All You Need","date":"2023-06-20","arxiv_id":"2306.11644","n_code_links":0,"syntology":null},{"paper":"/paper/a-preliminary-study-of-chatgpt-on-news","slug":"a-preliminary-study-of-chatgpt-on-news","title":"A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, Fake News","date":"2023-06-19","arxiv_id":"2306.10702","n_code_links":1,"syntology":null},{"paper":"/paper/bayling-bridging-cross-lingual-alignment-and","slug":"bayling-bridging-cross-lingual-alignment-and","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","date":"2023-06-19","arxiv_id":"2306.10968","n_code_links":1,"syntology":null},{"paper":"/paper/fine-tuning-language-models-for-scientific","slug":"fine-tuning-language-models-for-scientific","title":"Fine-Tuning Language Models for Scientific Writing Support","date":"2023-06-19","arxiv_id":"2306.10974","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-sequential-recommendation-with","title":"Generative Sequential Recommendation with GPTRec","date":"2023-06-19","arxiv_id":"2306.11114","n_code_links":0,"syntology":null},{"paper":null,"slug":"synergpt-in-context-learning-for-personalized","title":"SynerGPT: In-Context Learning for Personalized Drug Synergy Prediction and Drug Design","date":"2023-06-19","arxiv_id":"2307.11694","n_code_links":0,"syntology":null},{"paper":"/paper/instant-soup-cheap-pruning-ensembles-in-a","slug":"instant-soup-cheap-pruning-ensembles-in-a","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","date":"2023-06-18","arxiv_id":"2306.10460","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":["vita-group/instant_soup"],"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":"summarization-from-leaderboards-to-practice","title":"Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness","date":"2023-06-18","arxiv_id":"2306.10555","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-social-network-hate-detection-using","slug":"enhancing-social-network-hate-detection-using","title":"Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time","date":"2023-06-17","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/demystifying-gpt-self-repair-for-code","slug":"demystifying-gpt-self-repair-for-code","title":"Is Self-Repair a Silver Bullet for Code Generation?","date":"2023-06-16","arxiv_id":"2306.09896","n_code_links":1,"syntology":null},{"paper":"/paper/gpt4-is-slightly-helpful-for-peer-review","slug":"gpt4-is-slightly-helpful-for-peer-review","title":"GPT4 is Slightly Helpful for Peer-Review Assistance: A Pilot Study","date":"2023-06-16","arxiv_id":"2307.05492","n_code_links":2,"syntology":null},{"paper":null,"slug":"investigating-masking-based-data-generation","title":"Investigating Masking-based Data Generation in Language Models","date":"2023-06-16","arxiv_id":"2307.00008","n_code_links":0,"syntology":null},{"paper":null,"slug":"revealing-the-impact-of-social-circumstances","title":"Revealing the impact of social circumstances on the selection of cancer therapy through natural language processing of social work notes","date":"2023-06-16","arxiv_id":"2306.09877","n_code_links":0,"syntology":null},{"paper":"/paper/bed-bi-encoder-based-detectors-for-out-of","slug":"bed-bi-encoder-based-detectors-for-out-of","title":"BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection","date":"2023-06-15","arxiv_id":"2306.08852","n_code_links":1,"syntology":null},{"paper":"/paper/chessgpt-bridging-policy-learning-and-1","slug":"chessgpt-bridging-policy-learning-and-1","title":"ChessGPT: Bridging Policy Learning and Language Modeling","date":"2023-06-15","arxiv_id":"2306.09200","n_code_links":1,"syntology":{"ran":14,"of":20,"n_ran_checked":10,"n_instrument":4,"unverified":6,"pointer_only":0,"phrase":"14 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["waterhorse1/chessgpt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":8,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"distillation-strategies-for-discriminative","title":"Distillation Strategies for Discriminative Speech Recognition Rescoring","date":"2023-06-15","arxiv_id":"2306.09452","n_code_links":0,"syntology":null},{"paper":"/paper/explore-establish-exploit-red-teaming","slug":"explore-establish-exploit-red-teaming","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","date":"2023-06-15","arxiv_id":"2306.09442","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["algorithmic-alignment-lab/commonclaim","thestephencasper/common_claim","thestephencasper/explore_establish_exploit_llms"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"exploring-the-mit-mathematics-and-eecs","title":"Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models","date":"2023-06-15","arxiv_id":"2306.08997","n_code_links":0,"syntology":null},{"paper":null,"slug":"mapping-researcher-activity-based-on","title":"Mapping Researcher Activity based on Publication Data by means of Transformers","date":"2023-06-15","arxiv_id":"2306.09049","n_code_links":0,"syntology":null},{"paper":"/paper/slamb-accelerated-large-batch-training-with","slug":"slamb-accelerated-large-batch-training-with","title":"SLAMB: Accelerated Large Batch Training with Sparse Communication","date":"2023-06-15","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"stochastic-re-weighted-gradient-descent-via","title":"Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization","date":"2023-06-15","arxiv_id":"2306.09222","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-pop-song-generator-designing-an-online","title":"The pop song generator: designing an online course to teach collaborative, creative AI","date":"2023-06-15","arxiv_id":"2306.10069","n_code_links":0,"syntology":null},{"paper":null,"slug":"thrilled-by-your-progress-large-language","title":"Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses","date":"2023-06-15","arxiv_id":"2306.10073","n_code_links":0,"syntology":null},{"paper":"/paper/a-semantically-enhanced-dual-encoder-for","slug":"a-semantically-enhanced-dual-encoder-for","title":"A semantically enhanced dual encoder for aspect sentiment triplet extraction","date":"2023-06-14","arxiv_id":"2306.08373","n_code_links":1,"syntology":null},{"paper":"/paper/assessing-the-effectiveness-of-gpt-3-in","slug":"assessing-the-effectiveness-of-gpt-3-in","title":"Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset","date":"2023-06-14","arxiv_id":"2306.08190","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-corpus-for-biomedical-relation","title":"Building a Corpus for Biomedical Relation Extraction of Species Mentions","date":"2023-06-14","arxiv_id":"2306.08403","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-are-not-naysayers-an-analysis","slug":"language-models-are-not-naysayers-an-analysis","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","date":"2023-06-14","arxiv_id":"2306.08189","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-agi-in-computer-vision-lessons","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","date":"2023-06-14","arxiv_id":"2306.08641","n_code_links":0,"syntology":null},{"paper":"/paper/world-to-words-grounded-open-vocabulary","slug":"world-to-words-grounded-open-vocabulary","title":"World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models","date":"2023-06-14","arxiv_id":"2306.08685","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["sled-group/world-to-words"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":"/paper/enhancing-social-network-hate-detection-using-1","slug":"enhancing-social-network-hate-detection-using-1","title":"Enhancing Social Network Hate Detection Using Back Translation and GPT-3 Augmentations During Training and Test-Time","date":"2023-06-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"flame-few-shot-learning-from-natural-language","title":"FLamE: Few-shot Learning from Natural Language Explanations","date":"2023-06-13","arxiv_id":"2306.08042","n_code_links":0,"syntology":null},{"paper":null,"slug":"gemo-clap-gender-attribute-enhanced","title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","date":"2023-06-13","arxiv_id":"2306.07848","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-like-intuitive-behavior-and-reasoning","title":"Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4","date":"2023-06-13","arxiv_id":"2306.07622","n_code_links":0,"syntology":null},{"paper":"/paper/improving-zero-shot-detection-of-low","slug":"improving-zero-shot-detection-of-low","title":"Improving Zero-Shot Detection of Low Prevalence Chest Pathologies using Domain Pre-trained Language Models","date":"2023-06-13","arxiv_id":"2306.08000","n_code_links":1,"syntology":null},{"paper":null,"slug":"monolingual-and-cross-lingual-knowledge","title":"Monolingual and Cross-Lingual Knowledge Transfer for Topic Classification","date":"2023-06-13","arxiv_id":"2306.07797","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-of-vision-language-pre-training-from","title":"A Survey of Vision-Language Pre-training from the Lens of Multimodal Machine Translation","date":"2023-06-12","arxiv_id":"2306.07198","n_code_links":0,"syntology":null},{"paper":null,"slug":"imbalanced-multi-label-classification-for","title":"Imbalanced Multi-label Classification for Business-related Text with Moderately Large Label Spaces","date":"2023-06-12","arxiv_id":"2306.07046","n_code_links":0,"syntology":null},{"paper":"/paper/linear-classifier-an-often-forgotten-baseline","slug":"linear-classifier-an-often-forgotten-baseline","title":"Linear Classifier: An Often-Forgotten Baseline for Text Classification","date":"2023-06-12","arxiv_id":"2306.07111","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jameslyc88/text_classification_baseline_code"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"multimodal-audio-textual-architecture-for-1","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","date":"2023-06-12","arxiv_id":"2306.06819","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-n-gram-approximation-of-pre-trained","title":"On the N-gram Approximation of Pre-trained Language Models","date":"2023-06-12","arxiv_id":"2306.06892","n_code_links":0,"syntology":null},{"paper":"/paper/recursion-of-thought-a-divide-and-conquer","slug":"recursion-of-thought-a-divide-and-conquer","title":"Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models","date":"2023-06-12","arxiv_id":"2306.06891","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-bea-2023-shared-task-on-generating-ai","title":"The BEA 2023 Shared Task on Generating AI Teacher Responses in Educational Dialogues","date":"2023-06-12","arxiv_id":"2306.06941","n_code_links":0,"syntology":null},{"paper":"/paper/unipoll-a-unified-social-media-poll","slug":"unipoll-a-unified-social-media-poll","title":"UniPoll: A Unified Social Media Poll Generation Framework via Multi-Objective Optimization","date":"2023-06-12","arxiv_id":"2306.06851","n_code_links":1,"syntology":null},{"paper":"/paper/waffling-around-for-performance-visual","slug":"waffling-around-for-performance-visual","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","date":"2023-06-12","arxiv_id":"2306.07282","n_code_links":2,"syntology":{"ran":5,"of":5,"n_ran_checked":0,"n_instrument":5,"unverified":0,"pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["explainableml/waffleclip"],"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":["listed","official"]}}},{"paper":"/paper/attention-compilation-and-solver-based","slug":"attention-compilation-and-solver-based","title":"CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution","date":"2023-06-11","arxiv_id":"2306.06755","n_code_links":1,"syntology":null},{"paper":"/paper/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":"/paper/inductive-reasoning-in-humans-and-large","slug":"inductive-reasoning-in-humans-and-large","title":"Inductive reasoning in humans and large language models","date":"2023-06-11","arxiv_id":"2306.06548","n_code_links":1,"syntology":null},{"paper":null,"slug":"robertweet-a-bert-language-model-for-romanian","title":"RoBERTweet: A BERT Language Model for Romanian Tweets","date":"2023-06-11","arxiv_id":"2306.06598","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-low-resource-ner-using-assisting","title":"Enhancing Low Resource NER Using Assisting Language And Transfer Learning","date":"2023-06-10","arxiv_id":"2306.06477","n_code_links":0,"syntology":null},{"paper":null,"slug":"medical-data-augmentation-via-chatgpt-a-case","title":"Medical Data Augmentation via ChatGPT: A Case Study on Medication Identification and Medication Event Classification","date":"2023-06-10","arxiv_id":"2306.07297","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-generative-approach-to-product","title":"A Unified Generative Approach to Product Attribute-Value Identification","date":"2023-06-09","arxiv_id":"2306.05605","n_code_links":0,"syntology":null},{"paper":null,"slug":"cover-a-heuristic-greedy-adversarial-attack","title":"COVER: A Heuristic Greedy Adversarial Attack on Prompt-based Learning in Language Models","date":"2023-06-09","arxiv_id":"2306.05659","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-neural-network-compression-via","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","date":"2023-06-09","arxiv_id":"2306.05785","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-responses-of-large-language","title":"Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests","date":"2023-06-09","arxiv_id":"2306.05715","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-calls-enhancing-call-segmentation-and","title":"GPT-Calls: Enhancing Call Segmentation and Tagging by Generating Synthetic Conversations via Large Language Models","date":"2023-06-09","arxiv_id":"2306.07941","n_code_links":0,"syntology":null},{"paper":null,"slug":"implementing-bert-and-fine-tuned-roberta-to","title":"Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT","date":"2023-06-09","arxiv_id":"2306.07401","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-can-learn-exceptions-to","slug":"language-models-can-learn-exceptions-to","title":"Language Models Can Learn Exceptions to Syntactic Rules","date":"2023-06-09","arxiv_id":"2306.05969","n_code_links":1,"syntology":null},{"paper":"/paper/prodigy-an-expeditiously-adaptive-parameter","slug":"prodigy-an-expeditiously-adaptive-parameter","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","date":"2023-06-09","arxiv_id":"2306.06101","n_code_links":1,"syntology":null},{"paper":"/paper/reliability-check-an-analysis-of-gpt-3-s","slug":"reliability-check-an-analysis-of-gpt-3-s","title":"Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording","date":"2023-06-09","arxiv_id":"2306.06199","n_code_links":2,"syntology":null}],"record_sha256":"2263c9e6cf91aba08ab2abf609659dd4f6d6a3c719e4905a8e9f35312a368722","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}