{"total":308,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450,"area":null},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411,"area":null},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199,"area":null},{"id":"2108.02035","title":"Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification","created":"2021-08-04","cited_by_count":183,"area":null},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"area":null},{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123,"area":null},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76,"area":null},{"id":"2109.03659","title":"Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction","created":"2021-09-08","cited_by_count":73,"area":null},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2212.02199","title":"Legal Prompt Engineering for Multilingual Legal Judgement Prediction","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54,"area":null},{"id":"2204.12000","title":"Estimating the Personality of White-Box Language Models","created":"2022-04-25","cited_by_count":48,"area":null},{"id":"2109.14076","title":"RAFT: A Real-World Few-Shot Text Classification Benchmark","created":"2021-09-28","cited_by_count":44,"area":null},{"id":"2203.04640","title":"Memory Efficient Continual Learning with Transformers","created":"2022-03-09","cited_by_count":43,"area":null},{"id":"2103.00070","title":"Knowledge-aware Zero-Shot Learning: Survey and Perspective","created":"2021-02-26","cited_by_count":41,"area":null},{"id":"2403.17661","title":"Language Models for Text Classification: Is In-Context Learning Enough?","created":"2024-03-26","cited_by_count":40,"area":null},{"id":"2211.16285","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","created":"2022-11-29","cited_by_count":39,"area":null},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2112.11941","title":"CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models","created":"2021-12-22","cited_by_count":34,"area":null},{"id":"2404.01475","title":"Are large language models superhuman chemists?","created":"2024-04-01","cited_by_count":34,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2104.11882","title":"Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System","created":"2021-04-24","cited_by_count":30,"area":null},{"id":"2202.04824","title":"AdaPrompt: Adaptive Model Training for Prompt-based NLP","created":"2022-02-10","cited_by_count":30,"area":null},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28,"area":null},{"id":"2112.08643","title":"TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2212.09994","title":"Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2105.05541","title":"Evaluating Gender Bias in Natural Language Inference","created":"2021-05-12","cited_by_count":27,"area":null},{"id":"2210.17541","title":"Zero-Shot Text Classification with Self-Training","created":"2022-10-31","cited_by_count":26,"area":"synth"},{"id":"2305.10703","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2110.02591","title":"Weakly-supervised Text Classification Based on Keyword Graph","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2202.13758","title":"Logical Fallacy Detection","created":"2022-02-28","cited_by_count":25,"area":null},{"id":"2205.01376","title":"Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning","created":"2022-05-03","cited_by_count":25,"area":null},{"id":"2403.00165","title":"TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision","created":"2024-02-29","cited_by_count":25,"area":null},{"id":"2112.10006","title":"Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey","created":"2021-12-18","cited_by_count":23,"area":null},{"id":"2312.17543","title":"Building Efficient Universal Classifiers with Natural Language Inference","created":"2023-12-29","cited_by_count":22,"area":null},{"id":"2109.03685","title":"Open Aspect Target Sentiment Classification with Natural Language Prompts","created":"2021-09-08","cited_by_count":20,"area":null},{"id":"2112.08544","title":"NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledge","created":"2021-12-16","cited_by_count":20,"area":null},{"id":"2303.12513","title":"Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding","created":"2023-03-21","cited_by_count":20,"area":"lr"},{"id":"2305.01723","title":"Stance Detection: A Practical Guide to Classifying Political Beliefs in Text","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2204.07372","title":"A Personalized Dialogue Generator with Implicit User Persona Detection","created":"2022-04-15","cited_by_count":19,"area":null},{"id":"2403.13786","title":"Chain-of-Interaction: Enhancing Large Language Models for Psychiatric Behavior Understanding by Dyadic Contexts","created":"2024-03-20","cited_by_count":19,"area":null},{"id":"2205.01826","title":"Unified Semantic Typing with Meaningful Label Inference","created":"2022-05-04","cited_by_count":18,"area":null},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2202.06167","title":"Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference","created":"2022-02-12","cited_by_count":17,"area":null},{"id":"2206.14085","title":"Continual Learning with Transformers for Image Classification","created":"2022-06-28","cited_by_count":17,"area":null},{"id":"2209.11000","title":"Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation","created":"2022-09-22","cited_by_count":17,"area":null},{"id":"2305.14996","title":"The ACL OCL Corpus: Advancing Open Science in Computational Linguistics","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2405.00981","title":"Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation","created":"2024-05-02","cited_by_count":17,"area":null},{"id":"2109.04108","title":"MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction","created":"2021-09-09","cited_by_count":16,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2209.05987","title":"Design of Negative Sampling Strategies for Distantly Supervised Skill Extraction","created":"2022-09-13","cited_by_count":16,"area":null},{"id":"2106.08022","title":"Zero-shot Node Classification with Decomposed Graph Prototype Network","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2109.05357","title":"Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework","created":"2021-09-11","cited_by_count":15,"area":null},{"id":"2203.14655","title":"Few-Shot Learning with Siamese Networks and Label Tuning","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2410.17632","title":"LMLPA: Language Model Linguistic Personality Assessment","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2508.07662","title":"GLiClass: Generalist Lightweight Model for Sequence Classification Tasks","created":"2025-08-11","cited_by_count":15,"area":null},{"id":"2302.00609","title":"Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases","created":"2023-02-01","cited_by_count":14,"area":null},{"id":"2312.06798","title":"Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2401.14440","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2101.02661","title":"Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2209.06701","title":"Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora","created":"2022-09-14","cited_by_count":13,"area":null},{"id":"2102.04310","title":"The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point","created":"2021-02-08","cited_by_count":12,"area":null},{"id":"2108.13751","title":"A Search Engine for Discovery of Scientific Challenges and Directions","created":"2021-08-31","cited_by_count":12,"area":null},{"id":"2304.12730","title":"CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers","created":"2023-04-25","cited_by_count":12,"area":null},{"id":"2402.08341","title":"Eliciting Personality Traits in Large Language Models","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2405.05135","title":"Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks","created":"2024-04-24","cited_by_count":12,"area":null},{"id":"2510.08338","title":"LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings","created":"2025-10-09","cited_by_count":12,"area":null},{"id":"2204.09347","title":"Active Few-Shot Learning with FASL","created":"2022-04-20","cited_by_count":11,"area":null},{"id":"2202.05932","title":"Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification","created":"2022-02-11","cited_by_count":10,"area":null},{"id":"2310.02161","title":"Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2410.08820","title":"Which Demographics do LLMs Default to During Annotation?","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2104.01666","title":"Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning","created":"2021-04-04","cited_by_count":9,"area":null},{"id":"2111.04022","title":"MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information","created":"2021-11-07","cited_by_count":9,"area":null},{"id":"2204.03498","title":"On the Effectiveness of Pretrained Models for API Learning","created":"2022-04-05","cited_by_count":9,"area":null},{"id":"2206.13214","title":"Few-Shot Stance Detection via Target-Aware Prompt Distillation","created":"2022-06-27","cited_by_count":9,"area":null},{"id":"2302.03353","title":"What do Language Models know about word senses? Zero-Shot WSD with Language Models and Domain Inventories","created":"2023-02-07","cited_by_count":9,"area":null},{"id":"2302.04723","title":"Zero-Shot Learning for Requirements Classification: An Exploratory Study","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2302.04914","title":"Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using General Purpose Language Models","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2502.08825","title":"Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2609.37647","title":"Evaluating and Benchmarking the System One Model Jev","created":"2026-09-29","cited_by_count":9,"area":null},{"id":"2112.04539","title":"Prompt-based Zero-shot Relation Extraction with Semantic Knowledge Augmentation","created":"2021-12-08","cited_by_count":8,"area":null},{"id":"2208.01483","title":"Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours","created":"2022-08-02","cited_by_count":8,"area":null},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2405.11877","title":"A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus","created":"2024-05-20","cited_by_count":8,"area":null},{"id":"2411.08028","title":"Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data","created":"2024-11-12","cited_by_count":8,"area":"distill"},{"id":"2504.09277","title":"SynthTRIPs: A Knowledge-Grounded Framework for Benchmark Query Generation for Personalized Tourism Recommenders","created":"2025-04-12","cited_by_count":8,"area":null},{"id":"2104.05861","title":"Evaluating Pre-Trained Models for User Feedback Analysis in Software Engineering: A Study on Classification of App-Reviews","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2201.01337","title":"ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling","created":"2022-01-04","cited_by_count":7,"area":null},{"id":"2203.13602","title":"ZS4IE: A toolkit for Zero-Shot Information Extraction with simple Verbalizations","created":"2022-03-25","cited_by_count":7,"area":null},{"id":"2210.06023","title":"Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics","created":"2022-10-12","cited_by_count":7,"area":null},{"id":"2211.00171","title":"Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2303.05670","title":"Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoning","created":"2023-03-10","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2305.15282","title":"A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2306.16722","title":"Evaluating Paraphrastic Robustness in Textual Entailment Models","created":"2023-06-29","cited_by_count":7,"area":null}],"next_cursor":"100"}