{"total":112,"rows":[{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819,"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":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344,"area":null},{"id":"2203.03540","title":"GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records","created":"2022-02-02","cited_by_count":238,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204,"area":null},{"id":"2109.08668","title":"Primer: Searching for Efficient Transformers for Language Modeling","created":"2021-09-17","cited_by_count":164,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2401.01301","title":"Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models","created":"2024-01-02","cited_by_count":150,"area":null},{"id":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115,"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":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70,"area":null},{"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":"2204.04497","title":"IDPG: An Instance-Dependent Prompt Generation Method","created":"2022-04-09","cited_by_count":43,"area":null},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41,"area":null},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39,"area":null},{"id":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26,"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":"2302.10447","title":"Mask-guided BERT for Few Shot Text Classification","created":"2023-02-21","cited_by_count":25,"area":null},{"id":"2106.13876","title":"Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations","created":"2021-06-25","cited_by_count":24,"area":null},{"id":"2109.03564","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","created":"2021-09-08","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":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2109.12053","title":"Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus","created":"2021-09-24","cited_by_count":18,"area":null},{"id":"2205.05313","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2306.05523","title":"FACTIFY3M: A Benchmark for Multimodal Fact Verification with Explainability through 5W Question-Answering","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2202.09817","title":"$\\mathcal{Y}$-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning","created":"2022-02-20","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":"2209.15373","title":"PART: Pre-trained Authorship Representation Transformer","created":"2022-09-30","cited_by_count":13,"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":"2501.10860","title":"Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking","created":"2025-01-18","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":"2302.09236","title":"Scalable Prompt Generation for Semi-supervised Learning with Language Models","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2311.01876","title":"Sentiment Analysis through LLM Negotiations","created":"2023-11-03","cited_by_count":11,"area":null},{"id":"2403.09724","title":"ClaimVer: Explainable Claim-Level Verification and Evidence Attribution of Text Through Knowledge Graphs","created":"2024-03-12","cited_by_count":11,"area":null},{"id":"2310.00749","title":"SEED: Domain-Specific Data Curation With Large Language Models","created":"2023-10-01","cited_by_count":10,"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":"2112.09237","title":"PECO: Examining Single Sentence Label Leakage in Natural Language Inference Datasets through Progressive Evaluation of Cluster Outliers","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2306.11066","title":"Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding","created":"2023-06-19","cited_by_count":8,"area":null},{"id":"2307.02729","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2411.02948","title":"Grounding Natural Language to SQL Translation with Data-Based Self-Explanations","created":"2024-11-05","cited_by_count":8,"area":null},{"id":"2112.08628","title":"Explainable Natural Language Processing with Matrix Product States","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2203.03235","title":"Pre-trained Token-replaced Detection Model as Few-shot Learner","created":"2022-03-07","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":"2204.04392","title":"Contrastive Demonstration Tuning for Pre-trained Language Models","created":"2022-04-09","cited_by_count":7,"area":null},{"id":"2205.09229","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","created":"2022-05-18","cited_by_count":7,"area":null},{"id":"2211.11798","title":"Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions","created":"2022-11-21","cited_by_count":7,"area":null},{"id":"2412.09263","title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2405.15512","title":"ChatGPT Code Detection: Techniques for Uncovering the Source of Code","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2202.01924","title":"Zero-Shot Aspect-Based Sentiment Analysis","created":"2022-02-04","cited_by_count":5,"area":null},{"id":"2204.13915","title":"Czech Dataset for Cross-lingual Subjectivity Classification","created":"2022-04-29","cited_by_count":5,"area":null},{"id":"2210.05257","title":"Rethinking the Event Coding Pipeline with Prompt Entailment","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2310.06111","title":"BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2506.08713","title":"Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2204.10543","title":"Zero and Few-shot Learning for Author Profiling","created":"2022-04-22","cited_by_count":4,"area":null},{"id":"2205.01523","title":"ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2209.13953","title":"ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection","created":"2022-09-28","cited_by_count":4,"area":null},{"id":"2210.00910","title":"Hypothesis Engineering for Zero-Shot Hate Speech Detection","created":"2022-10-03","cited_by_count":4,"area":null},{"id":"2212.00301","title":"Learning to Select from Multiple Options","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2303.16764","title":"Boosting Few-Shot Text Classification via Distribution Estimation","created":"2023-03-26","cited_by_count":4,"area":null},{"id":"2310.09897","title":"Reformulating NLP tasks to Capture Longitudinal Manifestation of Language Disorders in People with Dementia","created":"2023-10-15","cited_by_count":4,"area":null},{"id":"2509.02452","title":"Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions","created":"2025-09-02","cited_by_count":4,"area":null},{"id":"2205.07220","title":"Adaptive Prompt Learning-based Few-Shot Sentiment Analysis","created":"2022-05-15","cited_by_count":3,"area":null},{"id":"2305.01616","title":"FreeLM: Fine-Tuning-Free Language Model","created":"2023-05-02","cited_by_count":3,"area":null},{"id":"2403.15938","title":"LlamBERT: Large-scale low-cost data annotation in NLP","created":"2024-03-23","cited_by_count":3,"area":null},{"id":"2405.03565","title":"Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2408.04420","title":"Recognizing Emotion Regulation Strategies from Human Behavior with Large Language Models","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2408.14830","title":"PolicyLR: A Logic Representation For Privacy Policies","created":"2024-08-27","cited_by_count":3,"area":null},{"id":"2207.10617","title":"Leveraging Natural Supervision for Language Representation Learning and Generation","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2305.06162","title":"Interpretable multimodal sentiment analysis based on textual modality descriptions by using large-scale language models","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2305.17197","title":"Entailment as Robust Self-Learner","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2308.08825","title":"Controlling Federated Learning for Covertness","created":"2023-08-17","cited_by_count":2,"area":null},{"id":"2401.16293","title":"Textual Entailment for Effective Triple Validation in Object Prediction","created":"2024-01-29","cited_by_count":2,"area":null},{"id":"2405.01682","title":"Leveraging Prompt-Learning for Structured Information Extraction from Crohn's Disease Radiology Reports in a Low-Resource Language","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2405.11775","title":"Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques","created":"2024-05-20","cited_by_count":2,"area":null},{"id":"2405.14437","title":"Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2502.09567","title":"MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2502.18841","title":"Sentiment Analysis of Movie Reviews Using BERT","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2510.21310","title":"Efficient semantic uncertainty quantification in language models via diversity-steered sampling","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2110.07331","title":"Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models","created":"2021-10-14","cited_by_count":1,"area":null},{"id":"2204.09481","title":"Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers","created":"2022-04-20","cited_by_count":1,"area":null},{"id":"2205.04050","title":"Few-shot Mining of Naturally Occurring Inputs and Outputs","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2209.00455","title":"Let Me Check the Examples: Enhancing Demonstration Learning via Explicit Imitation","created":"2022-08-31","cited_by_count":1,"area":null},{"id":"2209.06344","title":"CNN-Trans-Enc: A CNN-Enhanced Transformer-Encoder On Top Of Static BERT representations for Document Classification","created":"2022-09-13","cited_by_count":1,"area":null},{"id":"2209.12320","title":"Can We Automate the Analysis of Online Child Sexual Exploitation Discourse?","created":"2022-09-25","cited_by_count":1,"area":null},{"id":"2212.07428","title":"Towards Linguistically Informed Multi-Objective Pre-Training for Natural Language Inference","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2302.14286","title":"HugNLP: A Unified and Comprehensive Library for Natural Language Processing","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2306.03722","title":"Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2310.13409","title":"Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2312.08726","title":"Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks","created":"2023-12-14","cited_by_count":1,"area":null},{"id":"2410.09399","title":"Text Classification using Graph Convolutional Networks: A Comprehensive Survey","created":"2024-10-12","cited_by_count":1,"area":null},{"id":"2410.12847","title":"ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2502.20682","title":"Fine-tuning BERT with Bidirectional LSTM for Fine-grained Movie Reviews Sentiment Analysis","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2601.03270","title":"Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2205.11409","title":"Many-Class Text Classification with Matching","created":"2022-05-23","cited_by_count":0,"area":null},{"id":"2206.14263","title":"ZoDIAC: Zoneout Dropout Injection Attention Calculation","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2210.01979","title":"GAPX: Generalized Autoregressive Paraphrase-Identification X","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2210.07587","title":"ConEntail: An Entailment-based Framework for Universal Zero and Few Shot Classification with Supervised Contrastive Pretraining","created":"2022-10-14","cited_by_count":0,"area":null}],"next_cursor":"100"}