Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Wenpeng Yin, Jamaal Hay, Dan Roth. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This is evidenced by LLMs impressive zero-shot and few-shot learning ability [18,132], as well as the fact that in-context learning does not require weight update, which mechanically prevents unfavorable fine-tuning-related behavior like catastrophic forgetting.”
From Harnessing the power of llms in practice: a survey on chatGPT and beyond (2024) · cites this paper as [132]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“LLMs have been shown to outperform previous zero-shot methods [132].”
From Harnessing the power of llms in practice: a survey on chatGPT and beyond (2024) · cites this paper as [132]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 6×
“Regarding this label-fully-unseen evaluation, apart from our entailment models and three unsupervised baselines “Majority”, “Word2Vec” and “ESA”, we also report the following baseline: Wikipedia-based : We train a binary clas-sifier based on BERT on a dataset collected from Wikipedia.”
MethodInfluentialBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 6×
“Regarding this label-fully-unseen evaluation, apart from our entailment models and three unsupervised baselines “Majority”, “Word2Vec” and “ESA”, we also report the following baseline: Wikipedia-based : We train a binary clas-sifier based on BERT on a dataset collected from Wikipedia.”
MethodInfluentialDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 2×
“• Word2Vec 5 (Mikolov et al., 2013): Both the representations of the text and the labels are the addition of word embeddings element-wisely.”
BackgroundGLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222 · cited 11×
“For label-partially-unseen setup in which we intentionally provide annotated data, we first pretrain BERT on the MNLI/FEVER/RTE, then fine-tune on the provided training data.”
BackgroundMethodInfluentialA Broad-Coverage Challenge Corpus for Sentence Understanding through Inference
Williams, A., Nangia, N., & Bowman, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1101 · Cited by 3,342 · cited 2×
“, 2019), and train it on three mainstream entailment datasets: MNLI (Williams et al., 2018), GLUE RTE (Dagan et al.”
BackgroundMethodCharacter-level Convolutional Networks for Text Classification
Zhang, X., Zhao, J., & LeCun, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1509.01626 · Cited by 3,205 · cited 1×
“We use the large-scale Yahoo dataset released by Zhang et al. (2015).”
MethodComputing semantic relatedness using Wikipedia-based explicit semantic analysis
Gabrilovich, E., & Markovitch, S. (2007) · Cited by 1,981
The PASCAL Recognising Textual Entailment Challenge
Dagan, I., Glickman, O., & Magnini, B. (2006) · Lecture Notes in Computer Science · doi:10.1007/11736790_9 · Cited by 1,628
(2018) · International Conference on Learning Representations · Cited by 1,621
FEVER: a Large-scale Dataset for Fact Extraction and VERification
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1074 · Cited by 1,343 · cited 1×
“In this work, we make use of the widely-recognized state of the art entailment technique – BERT (Devlin et al., 2019), and train it on three mainstream entailment datasets: MNLI (Williams et al., 2018), GLUE RTE (Dagan et al., 2005; Wang et al., 2019) and FEVER 3 (Thorne et al., 2018), respectively.”
Method
Research works printed but not linked: 2
- [8]8. Chenliang Li, Jian Xing, Aixin Sun, and Zongyang Ma. 2016a. Effective document labeling with very few seed words: A topic model approach. In CIKM, pages 85-94.
- [11]11. Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed repre- sentations of words and phrases and their composi- tionality. In NIPS, pages 3111-3119.
Cited by
Items 601–700 of 867
Zero-shot Topic Classification via Automatic Tagging on Chinese Text Datasets
Cai, X., Tian, J., Yu, K., Xiao, H., Zhang, K., & Tsai, P. (2022) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom57177.2022.00068 · Cited by 1
NLI-based Filtering for Data Augmentation in Topic Classification
Chen, Y., & Liu, Y. (2022) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat55865.2022.00024 · Cited by 1
“This strategy has been reformulated as a natural language inference (NLI) problem [43], which takes the sentence we’re interested in labeling as premise and turns each candidate label into hypothesis.”
BackgroundErker, J.-J., Schaffer, S., & Spanakis, G. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.319 · Cited by 1
Shan, J., Ni, Y., & Nishihara, Y. (2023) · International Symposium on Information and Communication Technology · doi:10.1145/3628797.3628998 · Cited by 1
Simple Framework for Interpretable Fine-Grained Text Classification
Battogtokh, M., Flucke, G., Davidescu, C., & Borgo, R. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-50396-2_23 · Cited by 1
“A previous work [44] argued that this label-encoding prevents models from “understanding” a label.”
BackgroundInfluentialPhraseSumm: Abstractive Short Phrase Summarization
Bhattacharjee, K., McKeown, K. R., & Gangadharaiah, R. (2023) · doi:10.18653/v1/2023.findings-ijcnlp.8 · Cited by 1
“The premise consists of the utterance itself, while the hypothesis consists of the template “This text is about {} ” where the corresponding label is inserted in “ {} ”, as proposed in Yin et al. (2019).”
Yano, T., Takeoka, K., & Oyamada, M. (2024) · Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/2024.starsem-1.9 · Cited by 1
“Existing methods for zero-shot text classification decide the class y of an input instance x based on the relationship between a class name and an instance (Sappadla et al., 2016; Yin et al., 2019) such as semantic similarity.”
BackgroundMethodInfluentialOne-Shot Prompt for Language Variety Identification
Gillin, N. (2024) · Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial) · doi:10.18653/v1/2024.vardial-1.20 · Cited by 1
“…of using language models generation performs well in classification task (Li et al., 2018a; Thant and Nwet, 2020; Hadar and Shmueli, 2021) and generation models can also perform competitively as zero-shot text-classifiers (Yin et al., 2019; Meng et al., 2022; Sun et al., 2023; Wang et al., 2023).”
MethodMix-Initiative Response Generation with Dynamic Prefix Tuning
Nie, Y., Huang, H., Mao, X.-L., & Liao, L. (2024) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2024.naacl-long.485 · Cited by 1
Beyond Large Language Models: Rediscovering the Role of Classical Statistics in Modern Data Science
Gutiérrez, I., Gómez, D., Castro, J., Bimber, B., & Labarre, J. (2024) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz-ieee60900.2024.10611766 · Cited by 1
“We apply the models facebook/bart − large − mnli [14] (BART-based [7] useful for large datasets and trained with the MultiNLI dataset [15]), Jiva/xlm − roberta − large − it − mnli [16] (RoBERTa-based [6] also trained with MultiNLI) and KBLab/megatron − bert − large − swedish − cased − 165 − zero −…”
MethodZero-Shot Relation Classification Through Inference on Category Attributes
Xiao, Y., Jin, Y., Wang, B., Zhang, Y., Hao, K., & Li, H. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3474669 · Cited by 1
“To a certain extent, it aims to classify the relationship between sentence pairs under the presupposition of fully understanding the sentence, which can be helpful in several tasks, such as topic or emotion detection [45] and sentence similarity [46].”
The rise of AI-enabled new product ideation: End of innovation crowdsourcing?
Lee, H., & Maruping, L. M. (2026) · Decision Support Systems · doi:10.1016/j.dss.2026.114774 · Cited by 1
LCHAIM - Investigating Long Context Reasoning in Hebrew
Malul, E., Perets, O., Mor, Z., Kassel, Y., & Sulem, E. (2025) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2025.findings-acl.413 · Cited by 1
“This task has shown to be very helpful in various applications, including text classification, event extraction, and summarization evaluation, (Yin et al., 2019; Sainz et al., 2022; Scirè et al., 2024).”
Yu, Y., Shen, H., Lyu, Z., & He, Q. (2025) · ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD) · doi:10.1109/snpd65828.2025.11254671 · Cited by 1
“The concept of prompts was introduced to address issues with the ‘pre-training + fine-tuning’ approach, such as introducing new parameters at the model’s head during the fine-tuning stage and overfitting in few-shot or zero-shot scenarios.”
Unraveling Social Perceptions & Behaviors towards Migrants on Twitter
Khatua, A., & Wolfgang, N. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.6645675 · Cited by 1
Leveraging Natural Supervision for Language Representation Learning and GenerationPreprint
Chen, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2207.10617 · Cited by 1
Fang, Q., Giachanou, A., & Bagheri, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.06543 · Cited by 1
“This may allow the model to predict stances towards unseen targets, also known as zero-shot learning (Yin et al., 2019).”
ZS4IE: A toolkit for Zero-Shot Information Extraction with simple VerbalizationsPreprint
Sainz, O., Qiu, H., de Lacalle, O. L., Agirre, E., & Min, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.13602 · Cited by 1
Exploring Data Augmentation Methods on Social Media CorporaPreprint
Pietri, I. G., & Stanley, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.02198 · Cited by 1
Coping with low data availability for social media crisis message categorisationPreprint
Wang, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.17211 · Cited by 1
Towards Open-Domain Topic ClassificationPreprint
Ding, H., Yang, J., Deng, Y., Zhang, H., & Roth, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.17290 · Cited by 1
“Later on, (Yin et al., 2019) called this protocol “label fully unseen" and proposed an entailment approach to transfer knowledge from textual entailment to text classification.”
BackgroundMethodInfluentialSelf-citationGrokhowsky, N. (2023) · Research Square · doi:10.21203/rs.3.rs-3129370/v1 · Cited by 1
An Evaluation Framework for Mapping News Headlines to Event Classes in a Knowledge GraphPreprint
Mbouadeu, S. F., Lorenzo, M., Barker, K., & Hassanzadeh, O. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.02334 · Cited by 1
“Yin et al. (2019) present an excellent review of benchmarks for this task.”
BackgroundText-Based Correlation Matrix in Multi-Asset AllocationPreprint
Nakayama, Y., Sawaki, T., Furuya, I., & Tamura, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.14247 · Cited by 1
Balouchzahi, F., Butt, S., Sarker, A., Al-Garadi, M. A., Sidorov, G., & Gelbukh, A. F. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4930517 · Cited by 1
Manual Verbalizer Enrichment for Few-Shot Text ClassificationPreprint
Nguyen, Q. A., Tomeh, N., Lebbah, M., Charnois, T., Azzag, H., & Muñoz, S. C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.06173 · Cited by 1
“Classical fine-tuning, therefore becomes inapplicable for few-shot or zero-shot scenarios (Yin et al., 2019; Zhang et al., 2023).”
BackgroundChandrashekar, A., Gala, R., Tjärnberg, A., Khullar, S., Huynh, G. H., & Gabitto, M. I. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.13.637984 · Cited by 1
Text Psychometrics: Assessing Psychological Constructs in Text Using Natural Language ProcessingPreprint
Low, D. M., Mair, P., Nock, M. K., & Ghosh, S. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/9rdux_v1 · Cited by 2
Do Whitepaper Claims Predict Market Behavior? — Evidence from Cryptocurrency Factor AnalysisPreprint
Farzulla, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5918302 · Cited by 1
Automated detection of cryptocurrency investment scams at scale
Atondo Siu, J. (2024) · Apollo (University of Cambridge) · doi:10.17863/cam.115840 · Cited by 1
Quantifying Linguistic Variation:Data-driven Navigation of Variety Space
Müller-Eberstein, M. (2024) · IT University Of Copenhagen (IT University of Copenhagen) · Cited by 1
Jallad, K. A., Ghneim, N., & Rebdawi, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.20419 · Cited by 1
“Some state-of-the-art models that contain Arabic language are: Facebook Bart Large MNLI [39], [40], Facebook RoBERTa-Large-MNLI [41] , Microsoft Multilingual MiniLM [42], Microsoft XLM-RoBERTa [42], Microsoft DeBERTaV3 [43].”
Sentiment Analysis on Movie Reviews: A Deep Dive into Modern Techniques and Open ChallengesPreprint
Gosai, A., De, S., Thankachan, K., ZeinEldin, R. A., Mohamed, A., & Mousavirad, S. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.07235 · Cited by 1
MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text CategorizationPreprint
Costache, A. V., Dragomir, D.-N., Gheorghe, S.-F., Poesina, E., Irofti, P., & Ionescu, R. T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.13437 · Cited by 1
“ZSL is achieved either by adapting various related tasks in order to solve the classification problem (Yang et al., 2025; Yin et al., 2019; Zhou et al., 2024a), or by generating synthetic data and subsequently using a supervised method (Hu et al., 2017; Meng et al., 2022; Ye et al., 2022; Yu et…”
Rahman, M. M., & Chaudry, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.18454 · Cited by 1
“To map each topic τ j to its corresponding ethical category, we used the Bidirectional and Auto-Regressive Transformer (BART) model available in the HuggingFace library [63, 4].”
CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech DocumentsPreprint
Kostelník, M., Hradiš, M., & Dočekal, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.03884 · Cited by 1
“Other approaches reformulates zero-shot labeling as pairwise text–label classification: Yin et al. [49] model classification as textual entailment between input texts and label descriptions, while GLiNER [50] performs span extraction conditioned on natural-language labels, enabling zero-shot entity…”
Human-Machine Dialogue in the Medical Field. Using Dialog to Collect Important Patient Information
Liednikova, A. (2022) · theses.fr (ABES) · doi:10.70675/b572f8cbz5876z4683z828bzfb09085ddd78 · Cited by 1
Delmas, M. (2022) · theses.fr (ABES) · doi:10.70675/ad2bed6azbf7bz4153zba9dz638e945cff18 · Cited by 1
Aouina, O. (2024) · theses.fr (ABES) · doi:10.70675/2c8a820cz57f8z4594z9cb8zeaf9ec41fe5e · Cited by 1
Prompt-based Relation Extraction for Pharmacovigilance
Yeh, H.-S. (2024) · theses.fr (ABES) · doi:10.70675/762a3598ze739z4c47za72ez62e5a986fd1f · Cited by 1
Ningrum, P. K. (2025) · theses.fr (ABES) · doi:10.70675/cb5199baz28b9z4b73zb5f7z36d58a485d64 · Cited by 1
From Mainframes to Machine Learning: Skill Gaps over the Technology Life CyclePreprint
Agrawal, A. K., Kim, D., & Tambe, P. B. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6512358 · Cited by 1
Lin, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.06615 · Cited by 1
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision ModelsPreprint
Huang, J., Quan, J., Lyu, S., Guo, Z., & Ge, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.17727 · Cited by 1
“NLI supports zero-shot and few-shot classification by expressing labels as hypotheses (Yin et al., 2019; Wang et al., 2021).”
Stekel, T. R. C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.30970 · Cited by 1
“…of BERT-style encoders on SWAG and RACE [8,9,17], the basis of zero-shot classification by entailment, which scores each label as an NLI hypothesis [3] using models trained on corpora such as MNLI [18] (BART-large-MNLI [19] and the DeBERTa-v3 [20] classifiers of Laurer et al. [4, 21] are the…”
Deep neural networks for information mining from legal texts
Χαλκίδης, Η. (2021) · doi:10.12681/eadd/49458
Perazzoli, S., & Neto, J. P. D. S. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4053010
Towards Human Action Understanding in Social Media Videos Using Multimodal Models
Ignat, O. (2022) · Deep Blue (University of Michigan) · doi:10.7302/6344
TEMPLATE: TempRel Classification Model Trained with Embedded Temporal Relation Knowledge
Sun, T., & Li, L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17120-8_20
Unified Semantic Typing with Meaningful Label InferencePreprint
Huang, J. Y., Li, B., Xu, J., & Chen, M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.01826 · Cited by 1
“…traditional paradigm for semantic typing, several studies have explored alternative approaches such as prompt-based learning (Schick and Schütze, 2021; Ding et al., 2021) and indirect supervision from NLI models (Yin et al., 2019; Sainz et al., 2021) to make more efficient use of label semantics.”
BackgroundWeakly supervised text classification method based on transformer
Gan, L., & yi, A. (2023) · International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI) · doi:10.1117/12.2672391
“WeSTClass [4] introduces a self-training module bootstrapped on real unlabeled data for model fine-tuning.”
BackgroundIdentification of Fine-Grained Fit Information from Customer Reviews in Fashion
Puzikov, Y., Pecenakova, S., Weffer, R., Lefakis, L., & Shirvany, R. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-3-031-22192-7_1
Text Style Transfer Study for Article-Broadcast Style
Kim, K. M., Im, S., Kim, G. B., & Oh, H. (2023) · Journal of Digital Contents Society · doi:10.9728/dcs.2023.24.2.267
A Weakly Supervised Text Classification Method Based on Vocabulary Construction
Li, P., Lin, D., & Li, Z. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-30237-4_12
From Natural Language Models to Cognitive Model Validation: A Theoretical FrameworkPreprint
Mechera‐Ostrovsky, T., & Newell, B. R. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/r6det
Natural language processing for digital advertising
Jin, Y., & Wanvarie, D. (2021) · Chula Digiverse · doi:10.58837/chula.the.2021.121
Ozmen, M., Cotnareanu, J., & Coates, M. (2023) · arXiv.org · doi:10.48550/arxiv.2309.13543
Licon: A Diverse, Controllable and Challenging Linguistic Concept Learning Benchmark
Yu, S., Zhang, Y., Guo, W., Zhang, Z., Zhou, R., & Yuan, X. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.358
“…development of Large pre-trained language models (LMs) (Devlin et al., 2018;Liu et al., 2019;Raffel et al., 2020), many works (Zhang et al., 2019;Yin et al., 2019;Ye et al., 2020b;Sanh et al., 2021;Mishra et al., 2021) focus on zero-shot learning, which aims to train a model that can classify…”
BackgroundYokoyama, T., Natter, J., & Godet, J. (2023) · medRxiv · doi:10.1101/2023.12.09.23299754
“In zero-shot classification, pre-trained models are used without any specific additional training examples for new classes (30).”
MethodElourajini, F., & Aïrncur, E. (2023) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat59888.2023.00044
“Prompt-based learning has been successfully applied to many applications, such as text summarizing [26], text classification [27], text generation [3], and lately item recommendation .”
MethodCulture Configuration, Digital Innovation and State-Ownership: Evidence from an Emerging EconomyPreprint
Zhang, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4797277
Detecting Statements in Text: A Domain-Agnostic Few-Shot SolutionPreprint
Chausson, S., & Roß, B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.05705
Zero-Shot Text Classification Guided by Dynamic Enhanced LabelsPreprint
Zhang, X., Xiang, J., Liu, H., Zhang, X., & Liu, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4837243
CLIP-Prefix for Image Captioning and an Experiment on Blind Image Guessing
Huynh, T. M., Nguyen, D., Nguyen, T. T., Vu, T.-D. T., Dang-Ngoc, H., & Dang, D. N. M. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-67357-3_14
Liu, Z., Huang, X., Chen, W., & Liu, J. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650958
“Due to the potential of prompt-based methods in low-data environments, zero-shot text classification [12] has garnered increasing attention.”
BackgroundLeveraging Entity Recognition for Automotive Customer Feedback Topic Modeling
Weber, L. J., Ramalingam, K. J., Liu, C., Beyer, M., & Zimmermann, A. P. (2024) · doi:10.1109/icnlp60986.2024.10692404
Esener, Y. Y. (2024) · University of North Texas Digital Library (University of North Texas) · doi:10.12794/metadc2356238
Specifics Matter: An Analysis of Mutual Fund ESG DisclosuresPreprint
Shi, H., Han, X., Lee, J. B.-T., & Lu, H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4954234
Ni, Y., Shan, J., & Nishihara, Y. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.155
Automatic Generation of Comparison Charts of Similar GitHub Repositories from Readme Files
Albassam, E. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.01511110
“To extract these limitations and unsupported features of a repository, we incorporated a zero-shot classifier [28] based on the bart-large-mnli model, which is based on the bart-large model [23] and trained on the MultiNLI dataset consisting of 433k sentence pairs annotated with textual entailment…”
Pham, H., & Arul, M. (2024) · Frontiers in Built Environment · doi:10.3389/fbuil.2024.1485388
Vecchi, L. P., Barbon, S., & Paraíso, E. C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-79038-6_18
Tell Me More! Using Multiple Features for Binary Text Classification with a Zero-Shot Model
Broneske, D., Italiya, N., & Mierisch, F. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00249
“While zero-shot classifiers offer promising solutions to the challenges of supervised learning [3, 4], existing methods in text classification primarily rely on single-feature representations.”
InfluentialPi, Q., Lu, J., Sun, Y., Fan, Q., Zhou, X., & Shang, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888183
“A pre-trained NLI model [19] calculates entailment probabilities p i for relevance assessment between tweet content and target candidates.”
Duan, D., Lv, C.-C., Zhang, C., Hou, W., Shi, L., Li, Y.-X., & Zhao, X. (2025) · Knowledge and Information Systems · doi:10.1007/s10115-025-02379-5
“Thetext-labelmatchinghasalsobeenformulatedastextentailment problem [5] such that the model can gain knowledge from entailment datasets.”
DyCoDe: Dynamic Context Detection from Voice Commands and Conversations in Smart Homes
Sultana, J., & Iqbal, R. (2025) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc54725.2025.10976079
“Insights from our prior model implementation also reinforced this conclusion, leading to the selection of the Zero-Shot Text Classification approach from [17].”
Aumento de dados com geração palavras-chaves para texto com grandes modelos de linguagem.
Pellicer, L. F. A. O. (2024) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.3.2024.tde-06052025-083820
Maleki, N., Padmanabhan, B., & Dutta, K. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128531
Banerjee, M., Koçak, Ö., & Yeaton, M. (2025) · SocArXiv (OSF Preprints) · doi:10.31235/osf.io/w4ybc_v1
Gong, Y., Zhang, J., Lin, Y.-F. F., & Wang, H. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033332
Specifics Matter: An Analysis of Mutual Fund ESG DisclosuresPreprint
Shi, H., Han, X., Lee, J. B., & Lu, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5355991
Mapping Poverty and Well-Being Through Natural Language Processing
Santa, G. M., Aguirre, C. A. P., & Orozco‐Arroyave, J. R. (2025) · Revista de Estudios Sociales · doi:10.7440/res93.2025.03
Cabrera, M. V., Johnstone, M., Khan, B., Hayward, J., Bolton, K. A., & Creighton, D. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5390470
Verbal Femininity and CEOs Compensation
Kim, S., & Lee, J. (2025) · Blockchain technologies · doi:10.1007/978-981-96-5833-6_6
AI ‐Generated Price‐Setting Insights from Firms' Earnings Calls*
Windsor, C., & Zang, M. (2025) · Economic Record · doi:10.1111/1475-4932.70004
Abbas, S. H., Wadhwa, G., & Hummel, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00793-3_29
Stock Market Forecasting with Pretrained Deep Learning Models
Do, S. T., Chu, A., Zhao, Y., & Li, Y. (2025) · IEEE International Conference on Big Data Computing Service and Applications (BigDataService) · doi:10.1109/bigdataservice65758.2025.00026
“Furthermore, a textual entailment paradigm is proposed to solve the 0Shot-TC problem with text documents [18].”
Prompt vs. Supervise: A Case of Using Language Models to Assess Students’ Science Explanations
Karumbaiah, S., Ganesh, A., Yang, S., & Tseng, N. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-03870-8_17
Wagneur, N., Capitain, O., Supiot, S., Leborgne, F., Bocquet, F., Campone, M., & Perennec, T. (2025) · JCO Clinical Cancer Informatics · doi:10.1200/cci-25-00130
Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only ModelsPreprint
Elshabrawy, A., Nguyen, T., Kang, Y., Feng, L., Jain, A., Shaikh, F. A., Mansurov, J., Imam, M. F. M., Ortiz-Barajas, J.-G., Chevi, R., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.01592
“Yin et al. (2019) introduce the reformulation of any zero-shot text classification in the form of entailment where statements can be formed from a series of choices and the correct choice is seen to be an entailment.”
Language Models Guidance with Multi-Aspect-Cueing: A Case Study for Competitor AnalysisPreprint
Hadifar, A., Ochs, C., & Ewijk, A. V. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.02984
“For baselines we evaluate it against zero-shot text classification (0Shot-TC; Yin et al., 2019), fine-tuned roberta (FT-Roberta; Liu et al., 2019), Llama2-70B (Touvron et al., 2023), and Llama2-70B with CoT (Kojima et al., 2022).”
Leveraging Large Language Models to Enhance Arabic Prompting and Response Generation in ChatGPT
Kanaan, G., Hendawi, S., Al-Zoubi, A. M., Kanan, T. G., & AlZu’bi, S. M. F. (2025) · International Generative AI and Computational Language Modelling Conference (GACLM) · doi:10.1109/gaclm67198.2025.11232036
Kulkarni, M., Godase, S. K., Khilare, D., & Utpat, V. B. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-29508
A Systematic Review- True News Detection
Kulkarni, M., Godase, S. K., Khilare, D., & Utpat, V. B. (2025) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-29507
Exploring the use of large language models for COICOP classification
Toth, B. (2025) · Statistical Journal of the IAOS · doi:10.1177/18747655251393372
Metadata
- Authors
- Yin, W., Hay, J., & Roth, D.
- Affiliations
- University of Pennsylvania (US)
- Venue
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Published
- 2019
- Pages
- 3912-3921
- OpenAlex
- W2970200208
- Cited by
- 537
- References
- 30
- Citations by year
- 2026: 66 · 2025: 86 · 2024: 75 · 2023: 141 · 2022: 94 · 2021: 64 · 2020: 11
- FWCI
- 16.17
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- Funders
- U.S. Department of Defense
- Defense Advanced Research Projects Agency (HR0011-15-C-0113)
- Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- zero-shot text classification, benchmarking, evaluation metrics, logical consequence, cross-domain classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.

