Papers with zero-shot classification
The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks (2024.eacl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are not perfect generalists as they often underperform traditional fine-tuning methods. |
| Approach: | They compare human-labeled and synthetically generated data in CSS classification tasks . they leverage large language models such as OpenAI's GPT-4 for zero-shot classification . |
| Outcome: | The proposed models perform better on human-labeled data than synthetically augmented models on rare classes within multi-class tasks. |
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages (2021.tacl-1)
Copied to clipboard
| Challenge: | Currently, there are only 24 languages in the world that have not been annotated . transferring knowledge across domains is a common solution . |
| Approach: | They propose a Bayesian generative model for the space of neural parameters that factorizes into latent variables for each language and each task. |
| Outcome: | The proposed model can perform better than state-of-the-art methods with a typologically diverse sample of 33 languages from 4 continents and 11 families. |
Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models? (2023.findings-eacl)
Copied to clipboard
Jielin Qiu, William Han, Jiacheng Zhu, Mengdi Xu, Michael Rosenberg, Emerson Liu, Douglas Weber, Ding Zhao
| Challenge: | Recent advances in Large Language Models (LLMs) have shown powerful ability in various downstream applications. |
| Approach: | They propose an approach for cardiovascular disease diagnosis and automatic ECG diagnosis report generation. |
| Outcome: | The proposed approach generates high-quality cardiac diagnosis reports and achieves competitive zero-shot classification performance even compared with supervised baselines. |
A Checkpoint on Multilingual Misogyny Identification (2022.acl-srw)
Copied to clipboard
| Challenge: | a study on hate speech against minorities in Italian tweets found that 1 women are the most targeted group. |
| Approach: | They propose to train monolingual transformers and multilingual transformer models with monolingual data in English, Italian, and Spanish to detect misogyny in tweets. |
| Outcome: | The proposed model achieves state-of-the-art on English, Italian, and Spanish. |
Effective Few-Shot Classification with Transfer Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work on few-shot learning addresses the problem of learning based on a small amount of training data. |
| Approach: | They adapt the Amazon Review Sentiment Classification (ARSC) text dataset for few-shot learning . they train a single binary classifier to learn all few- shot classes jointly . |
| Outcome: | The proposed approach outperforms most published results on the ARSC text dataset . the results suggest that the classes in the AR SC few-shot task are very similar to each other . |
Open Vocabulary Extreme Classification Using Generative Models (2022.findings-acl)
Copied to clipboard
Daniel Simig, Fabio Petroni, Pouya Yanki, Kashyap Popat, Christina Du, Sebastian Riedel, Majid Yazdani
| Challenge: | Extreme multi-label classification (XMC) aims at tagging content with subset of labels from an extremely large label set. |
| Approach: | They propose a model that predicts a set of labels outside of the known vocabulary by using a loss-dependent loss-based loss-free model. |
| Outcome: | The proposed model can predict labels outside the known vocabulary while performing on par with state-of-the-art solutions for known labels. |
Uncovering Temporal Framing in the News (2026.acl-long)
Copied to clipboard
Tarek Mahmoud, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj, Max Upravitelev, Mervat Abassy, Hana Fatima Shaikh, Neda Foroutan, Vera Schmitt, Preslav Nakov
| Challenge: | Temporal language is used to structure meaning rather than report chronology in news discourse . a recent study focused on temporal expression extraction and temporal reasoning . |
| Approach: | They propose a taxonomy of eight temporal frames grounded in prior work on time and framing . they analyze frame prevalence, co-occurrence patterns, and lexical cues from a news corpus . |
| Outcome: | The proposed taxonomy outperforms zero-shot models at the sentence level . it shows that temporal framing is learnable at the sentences level compared to other methods . |
Investigating the Emergent Audio Classification Ability of ASR Foundation Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Text and vision foundation models can perform many tasks in a zero-shot setting . however, there has been little work on the zero-shoot abilities of ASR foundation models . |
| Approach: | They investigate the ability of ASR foundation models to perform zero-shot audio classification using text prompts and a decoding probability generator. |
| Outcome: | The proposed model outperforms state-of-the-art models on audio classification datasets without training them on extra data or adding any parameters. |
Definitions Matter: Guiding GPT for Multi-label Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent success of Large Language Models (LLMs) is due to their superior performance on various tasks such as text generation, summarization, question answering, and inductive reasoning. |
| Approach: | They propose to generate definitions from examples and use them for zero-shot classification and to investigate how an LLM makes use of the definitions. |
| Outcome: | The proposed method improves the definitions of class labels and improves their understanding of the definition. |
RWKV-CLIP: A Robust Vision-Language Representation Learner (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using large image-text datasets, large-scale image-data sets have been used for visionlanguage pre-training. |
| Approach: | They propose a framework that leverages Large Language Models to combine and refine information from web-based image-text pairs, synthetic captions, and detection tags. |
| Outcome: | The proposed framework can combine and refine information from web-based image-text pairs, synthetic captions, and detection tags. |
Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP (2024.emnlp-main)
Copied to clipboard
| Challenge: | Image-text contrastive models like CLIP struggle on compositional visio-linguistic tasks where their performance is no better than random chance. |
| Approach: | They propose a distillation method to enhance CLIP's compositional visio-linguistic reasoning by using a model-derived distillation objective borrowed from large text-to-image generative models like Stable-Diffusion. |
| Outcome: | The proposed method improves CLIP models' visio-linguistic performance on the Winoground benchmark by 7% while on the ARO dataset, it boosts performance by 3%. |
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current methods for multimodal representation learning for electrocardiograms often result in suboptimal alignment of ECG signals with their corresponding text reports. |
| Approach: | They propose a framework to learn ECG representations by aligning ECG signals with paired free-text reports. |
| Outcome: | The proposed framework outperforms existing methods in zero-shot classification and linear probing tasks using 12 leads. |
Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data (2025.naacl-long)
Copied to clipboard
Haonan Wang, Minbin Huang, Runhui Huang, Lanqing Hong, Hang Xu, Tianyang Hu, Xiaodan Liang, Zhenguo Li, Hong Cheng, Kenji Kawaguchi
| Challenge: | Contrastive Language-Image Pre-training (CLIP) is a standard for cross-modal image-text representation learning. |
| Approach: | They propose a framework that enhances pre-trained CLIP models by exploiting challenging text-image pairs within existing datasets. |
| Outcome: | The proposed framework improves CLIP models by exploiting text-image pairs in training. |
Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) with chat interfaces are increasingly popular in various scientific fields, for a variety of tasks related to social science research questions. |
| Approach: | They propose to use large language models to combine human and machine expertise to improve their models' performance. |
| Outcome: | The proposed model performs better with co-created definitions than with expert-written definitions. |
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations (2023.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that CLORE is superior to baselines on zero-shot classification tasks. |
| Approach: | They propose a framework for classification by logically parsing and reasoning on natural language explanations. |
| Outcome: | The proposed framework outperforms baselines on zero-shot classification tasks. |
Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Learning and using abstract perceptual concepts is under-investigated in the language-and-vision field. |
| Approach: | They propose a framework for testing category-level perceptual grounding in multi-modal language models by using separate neural networks to generate and interpret descriptions of visual categories. |
| Outcome: | The proposed framework compares prototype- and interpretation-based representations with the performance of the generation model and the interpretation model, which is an indicator of perceptual grounding. |
Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data? (2025.findings-acl)
Copied to clipboard
Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Nikolay Burlutskiy, Fariba Yousefi, Rossella Arcucci
| Challenge: | Medical Vision-Language Pretraining (MedVLP) models typically require large-scale datasets with paired, high-quality image-text data. |
| Approach: | They propose to generate large-scale synthetic image-text pairs using off-the-shelf generative models . they propose to isolate model and training settings, focusing entirely from the data perspective. |
| Outcome: | The proposed pipeline outperforms models trained on real data by 3.8% on averaged AUC on zero-shot classification tasks. |
The Benefits of Label-Description Training for Zero-Shot Text Classification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data to classify among specific label sets in downstream tasks. |
| Approach: | They propose to use a small finetuning dataset to describe the labels for a task and to use it to further improve zero-shot accuracies. |
| Outcome: | The proposed model is more accurate than zero-shot by 17-19% absolute across topic and sentiment datasets and more robust to choices required for zero- shot classification. |
PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation (2025.acl-long)
Copied to clipboard
| Challenge: | Psychological studies have shown that infusing persuasion knowledge enhances disinformation detection. |
| Approach: | They introduce a persuasion-augmented chain of thought approach that leverages persulasion to improve disinformation detection in zero-shot classification. |
| Outcome: | The proposed approach outperforms competitive methods by 15% on online news and social media posts. |
Using tournaments to calculate AUROC for zero-shot classification with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models perform well on zero-shot classification tasks, but are difficult to compare to supervised classifiers due to the lack of a modifiable decision boundary. |
| Approach: | They propose a method that transforms binary classification tasks into pairwise comparisons between instances within a dataset. |
| Outcome: | The proposed method produces relative rankings of instances using the Elo rating system . |
Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | In-context learning (ICL) performance is highly sensitive to prompt design, yet the impact of class label options (e.g. lexicon or order) in zero-shot classification remains underexplored. |
| Approach: | They propose a post-hoc method for selecting optimal label sets in zero-shot ICL with large language models. |
| Outcome: | The proposed method consistently achieves performance gains of 0.54 to 0.76 compared to the conventional method. |