English
Related papers

Related papers: Few-shot Prompting for Pairwise Ranking: An Effect…

200 papers

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Yonglong Tian , Yue Wang , Dilip Krishnan , Joshua B. Tenenbaum , Phillip Isola

Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is classified by finding the nearest prototype from the…

Computer Vision and Pattern Recognition · Computer Science 2021-06-04 Zhizheng Zhang , Cuiling Lan , Wenjun Zeng , Zhibo Chen , Shih-Fu Chang

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to…

Computer Vision and Pattern Recognition · Computer Science 2019-06-13 Spyros Gidaris , Andrei Bursuc , Nikos Komodakis , Patrick Pérez , Matthieu Cord

Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has…

Machine Learning · Computer Science 2020-04-14 Meiyu Huang , Xueshuang Xiang , Yao Xu

Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…

Computation and Language · Computer Science 2025-09-17 Yongjian Tang , Doruk Tuncel , Christian Koerner , Thomas Runkler

Standard few-shot benchmarks are often built upon simplifying assumptions on the query sets, which may not always hold in practice. In particular, for each task at testing time, the classes effectively present in the unlabeled query set are…

Machine Learning · Computer Science 2022-10-27 Ségolène Martin , Malik Boudiaf , Emilie Chouzenoux , Jean-Christophe Pesquet , Ismail Ben Ayed

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and…

Computer Vision and Pattern Recognition · Computer Science 2020-01-14 Wei-Yu Chen , Yen-Cheng Liu , Zsolt Kira , Yu-Chiang Frank Wang , Jia-Bin Huang

Conducting pairwise comparisons is a widely used approach in curating human perceptual preference data. Typically raters are instructed to make their choices according to a specific set of rules that address certain dimensions of image…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Hossein Talebi , Ehsan Amid , Peyman Milanfar , Manfred K. Warmuth

This study presents a comprehensive reproducibility and extension analysis of the Setwise prompting methodology for zero-shot ranking with Large Language Models (LLMs), as proposed by Zhuang et al. We evaluate its effectiveness and…

Information Retrieval · Computer Science 2025-04-16 Jakub Podolak , Leon Peric , Mina Janicijevic , Roxana Petcu

Recent studies show that large language models (LLMs) can be instructed to effectively perform zero-shot passage re-ranking, in which the results of a first stage retrieval method, such as BM25, are rated and reordered to improve relevance.…

Information Retrieval · Computer Science 2023-10-24 Andrew Drozdov , Honglei Zhuang , Zhuyun Dai , Zhen Qin , Razieh Rahimi , Xuanhui Wang , Dana Alon , Mohit Iyyer , Andrew McCallum , Donald Metzler , Kai Hui

Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. The Web likely contains the information necessary to excel…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Hamed Damirchi , Cristian Rodríguez-Opazo , Ehsan Abbasnejad , Damien Teney , Javen Qinfeng Shi , Stephen Gould , Anton van den Hengel

In this work, we aim to capitalize on the unique few-shot capabilities of large-scale language models (LSLMs) to overcome some of their challenges with respect to grounding to factual and up-to-date information. Motivated by semi-parametric…

Computation and Language · Computer Science 2022-05-24 Angeliki Lazaridou , Elena Gribovskaya , Wojciech Stokowiec , Nikolai Grigorev

A particularly successful class of approaches for few-shot learning combines language models with prompts -- hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires…

Computation and Language · Computer Science 2023-10-24 Rami Aly , Xingjian Shi , Kaixiang Lin , Aston Zhang , Andrew Gordon Wilson

The ability to learn from limited data, or few-shot learning, is a desirable and often critical requirement for NLP systems. While many existing methods do poorly at learning from a handful of examples, large pretrained language models have…

Computation and Language · Computer Science 2021-06-04 Sawan Kumar , Partha Talukdar

Prompting methods have shown impressive performance in a variety of text mining tasks and applications, especially few-shot ones. Despite the promising prospects, the performance of prompting model largely depends on the design of prompt…

Computation and Language · Computer Science 2023-06-16 Hongyuan Dong , Weinan Zhang , Wanxiang Che

Pairwise human-preference platforms such as Chatbot Arena have become central to large language model (LLM) evaluation, yet reliable task-specific ranking remains challenging. Global leaderboards mask task heterogeneity, while ranking each…

Methodology · Statistics 2026-05-29 Jiachun Li , David Simchi-Levi , Will Wei Sun

Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…

Computation and Language · Computer Science 2023-05-17 Jinghui Lu , Dongsheng Zhu , Weidong Han , Rui Zhao , Brian Mac Namee , Fei Tan

Prompting language models (LMs) with training examples and task descriptions has been seen as critical to recent successes in few-shot learning. In this work, we show that finetuning LMs in the few-shot setting can considerably reduce the…

Computation and Language · Computer Science 2021-07-02 Robert L. Logan , Ivana Balažević , Eric Wallace , Fabio Petroni , Sameer Singh , Sebastian Riedel

While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed from unlabeled data. Exploiting the complementarity of…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Zhengyu Chen , Jixie Ge , Heshen Zhan , Siteng Huang , Donglin Wang

Preference-based reinforcement learning (RL) has emerged as a new field in robot learning, where humans play a pivotal role in shaping robot behavior by expressing preferences on different sequences of state-action pairs. However,…

Robotics · Computer Science 2024-02-26 Simon Holk , Daniel Marta , Iolanda Leite