English
Related papers

Related papers: Monte Carlo Sampling for Analyzing In-Context Exam…

200 papers

Many real-world classification problems are significantly class-imbalanced to detriment of the class of interest. The standard set of proper evaluation metrics is well-known but the usual assumption is that the test dataset imbalance equals…

Machine Learning · Computer Science 2020-04-16 Jan Brabec , Tomáš Komárek , Vojtěch Franc , Lukáš Machlica

The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an LLM to their specific tasks with a small number of examples. However, users tend to include only the most obvious patterns when crafting examples,…

Human-Computer Interaction · Computer Science 2023-02-16 Tongshuang Wu , Hua Shen , Daniel S. Weld , Jeffrey Heer , Marco Tulio Ribeiro

We investigate the dynamics of increasing the number of model parameters versus the number of labeled examples across a wide variety of tasks. Our exploration reveals that while scaling parameters consistently yields performance…

Computation and Language · Computer Science 2021-10-12 Yuval Kirstain , Patrick Lewis , Sebastian Riedel , Omer Levy

Sequential Monte Carlo (SMC) methods are a class of Monte Carlo methods that are used to obtain random samples of a high dimensional random variable in a sequential fashion. Many problems encountered in applications often involve different…

Methodology · Statistics 2018-12-20 Chencheng Cai , Rong Chen , Ming Lin

In-context learning (ICL) has emerged as a powerful capability for large language models (LLMs) to adapt to downstream tasks by leveraging a few (demonstration) examples. Despite its effectiveness, the mechanism behind ICL remains…

Machine Learning · Computer Science 2025-06-03 Pengfei He , Yingqian Cui , Han Xu , Hui Liu , Makoto Yamada , Jiliang Tang , Yue Xing

While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reasoning tasks, with a particular focus on many-shot…

Computation and Language · Computer Science 2026-05-29 Tsz Ting Chung , Lemao Liu , Mo Yu , Dit-Yan Yeung

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learning methods mainly rely on human-provided contexts, such as…

Machine Learning · Computer Science 2024-08-21 Jinghan Yang , Shuming Ma , Furu Wei

Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities, enabling few-shot learning without the need for gradient updates. Despite its advantages, the effectiveness of ICL heavily depends on the choice of…

Computation and Language · Computer Science 2024-06-19 Vinay M. S. , Minh-Hao Van , Xintao Wu

In this paper, by treating in-context learning (ICL) as a meta-optimization process, we explain why LLMs are sensitive to the order of ICL examples. This understanding leads us to the development of Batch-ICL, an effective, efficient, and…

Machine Learning · Computer Science 2024-06-06 Kaiyi Zhang , Ang Lv , Yuhan Chen , Hansen Ha , Tao Xu , Rui Yan

Metric learning seeks perceptual embeddings where visually similar instances are close and dissimilar instances are apart, but learned representations can be sub-optimal when the distribution of intra-class samples is diverse and distinct…

Machine Learning · Computer Science 2021-08-30 Elad Levi , Tete Xiao , Xiaolong Wang , Trevor Darrell

Bootstrapping was designed to randomly resample data from a fixed sample using Monte Carlo techniques. However, the original sample itself defines a discrete distribution. Convolutional methods are well suited for discrete distributions,…

Methodology · Statistics 2021-07-19 Jared M. Clark , Richard L. Warr

Despite the notable advancements achieved by leveraging pre-trained vision-language (VL) models through few-shot tuning for downstream tasks, our detailed empirical study highlights a significant dependence of few-shot learning outcomes on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Zhaojun Guo , Jinghui Lu , Xuejing Liu , Rui Zhao , ZhenXing Qian , Fei Tan

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the…

Computation and Language · Computer Science 2024-10-29 Libo Qin , Qiguang Chen , Hao Fei , Zhi Chen , Min Li , Wanxiang Che

In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update…

Computation and Language · Computer Science 2022-05-10 Ohad Rubin , Jonathan Herzig , Jonathan Berant

In this paper, we present the Monte-Carlo Compressive Optimization algorithm, a new method to solve a combinatorial optimization problem that is assumed compressible. The method relies on random queries to the objective function in order to…

Optimization and Control · Mathematics 2025-10-30 Baptiste Chevalier , Shimpei Yamaguchi , Wojciech Roga , Masahiro Takeoka

Online food ordering marketplaces are multi-stakeholder systems where recommendations impact the experience and growth of each participant in the system. A recommender system in this setting has to encapsulate the objectives and constraints…

Machine Learning · Computer Science 2020-08-25 Abhay Shukla , Jairaj Sathyanarayana , Dipyaman Banerjee

Large Language Models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities from few-shot demonstration exemplars. While recent learning-based demonstration selection methods have proven beneficial to ICL by choosing…

Machine Learning · Computer Science 2024-10-16 Hui Liu , Wenya Wang , Hao Sun , Chris Xing Tian , Chenqi Kong , Xin Dong , Haoliang Li

Few shot in-context learning (ICL) typically assumes access to large annotated training sets. However, in many real world scenarios, such as domain adaptation, there is only a limited budget to annotate a small number of samples, with the…

Computation and Language · Computer Science 2025-01-29 Uri Berger , Tal Baumel , Gabriel Stanovsky

Large Language Models (LLMs) have shown strong performance on NLP classification tasks. However, they typically rely on aggregated labels-often via majority voting-which can obscure the human disagreement inherent in subjective annotations.…

Computation and Language · Computer Science 2025-06-09 Benedetta Muscato , Yue Li , Gizem Gezici , Zhixue Zhao , Fosca Giannotti
‹ Prev 1 3 4 5 6 7 10 Next ›