paper-with-me

Papers

Active Example Selection for In-Context Learning

2022-11-08 · Yiming Zhang, Shi Feng, Chenhao Tan

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5.8\%$ improvement on average. Examples selected from our learned policies can even achieve a small improvement on GPT-3 Ada. However, the improvement diminishes on larger GPT-3 models, suggesting emerging capabilities of large language models.

📄 PDF Abstract BibTeX arXiv:2211.04486

Code (1)

chicagohai/active-example-selection 공식 구현 pytorch

Tasks

In-Context Learning

Methods 이 논문이 사용한 방법론

15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Targeting Optimal Active Learning via Example Quality

2014-07-30 · Lewis P. G. Evans, Niall M. Adams, Christoforos Anagnostopoulos

In many classification problems unlabelled data is abundant and a subset can be chosen for labelling. This defines the context of active learning (AL), where methods systematically select that subset, to improve a classi…

Active LearningGeneral Classification

Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection

2024-08-17 · Hsiu-Yuan Huang, Zichen Wu, Yutong Yang, Junzhao Zhang 외

Large Language Models (LLMs) have shown remarkable performance across a wide range of downstream tasks. However, it is challenging for users to discern whether the responses of LLM are generated with certainty or are fab…

Active LearningIn-Context LearningInformativeness

Activation-Based Active Learning for In-Context Learning: Challenges and Insights

2026-06-03 · Yaseen M. Osman, Geoff V. Merrett, Stuart E. Middleton arxiv

Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of transformer activations. In this paper, we test the hypothesis …

Active Learning

Active Learning Principles for In-Context Learning with Large Language Models

2023-05-23 · Katerina Margatina, Timo Schick, Nikolaos Aletras, Jane Dwivedi-Yu

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs…

Active LearningDiversityFew-Shot LearningIn-Context Learning

What Makes Good Few-shot Examples for Vision-Language Models?

2024-05-22 · Zhaojun Guo, Jinghui Lu, Xuejing Liu, Rui Zhao 외

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 l…

Active LearningFew-Shot LearningPrompt Learning