The emergence of in-context learning (ICL) enables large pre-trained language
models (PLMs) to make predictions for unseen inputs without updating
parameters. Despite its potential, ICL's effectiveness heavily relies on the
quality, quantity, and permutation of demonstrations, commonly leading to
suboptimal and unstable performance. In this paper, we tackle this challenge
for the first time from the perspective of demonstration augmentation.
Specifically, we start with enriching representations of demonstrations by
leveraging their deep feature distribution. We then theoretically reveal that
when the number of augmented copies approaches infinity, the augmentation is
approximately equal to a novel logit calibration mechanism integrated with
specific statistical properties. This insight results in a simple yet highly
efficient method that significantly improves the average and worst-case
accuracy across diverse PLMs and tasks. Moreover, our method effectively
reduces performance variance among varying demonstrations, permutations, and
templates, and displays the capability to address imbalanced class
distributions.

在这篇论文中，我们首次从演示增强的角度来解决上下文学习的挑战，通过丰富演示的表示以及集成特定的统计特性，我们提出了一种简单但高效的方法，显著提高了各种预训练语言模型和任务的平均和最坏情况准确性，并有效减少了不同演示、排列和模板之间的性能差异，并且具备处理不平衡类别分布的能力。

通过隐式示范增强上下文学习

Enhancing In-Context Learning via Implicit Demonstration Augmentation

Large Language Models (LLMs) have demonstrated an impressive capability known
as In-context Learning (ICL), which enables them to acquire knowledge from
textual demonstrations without the need for parameter updates. However, many
studies have highlighted that the model's performance is sensitive to the
choice of demonstrations, presenting a significant challenge for practical
applications where we lack prior knowledge of user queries. Consequently, we
need to construct an extensive demonstration pool and incorporate external
databases to assist the model, leading to considerable time and financial
costs. In light of this, some recent research has shifted focus towards
zero-shot ICL, aiming to reduce the model's reliance on external information by
leveraging their inherent generative capabilities. Despite the effectiveness of
these approaches, the content generated by the model may be unreliable, and the
generation process is time-consuming. To address these issues, we propose
Demonstration Augmentation for In-context Learning (DAIL), which employs the
model's previously predicted historical samples as demonstrations for
subsequent ones. DAIL brings no additional inference cost and does not rely on
the model's generative capabilities. Our experiments reveal that DAIL can
significantly improve the model's performance over direct zero-shot inference
and can even outperform few-shot ICL without any external information.

我们提出了一种名为 Demonstration Augmentation for In-context Learning (DAIL) 的方法，通过利用模型之前预测的历史样本作为后续样本的演示，来解决大型语言模型在零 - shot 学习中依赖外部信息并且生成过程耗时的问题，同时在没有任何外部信息的情况下，DAIL 不增加推理成本可以显著提高模型的性能。

零样本上下文学习的演示增强

Demonstration Augmentation for Zero-shot In-context Learning

Robotic systems that aspire to operate in uninstrumented real-world
environments must perceive the world directly via onboard sensing. Vision-based
learning systems aim to eliminate the need for environment instrumentation by
building an implicit understanding of the world based on raw pixels, but
navigating the contact-rich high-dimensional search space from solely sparse
visual reward signals significantly exacerbates the challenge of exploration.
The applicability of such systems is thus typically restricted to simulated or
heavily engineered environments since agent exploration in the real-world
without the guidance of explicit state estimation and dense rewards can lead to
unsafe behavior and safety faults that are catastrophic. In this study, we
isolate the root causes behind these limitations to develop a system, called
MoDem-V2, capable of learning contact-rich manipulation directly in the
uninstrumented real world. Building on the latest algorithmic advancements in
model-based reinforcement learning (MBRL), demo-bootstrapping, and effective
exploration, MoDem-V2 can acquire contact-rich dexterous manipulation skills
directly in the real world. We identify key ingredients for leveraging
demonstrations in model learning while respecting real-world safety
considerations -- exploration centering, agency handover, and actor-critic
ensembles. We empirically demonstrate the contribution of these ingredients in
four complex visuo-motor manipulation problems in both simulation and the real
world. To the best of our knowledge, our work presents the first successful
system for demonstration-augmented visual MBRL trained directly in the real
world. Visit this https URL for videos and more
details.

本研究通过模型强化学习、演示增强的方法，构建了一个能够直接在真实世界中学习联系丰富的灵巧操纵技能的系统 MoDem-V2，在模拟和实际环境中进行了实证研究，为直接在真实世界中进行演示增强的视觉模型强化学习提供了成功的案例。