English

Enhancing In-context Learning via Linear Probe Calibration

Computation and Language 2024-01-24 v1 Artificial Intelligence Machine Learning

Abstract

In-context learning (ICL) is a new paradigm for natural language processing that utilizes Generative Pre-trained Transformer (GPT)-like models. This approach uses prompts that include in-context demonstrations to generate the corresponding output for a new query input. However, applying ICL in real cases does not scale with the number of samples, and lacks robustness to different prompt templates and demonstration permutations. In this paper, we first show that GPT-like models using ICL result in unreliable predictions based on a new metric based on Shannon entropy. Then, to solve this problem, we propose a new technique called the Linear Probe Calibration (LinC), a method that calibrates the model's output probabilities, resulting in reliable predictions and improved performance, while requiring only minimal additional samples (as few as five labeled data samples). LinC significantly enhances the ICL test performance of GPT models on various benchmark datasets, with an average improvement of up to 21%, and up to a 50% improvement in some cases, and significantly boosts the performance of PEFT methods, especially in the low resource regime. Moreover, LinC achieves lower expected calibration error, and is highly robust to varying label proportions, prompt templates, and demonstration permutations. Our code is available at \url{https://github.com/mominabbass/LinC}.

Keywords

Cite

@article{arxiv.2401.12406,
  title  = {Enhancing In-context Learning via Linear Probe Calibration},
  author = {Momin Abbas and Yi Zhou and Parikshit Ram and Nathalie Baracaldo and Horst Samulowitz and Theodoros Salonidis and Tianyi Chen},
  journal= {arXiv preprint arXiv:2401.12406},
  year   = {2024}
}

Comments

Accepted at AISTATS2024

R2 v1 2026-06-28T14:24:11.073Z