Fairness-guided Few-shot Prompting for Large Language Models

TL;DR

This paper introduces a fairness-guided prompt search method for large language models that reduces predictive bias, leading to improved in-context learning performance across various tasks.

Contribution

It proposes a novel bias evaluation metric and a greedy search strategy to identify prompts that enhance model performance and fairness.

Findings

Prompt bias correlates with predictive quality.

The proposed method improves GPT-3 in-context learning results.

Enhanced interpretability of prompt selection process.

Abstract

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples. However, prior research has shown that in-context learning can suffer from high instability due to variations in training examples, example order, and prompt formats. Therefore, the construction of an appropriate prompt is essential for improving the performance of in-context learning. In this paper, we revisit this problem from the view of predictive bias. Specifically, we introduce a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes. Then we empirically show that prompts with higher bias always lead to unsatisfactory predictive quality. Based on this observation, we propose a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning. We perform comprehensive experiments with state-of-the-art mainstream models such as GPT-3 on various downstream tasks. Our results indicate that our method can enhance the model's in-context learning performance in an effective and interpretable manner.