Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

TL;DR

This paper introduces GLIM, a scalable, gradient-free large language model-based framework for strategic classification that leverages in-context learning without fine-tuning, demonstrating robustness and efficiency in real-world applications.

Contribution

The paper proposes GLIM, a novel large language model-based method for strategic classification that avoids fine-tuning and supports dynamic environments, addressing scalability issues of prior models.

Findings

GLIM is robust across diverse datasets.

GLIM is more efficient than traditional methods.

GLIM effectively handles large-scale strategic classification.

Abstract

Strategic classification~(SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, which are largely based on linear models or shallow neural networks, face significant limitations in terms of scalability and capacity when applied to real-world datasets with significantly increasing scale, especially in financial services and the internet sector. In this paper, we investigate how to leverage large language models to design a more scalable and efficient SC framework, especially in the case of growing individuals engaged with decision-making processes. Specifically, we introduce GLIM, a gradient-free SC method grounded in in-context learning. During the feed-forward process of self-attention, GLIM implicitly simulates the typical bi-level optimization process of SC, including both the feature manipulation and decision rule optimization. Without fine-tuning the LLMs, our proposed GLIM enjoys the advantage of cost-effective adaptation in dynamic strategic environments. Theoretically, we prove GLIM can support pre-trained LLMs to adapt to a broad range of strategic manipulations. We validate our approach through experiments with a collection of pre-trained LLMs on real-world and synthetic datasets in financial and internet domains, demonstrating that our GLIM exhibits both robustness and efficiency, and offering an effective solution for large-scale SC tasks.