LLM-based Few-Shot Early Rumor Detection with Imitation Agent

TL;DR

This paper introduces a novel framework combining an autonomous agent and LLMs for early rumor detection in social media, achieving high accuracy with minimal training in data-scarce scenarios.

Contribution

It presents the first few-shot EARD method that trains only a lightweight agent, leveraging LLMs as training-free rumor detectors, improving early detection performance.

Findings

Outperforms existing EARD methods in accuracy.

Achieves earlier detection points.

Works effectively across multiple real-world datasets.

Abstract

Early Rumor Detection (EARD) aims to identify the earliest point at which a claim can be accurately classified based on a sequence of social media posts. This is especially challenging in data-scarce settings. While Large Language Models (LLMs) perform well in few-shot NLP tasks, they are not well-suited for time-series data and are computationally expensive for both training and inference. In this work, we propose a novel EARD framework that combines an autonomous agent and an LLM-based detection model, where the agent acts as a reliable decision-maker for \textit{early time point determination}, while the LLM serves as a powerful \textit{rumor detector}. This approach offers the first solution for few-shot EARD, necessitating only the training of a lightweight agent and allowing the LLM to remain training-free. Extensive experiments on four real-world datasets show our approach boosts performance across LLMs and surpasses existing EARD methods in accuracy and earliness.