Enhancing LLM-Based Social Bot via an Adversarial Learning Framework

TL;DR

This paper presents EvoBot, an adversarial learning framework that enhances LLM-based social bots to generate more human-like, socially responsive content by iterative refinement and co-adaptive detection, improving realism and detection robustness.

Contribution

Introduces EvoBot, a novel adversarial learning framework combining supervised fine-tuning, preference optimization, and co-adaptive detection to improve social bot realism and responsiveness.

Findings

EvoBot produces human-like, diverse content aligned with user profiles.

EvoBot increasingly bypasses the co-adapting detector, indicating improved realism.

The framework enhances the detector's ability to distinguish bots from humans.

Abstract

Developing Large Language Model (LLM) agents that exhibit human-like behavior, encompassing not only individual heterogeneity rooted in unique user profiles but also adaptive response to socially connected neighbors, is a significant research challenge. Social media platforms, with their diverse user data and explicit social structures, provide an ideal testbed for such investigations. This paper introduces EvoBot, an \textbf{Evo}lving LLM-based social \textbf{Bot} that significantly enhances human-like generative capabilities through a novel adversarial learning framework. EvoBot is initialized by Supervised Fine-Tuning (SFT) on representative data from social media and then iteratively refines its generation of sophisticated, human-like content via Direct Preference Optimization (DPO). This refinement is guided by feedback from a co-adapting \textbf{Detector} which concurrently improves its ability to distinguish EvoBot from humans, thereby creating an increasingly challenging learning environment for EvoBot. Experiments demonstrate that EvoBot generates content aligned with diverse user profiles, increasingly bypassing the co-adapting Detector through human-like expression. Moreover, it exhibits strong social responsiveness, more accurately modeling real-world opinion dynamics and information spread in multi-agent simulations. The framework also yields a more robust Detector, underscoring its broader utility for both advanced agent development and related detection tasks. The code is available at https://github.com/kfq20/EvoBot.