X-Troll: eXplainable Detection of State-Sponsored Information Operations Agents

TL;DR

X-Troll is an explainable framework that combines linguistically-informed adapters with large language models to detect state-sponsored trolls and provide human-readable explanations of their manipulation strategies.

Contribution

It introduces a novel, interpretable approach integrating expert linguistic knowledge with LLMs for detecting sophisticated state-sponsored information operations.

Findings

Outperforms baseline models in accuracy on real-world data

Provides human-readable explanations of manipulation strategies

Enhances transparency in automated troll detection

Abstract

State-sponsored trolls, malicious actors who deploy sophisticated linguistic manipulation in coordinated information campaigns, posing threats to online discourse integrity. While Large Language Models (LLMs) achieve strong performance on general natural language processing (NLP) tasks, they struggle with subtle propaganda detection and operate as ``black boxes'', providing no interpretable insights into manipulation strategies. This paper introduces X-Troll, a novel framework that bridges this gap by integrating explainable adapter-based LLMs with expert-derived linguistic knowledge to detect state-sponsored trolls and provide human-readable explanations for its decisions. X-Troll incorporates appraisal theory and propaganda analysis through specialized LoRA adapters, using dynamic gating to capture campaign-specific discourse patterns in coordinated information operations. Experiments on real-world data demonstrate that our linguistically-informed approach shows strong performance compared with both general LLM baselines and existing troll detection models in accuracy while providing enhanced transparency through expert-grounded explanations that reveal the specific linguistic strategies used by state-sponsored actors. X-Troll source code is available at: https://github.com/ltian678/xtroll_source/.