MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters

Abstract

State-sponsored trolls are the main actors of influence campaigns on social media and automatic troll detection is important to combat misinformation at scale. Existing troll detection models are developed based on training data for known campaigns (e.g. the influence campaign by Russia's Internet Research Agency on the 2016 US Election), and they fall short when dealing with novel campaigns with new targets. We propose MetaTroll, a text-based troll detection model based on the meta-learning framework that enables high portability and parameter-efficient adaptation to new campaigns using only a handful of labelled samples for few-shot transfer. We introduce campaign-specific transformer adapters to MetaTroll to "memorise" campaign-specific knowledge so as to tackle catastrophic forgetting, where a model "forgets" how to detect trolls from older campaigns due to continual adaptation. Our experiments demonstrate that MetaTroll substantially outperforms baselines and state-of-the-art few-shot text classification models. Lastly, we explore simple approaches to extend MetaTroll to multilingual and multimodal detection. Source code for MetaTroll is available at: https://github.com/ltian678/metatroll-code.git CCS CONCEPTS• Computing methodologies → Natural language processing; Information extraction.

Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models

“…Claim verification (Guo et al, 2022) has become increasingly important due to widespread online misinformation (Tian et al, 2023;Jin et al, 2023). Most of the existing claim verification models (Zhou et al, 2019;Jin et al, 2022;Yang et al, 2022;Wadden et al, 2022b;Liu et al, 2020;Zhong et al, 2020) use an automated pipeline that consists Table 1: An example from FOLK with GPT-3.5 on HoVER, a multi-hop claim verification dataset.…”