The Proactive Gap: A Scoping Review of Publicly Available LLM-based Browser Extensions and Their Potential to Mitigate Information Disorder

Abstract

Information disorder - including misinformation, disinformation, and malinformation - continues to undermine public discourse. Large language model (LLM)-based browser extensions show promise as tools for intervention, yet the role of publicly available tools in this space is not well understood. We conducted a scoping review of the Chrome Web Store and Firefox Add-Ons Store (May-July 2025), screening 951 records and including 34 extensions that use LLMs to process webpage content or user input. Through thematic analysis, we identified six interaction design concept categories: Extension Access, Display Mode, User Guidance, Customization, Content Understanding & Manipulation, and Navigation & Utilities. While extensions demonstrated diverse functionality and potential to debunk information disorder, they overwhelmingly operated as reactive tools, requiring explicit user initiation. Moreover, they rarely embedded themselves within webpage context. These findings reveal a "proactive gap"in current designs. Future LLM-powered extensions should move beyond responsiveness toward proactive, context-aware interventions that inoculate users against misinformation and strengthen critical thinking.