VIGIL: An Extensible System for Real-Time Detection and Mitigation of Cognitive Bias Triggers

2026-03-12

AI Summary

Online content frequently exploits cognitive biases to manipulate users, undermining the health of public discourse; however, existing tools struggle to detect and intervene on such manipulative mechanisms in real time. This work proposes VIGIL, the first browser extension supporting scroll-synchronized analysis that leverages large language models to identify cognitive bias triggers in textual content and provides reversible restatements to enhance user awareness. Built upon a modular architecture, VIGIL integrates multiple NLP-benchmarked analysis components and supports multi-tier privacy-preserving inference—from fully offline to cloud-based execution. The system is open-sourced and deployable in full functionality, demonstrably improving users’ ability to recognize and resist cognitive biases.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Responsible Web: Measurement, analysis, and circumvention of Web censorship
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

The rise of generative AI is posing increasing risks to online information integrity and civic discourse. Most concretely, such risks can materialise in the form of mis- and disinformation. As a mitigation, media-literacy and transparency tools have been developed to address factuality of information and the reliability and ideological leaning of information sources. However, a subtler but possibly no less harmful threat to civic discourse is to use of persuasion or manipulation by exploiting human cognitive biases and related cognitive limitations. To the best of our knowledge, no tools exist to directly detect and mitigate the presence of triggers of such cognitive biases in online information. We present VIGIL (VIrtual GuardIan angeL), the first browser extension for real-time cognitive bias trigger detection and mitigation, providing in-situ scroll-synced detection, LLM-powered reformulation with full reversibility, and privacy-tiered inference from fully offline to cloud. VIGIL is built to be extensible with third-party plugins, with several plugins that are rigorously validated against NLP benchmarks are already included. It is open-sourced at https://github.com/aida-ugent/vigil.

Problem

• cognitive bias
• misinformation
• online manipulation
• civic discourse
• information integrity

Innovation

• cognitive bias detection
• real-time mitigation
• LLM-powered reformulation
• privacy-tiered inference
• extensible browser extension