MetaCues: Enhancing Critical Thinking in Generative AI Use with Metacognitive Cues

Overview

As generative AI systems become increasingly prevalent in search and information retrieval, there is a growing concern about users’ over-reliance on AI-generated content without proper critical evaluation. MetaCues addresses this challenge by integrating metacognitive cue techniques into AI search interfaces to enhance users’ critical thinking abilities. The system employs strategic cues that encourage users to reflect on their information needs, evaluate AI responses, and develop more sophisticated search strategies.

MetaCues leverages research in metacognition and critical thinking to design interventions that prompt users to:

  • Reflect on their search goals and information requirements
  • Evaluate the credibility and relevance of AI-generated responses
  • Consider alternative perspectives and potential biases
  • Develop more effective search strategies through guided reflection
  • ASIS&T 2025: Anjali Singh, Zhitong Guan, Soo Young Rieh, Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts, 88th Annual Meeting of the Association for Information Science & Technology, Nov. 14 – 18, 2025, Washington, DC, USA.
  • CHI 2025: Anjali Singh, Karan Taneja, Zhitong Guan, Avijit Ghosh, Protecting human cognition in the age of AI, Tools for Thought Workshop at the 2025 CHI Conference on Human Factors in Computing Systems.

Research Contributions

This research work aims to contribute to the growing field of human-AI interaction by:

  • Demonstrating the effectiveness of metacognitive interventions in AI search contexts
  • Providing empirical evidence for the impact of cue strategies on user behavior
  • Developing novel techniques for measuring critical thinking in AI-assisted search tasks

Technologies and Tools

LLMs, Metacognitive Cues, OpenAI API, Search Interface Design, ReactJS, Flask

Team

Anjali Singh (Project Lead), Karan Taneja, Zhitong Guan, Soo Young Rieh