"Can You Tell Me?": Designing Copilots to Support Human Judgement in Online Information Seeking
This study addresses the risk that generative AI in information retrieval may foster user overreliance, thereby undermining critical thinking and independent verification skills. To counter this, the authors propose a large language model–based conversational collaborator that eschews direct answers in favor of Socratic questioning, employing cognitive scaffolding to prompt users to reflect on the credibility of information and cultivate digital literacy. Evaluated through a randomized controlled trial and mixed-methods analysis, the system elicited significantly enhanced metacognitive reflection among users. However, it did not yield measurable improvements in answer accuracy or search engagement, highlighting an inherent tension between efficiency-oriented search behaviors and the cultivation of critical information literacy. This approach offers a novel paradigm that supports—rather than supplants—user judgment.