When More Becomes Too Much: Cognitive Support and Interpretive Constraint in Generative-AI-Assisted Reading of Chinese Classical Poetry
Abstract
Generative AI can enrich classical Chinese poetry reading through paraphrases, images and video, but these representations also shape how poems are presented, interpreted and understood by readers. We compared four reading packages in a within-participant study with 64 Chinese readers: poem only (P), poem plus AI paraphrase (PT), PT plus a four-panel image (PTI), and PT plus a silent video (PTV). Paraphrases improved perceived comprehension, vividness and engagement and reduced mental effort, while increasing perceived interpretive constraint by 0.75 points on a seven-point scale. Static imagery further increased vividness by 1.29 points and constraint by 1.22, alongside greater engagement and lower effort. Video increased vividness by 0.43 points and distraction by 1.40; the distraction pattern persisted in sensitivity and paired-response analyses. Objective comprehension accuracy was near ceiling, with no detectable differences in the focal comparisons. These findings reveal two costs of richer AI support: stronger perceived direction of interpretation and, for video, greater distraction. With static imagery, poems became more vivid while their meanings felt more predetermined. We therefore argue that literary AI interfaces should balance experiential benefits with interpretive freedom and attention, prioritizing optional support, explicit presentation of interpretive choices and reader-controlled playback.
Keywords: Chinese Classical Poetry, Generative Artificial Intelligence, Multimedia Reading, Cognitive Load, Interpretive Constraint
DOI: 10.54941/ahfe1008335
Cite this paper
More from this volume
- AI-Enhanced Live-Streamed English Language Learning: Designing and Evaluating an Intelligent Platform for Chinese Learners
- "They Will Move": Confirmation Bias, Expectation Frames, and Premature Monitoring Drop Off in COLREG Encounters
- Automation transparency communication does not improve supervisory control performance, but shapes operator trust
- The influence of neuroticism on startle and surprise response: a flight simulator study
- EEG-Based Classification of Reward, Penalty, and Movement Events Across Four Video Games of Varying Complexity
- The Effects of Task Similarity and Time Pressure on Task Performance Following Interruptions in Complex Human-Computer Interaction Systems
- Trusting the Chain, Not the Black Box: A Provenance-Based Architecture for Human-Machine Teaming in Military Autonomy
- Design of a Simplified Humanoid Robot Face: Cultural Differences and Emotional Synchronization
- From Visual Observation to Auditory Interaction: A Human-Centered Tangible Music System Based on Physical Objects
- The Impact of Scarcity-Based Dark Patterns on User Performance, Perceived Darkness, and Workload in Subscription Services
- A Behavioral Observation Tool for Diagnosing Human–AI Interaction Profiles in Engineering Design Education
- The Mediated Moon: Semantic Mediation Between Gesture and Generative Image


AHFE Open Access