Pre-Conference Talk by LIAW Shao Yi | Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment

Digital knowledge production on collaborative platforms is governed by the interplay between crowd evaluation and feedback, especially in the generative AI era, when ideas and suggestions can be produced at far greater speed and scale. This study examines how evaluator identity disclosure shapes users’ evaluation and ideators’ incorporation of crowd feedback. Leveraging a design change on TVTropes that shifted voting from anonymous to attributable, we find that identity disclosure reduces both positive and negative evaluations, suggesting lower evaluative participation. We also find that the incorporation of detractor feedback is reduced with identity disclosure, indicating that ideators are less receptive to opposing input when feedback is tied to revealed evaluative stance. These findings reveal a governance trade-off: while identity disclosure enhances accountability and transparency, it simultaneously reduces participation and limits learning from dissent. 

This is a Pre-Conference talk for Twenty-second Symposium on Statistical Challenges in Electronic Commerce Research (SCERC 2026).

LIAW Shao Yi is a Ph.D. candidate in Information Systems, supervised by Prof. TANG Qian. Her general research interests are in product and human innovation with an emphasis on how individuals generate, evaluate, and refine ideas on digital platforms.