This synthesis of 45 papers published between January 2020 and June 2026 reveals an overreliance on multi-stage, text-centric pipelines, a predominance of active, screen-bound interactions, and a severe demographic skew toward young, university-campus-based cohorts in empirical evaluations.
Min-Jie Liu, Li-Huan Li, Xu-Ran Li et al.· 0 citations
There is a gap between assisted task performance and subsequent recall and sense of ownership in this setting, which motivates the need for assessment practices and AI learning tools that require students to explain, retrieve, and contribute to the work they submit as active participants in their education.
Christian Bergh, B. Tag, Alexandra Vassar et al.· 0 citations
Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophancy, a well-documented by-product of alignment, causes the model to over-agree with the user regardless of factual and objective information. However, existing group ali...
Hao-Kai Zhao, Yunze Xiao, Wei-Hao Xuan et al.· 0 citations
Abstract Conversational agents are increasingly expected to adapt across contexts and evolve their personalities through interactions, yet most remain static once configured. We present an exploratory study of how user expectations form and evolve when agent personality is made dynamically adjustable. To investigate th...