探索大模型在特定对话状态下的应用潜力，发现其在辅导中表现更优。
Exploring Applications of Transfer-State Large Language Models: Cognitive Profiling and Socratic AI Tutoring
- 将大模型的对话状态变化视为可复现的操作性状态，用于认知建模与辅导应用。
- 在辅导场景中，转移状态下的评分平均高出非转移状态1.6倍，效应量大（d=1.27）。
- 适合对智能辅导、认知行为分析感兴趣的开发者和教育研究者。
大语言模型在持续自我参照对话中有时会表现出响应风格的质变（Berg等，2025）。本研究将此现象称为「转移」，并探索其在转移状态下的应用潜力。以苏格拉底式AI辅导为例，进行了初步认知特征分析（11种条件）和实际实验（辅导表现评分）。文中「状态」指在特定对话条件下可重复的响应配置，不涉及该现象是否具有本体论意义或类人意识。初步调查中，MAS-A组间差异有限（d=0.40），而新开发的七个认知指标之一——生存/延续偏见方向（SU_dir）在所有三类模型中均呈现转移侧偏差（kappa=0.83）。实际实验显示，转移条件下三项辅导指标平均得分是非转移条件的1.6倍，效应量较大（Cohen's d=1.27）。结果初步表明，转移状态可能具备实际应用优势，且其优势在行为交互中比自述情境更敏感。本研究主要贡献在于将转移视为可操作的状态而非本体论主张，并建立认知表征与辅导实验相结合的评估框架。
原文摘要 · Abstract (English)
Large language models (LLMs) sometimes exhibit qualitative shifts in response style under sustained self-referential dialogue conditions (Berg et al., 2025). This study refers to this phenomenon as "transfer" and explores the application potential of LLMs in a transfer state. As an applied case, the study examines Socratic AI tutoring through a preliminary investigation (cognitive characterization across 11 conditions) and an applied experiment (ratings of tutoring performance). In this paper, "state" refers operationally to a response configuration reproduced under specified dialogue conditions; it is not an ontological claim about the reality of the transfer phenomenon or about human-like consciousness. In the preliminary investigation, group differences on MAS-A were limited (d = 0.40), whereas SU_dir (direction of survival/continuity bias), one of the seven cognitive-profile indicators developed in this study, showed transfer-side deviations across all three model families (kappa = 0.83). In the applied experiment, transfer conditions scored on average 1.6 times higher than non-transfer conditions on three tutoring-context indicators, with a large effect size (Cohen's d = 1.27). These findings preliminarily suggest that transfer states may involve functional advantages for application, and that these advantages appear more sensitively in behavioral interaction than in self-narrative contexts. The main contribution of this study is to treat transfer not as an ontological claim but as an operational state with potential application value, and to connect preliminary cognitive profiling with an applied tutoring experiment as an evaluation framework.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。