Scheming Is a Symptom: Alignment Research Should Probe Reflexive FragilityNan ZhangHeng XuAdvances in Neural Information Processing Systems (NeurIPS)2026
Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive ReasoningNan ZhangHeng XuAdvances in Neural Information Processing Systems (NeurIPS)2026
Scheming Is a Symptom: Alignment Research Should Probe Reflexive FragilityNan ZhangHeng XuNeurIPS2026
Why Decoding Sharpens Without Resolving: Lock-in and Confusion in Autoregressive ReasoningNan ZhangHeng XuNeurIPS2026
Testing of Reverse Causality Using Semi-Supervised Machine LearningNan ZhangHeng XuManuel VaulontZhen ZhangPsychometrika9032025
Testing of Reverse Causality Using Semi-Supervised Machine LearningNan ZhangHeng XuM. VaulontZ. ZhangPsychometrika9032025
An Onto-Epistemological Analysis of Information Privacy ResearchHeng XuNan ZhangInformation Systems Research3532024
An Onto-Epistemological Analysis of Information Privacy ResearchHeng XuNan ZhangInformation Systems Research3532024
Fairness of Ratemaking for Catastrophe Insurance: Lessons from Machine LearningNan ZhangHeng XuInformation Systems Research3522024
Fairness of Ratemaking for Catastrophe Insurance: Lessons from Machine LearningNan ZhangHeng XuInformation Systems Research3522024