Affective directions in activation space: An interpretable inference-time control mechanism
Authors:
- Yurui DongYDYurui Dong
- Luozhijie JinLJLuozhijie Jin
- Yao YangYYYao Yang
- Bingjie LuBLBingjie Lu
- Jiaxi YangJYJiaxi Yang
- Zhi LiuZLZhi Liu
- 9 October 2026
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 185
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (82405609)
- Key Research and Development Program of Zhejiang Province
This publication has 35 references indexed in Scilit:
- Burnout in Teachers: The Role of Emotion Regulation, Empathy, and Educational Level TaughtSchool Mental Health, 2025
- The role of large language models in personalized learning: a systematic review of educational impactDiscover Sustainability, 2025
- Large language models-powered clinical decision support: enhancing or replacing human expertise?Intelligent Medicine, 2025
- Large Language Model Influence on Diagnostic ReasoningJAMA Network Open, 2024
- The current state of empathy, compassion and person-centred communication training in healthcare: An umbrella reviewPatient Education and Counseling, 2023
- Teachers’ consistency of emotional support moderates the association between young children's regulation capacities and their preschool adjustmentPsychology in the Schools, 2022
- Early childhood teachers' stress and children's social, emotional, and behavioral functioningJournal of Applied Developmental Psychology, 2019
- A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability ResearchJournal of Chiropractic Medicine, 2016
- Core affect, prototypical emotional episodes, and other things called emotion: Dissecting the elephant.Journal of Personality and Social Psychology, 1999
- Constants across cultures in the face and emotion.Journal of Personality and Social Psychology, 1971