Ehsan Dehghan

Designing for the Intentional Stance: Stance Misalignment, Value Alignment, and the Case for Care Ethics in Human-LLM Relationships (Extended Abstract)

Users are increasingly forming emotionally charged relation-ships with general-purpose large language models (LLMs), producing documented patterns of dependency, relational harm, and affective disappointment. Existing value alignment frameworks, including Reinforcement Learning from Human Feedback, Constitutional AI, a...