AINeutralarXiv – CS AI · Mar 95/10
🧠
Evaluating LLM Alignment With Human Trust Models
Researchers analyzed how the GPT-J-6B language model internally represents and reasons about trust by comparing its embeddings to established human trust models. The study found that the AI's trust representation most closely aligns with the Castelfranchi socio-cognitive model, suggesting LLMs encode social concepts in meaningful ways.