Researchers have developed a new LLM-based framework called Cognitive World Model (CogWM) to evaluate social influence in dialogues. Unlike traditional methods that focus on surface-level text, CogWM tracks changes in a user's internal cognitive states, such as beliefs, desires, intentions, and emotions, throughout a conversation. The model, trained on over 150,000 user-turn samples, demonstrates strong performance in predicting cognitive states and distinguishing between different commercial agents based on their influence. AI
IMPACT This framework could enable more nuanced evaluation of AI agents in social contexts by tracking internal cognitive shifts rather than just surface-level responses.
RANK_REASON The item describes a new LLM-based framework and its evaluation, fitting the research category. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Daily Papers →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
