New LLM framework models household decisions using behavioral theory

Researchers have developed PEMAND, a new LLM-based framework designed to model household decision-making more realistically. This framework integrates behavioral theory into individualized persona modeling and simulates negotiations within households. PEMAND transforms demographic data into detailed profiles that encode attitudes, norms, and perceived behavioral controls, following the proposed Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework. Evaluations on travel behavior and residential mobility datasets show PEMAND consistently outperforms existing benchmarks. AI

IMPACT This framework could improve AI's ability to model complex human interactions in applications like urban planning and disaster management.

RANK_REASON The cluster contains a research paper detailing a novel LLM-based framework for household decision-making. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Household-Aware Chain-of-Planned-Behavior
• Yuran Sun

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →