Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
This work addresses the challenge of improving AI decision-making through emotional awareness, though it appears incremental as it applies existing methods like LoRA fine-tuning to a new emotional dataset.
This research tackled the problem of enhancing collective intelligence in Large Language Models by integrating emotional diversity, finding that emotional integration shapes response patterns while maintaining acceptable prediction accuracy on a distance estimation task across 15,064 persona configurations.
This research investigates the integration of emotional diversity into Large Language Models (LLMs) to enhance collective intelligence. Inspired by the human wisdom of crowds phenomenon, where group decisions often outperform individual judgments, we fine-tuned the DarkIdol-Llama-3.1-8B model using Google's GoEmotions dataset and Low-Rank Adaptation (LoRA) to simulate emotionally diverse responses. Evaluating the model on a distance estimation task between Fargo, ND, and Seattle, WA, across 15,064 unique persona configurations, we analyzed how emotional states and social attributes influence decision-making. Our findings demonstrate that emotional integration shapes response patterns while maintaining acceptable prediction accuracy, revealing its potential to enhance artificial collective intelligence. This study provides valuable insights into the interplay of emotional diversity and decision-making in LLMs, suggesting pathways for creating emotionally aware AI systems that balance emotional depth with analytical precision.