Logo image
Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
Preprint   Open access

Enhancing Collective Intelligence in Large Language Models Through Emotional Integration

Likith Kadiyala, Ramteja Sajja, Yusuf Sermet and Ibrahim Demir
ArXiV.org
Cornell University
03/05/2025
DOI: 10.48550/arxiv.2503.04849
url
https://doi.org/10.48550/arxiv.2503.04849View
Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

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.
Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computers and Society Computer Science - Human-Computer Interaction Computer Science - Multiagent Systems

Details

Metrics

13 Record Views
Logo image