Enhancing Collective Intelligence in Large Language Models Through Emotional Integration

2025-03-05

AI Summary

Current large language models (LLMs) lack social-emotional modeling capabilities, hindering their ability to simulate collective decision-making processes characteristic of human group intelligence. Method: To address this, we propose injecting multidimensional emotional states into the response generation process of LLMs. Specifically, we fine-tune DarkIdol-Llama-3.1-8B on the GoEmotions dataset using LoRA and design 15,064 persona-based prompts to induce emotion-driven response diversification. Contribution/Results: Empirical evaluation on a distance estimation task demonstrates that affective states significantly shift response distributions (MAE < 82 km) without compromising predictive accuracy. This work constitutes the first systematic integration of affective diversity—the hallmark of human collective intelligence—into LLMs, enabling emergent swarm-like intelligence. It establishes a novel paradigm for developing socially aware artificial collective intelligence grounded in computational affective science.

Technology Category

• Humans and AI: Emotional Intelligence
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Integrating emotional diversity into Large Language Models (LLMs).
• Enhancing collective intelligence through emotional simulation.
• Balancing emotional depth with analytical precision in AI systems.

Innovation

• Emotional diversity integration in LLMs
• Fine-tuning with GoEmotions and LoRA
• Analyzing emotional impact on decision-making