Enhancing Collective Intelligence in Large Language Models Through Emotional Integration

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kadiyala, Likith, Sajja, Ramteja, Sermet, Yusuf, Demir, Ibrahim
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915184793092096
author Kadiyala, Likith
Sajja, Ramteja
Sermet, Yusuf
Demir, Ibrahim
author_facet Kadiyala, Likith
Sajja, Ramteja
Sermet, Yusuf
Demir, Ibrahim
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
Kadiyala, Likith
Sajja, Ramteja
Sermet, Yusuf
Demir, Ibrahim
Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
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.
title Enhancing Collective Intelligence in Large Language Models Through Emotional Integration
topic Computation and Language
Artificial Intelligence
Computers and Society
Human-Computer Interaction
Multiagent Systems
url https://arxiv.org/abs/2503.04849