When LLMs Team Up: The Emergence of Collaborative Affective Computing

2025-06-02

AI Summary

Large language models (LLMs) exhibit cognitive limitations in affective computing, including insufficient cultural sensitivity, contextual misinterpretation, and frequent hallucination. To address these issues, this paper proposes the first systematic LLM-augmented affective computing framework grounded in Dual-Process Theory, establishing a “structured → autonomous” collaborative evolution pathway. The framework integrates modular role assignment, dynamic routing, cross-validation, and reflective generation mechanisms to achieve organic integration of affective and rational reasoning. Experimental results demonstrate significant improvements in cultural adaptability, robustness, and contextual consistency across emotion understanding and generation tasks, while effectively mitigating hallucination. This work advances a novel paradigm for human-like social intelligence by bridging cognitive architecture with affective computation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Affective Computing (AC) is essential in bridging the gap between human emotional experiences and machine understanding. Traditionally, AC tasks in natural language processing (NLP) have been approached through pipeline architectures, which often suffer from structure rigidity that leads to inefficiencies and limited adaptability. The advent of Large Language Models (LLMs) has revolutionized this field by offering a unified approach to affective understanding and generation tasks, enhancing the potential for dynamic, real-time interactions. However, LLMs face cognitive limitations in affective reasoning, such as misinterpreting cultural nuances or contextual emotions, and hallucination problems in decision-making. To address these challenges, recent research advocates for LLM-based collaboration systems that emphasize interactions among specialized models and LLMs, mimicking human-like affective intelligence through the synergy of emotional and rational thinking that aligns with Dual Process Theory in psychology. This survey aims to provide a comprehensive overview of LLM-based collaboration systems in AC, exploring from structured collaborations to autonomous collaborations. Specifically, it includes: (1) A systematic review of existing methods, focusing on collaboration strategies, mechanisms, key functions, and applications; (2) Experimental comparisons of collaboration strategies across representative tasks in affective understanding and generation; (3) An analysis highlighting the potential of these systems to enhance robustness and adaptability in complex affective reasoning; (4) A discussion of key challenges and future research directions to further advance the field. This work is the first to systematically explore collaborative intelligence with LLMs in AC, paving the way for more powerful applications that approach human-like social intelligence.

Problem

• Addressing LLMs' cognitive limitations in affective reasoning
• Enhancing robustness in complex affective understanding and generation
• Exploring collaborative systems for human-like affective intelligence

Innovation

• LLM-based collaboration for affective computing
• Specialized models enhance emotional reasoning
• Dual Process Theory guides affective intelligence