arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18339cs.CLcs.AI
收藏

AER-LLM:利用大型语言模型的歧义感知情绪识别

AER-LLM: Ambiguity-aware Emotion Recognition Leveraging Large Language Models

University of Melbourne(墨尔本大学);Massachusetts Institute of Technology(麻省理工学院);xAI Corp(xAI公司);University of New South Wales(新南威尔士大学)

Xin Hong, Yuan Gong, Vidhyasaharan Sethu, Ting Dang

AI总结:

本文提出AER-LLM,通过零样本、少样本提示及历史对话上下文探索LLM识别歧义情绪的能力,并在三个数据集上验证其有效性与上下文增益。

摘要:

大型语言模型(LLM)的最新进展已在许多自然语言处理(NLP)任务中取得巨大成功。除了其认知智能之外,探索它们在情绪智能方面的能力也至关重要,因为这能够实现更自然、更具共情能力的对话式AI。近期研究表明LLM具备识别情绪的能力,但这些研究通常聚焦于单一情绪标签,忽视了人类情绪复杂且具有歧义的本质。本研究首次通过探索LLM在识别歧义情绪方面的潜力来弥补这一空白,利用其强大的泛化能力和上下文学习能力。我们设计了零样本和少样本提示,并将过往对话作为上下文信息纳入歧义情绪识别。在三个数据集上开展的实验表明,LLM在识别歧义情绪方面具有显著潜力,并凸显了纳入上下文信息的实质性益处。此外,研究结果表明,LLM在识别歧义程度较低的情绪方面表现出高度有效性,并在识别歧义程度较高的情绪方面展现出潜力,与人类的感知能力相近。

英文摘要:

Recent advancements in Large Language Models (LLMs) have demonstrated great success in many Natural Language Processing (NLP) tasks. In addition to their cognitive intelligence, exploring their capabilities in emotional intelligence is also crucial, as it enables more natural and empathetic conversational AI. Recent studies have shown LLMs' capability in recognizing emotions, but they often focus on single emotion labels and overlook the complex and ambiguous nature of human emotions. This study is the first to address this gap by exploring the potential of LLMs in recognizing ambiguous emotions, leveraging their strong generalization capabilities and in-context learning. We design zero-shot and few-shot prompting and incorporate past dialogue as context information for ambiguous emotion recognition. Experiments conducted using three datasets indicate significant potential for LLMs in recognizing ambiguous emotions, and highlight the substantial benefits of including context information. Furthermore, our findings indicate that LLMs demonstrate a high degree of effectiveness in recognizing less ambiguous emotions and exhibit potential for identifying more ambiguous emotions, paralleling human perceptual capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑