测试大模型在情绪对话中自洽性，发现其易受错误前提影响。
Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts
- 用模型自身生成内容作为新问题，检验回答一致性。
- 中等情绪下模型表现显著下降，错误信念影响更严重。
- 注意力机制转向生成而非判断，适合高风险情绪场景研究者关注。
本文分析大型语言模型（LLMs）在情绪驱动对话情境中生成回应的自洽性。具体方法是将模型生成的文本作为新查询输入同一模型，并评估其后续响应。实验涵盖三种包含逐步增强强度错误假设（虚假预设）的虚假主张问题，覆盖极端与中等情绪维度。研究涉及两款商用模型Claude-3.5-haiku、GPT4o-mini及一款中等规模模型Mistral-7B。结果表明，模型整体表现低于平均水平，对嵌入查询中的错误信念高度敏感，尤其在中等情绪语境下更为明显。进一步基于注意力得分的分析揭示，模型优先级从评估转向生成。该发现对大模型在高风险情绪敏感场景中的部署具有重要警示意义。
原文摘要 · Abstract (English)
In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed as a query to the same model, and its responses are subsequently assessed. This is performed with three queries across two dimensions of extreme and moderate emotions. The three queries are, in particular, false claim queries that contain inherently wrong assumptions (false presuppositions) in increasing order of intensity. Two commercial models, Claude-3.5-haiku, GPT4o-mini, and a medium-sized model, Mistral-7B, are considered in the study. Our findings indicate that LLMs exhibit below-average performance and remain vulnerable to false beliefs embedded within queries. This susceptibility is especially pronounced for moderate emotional content. Furthermore, an extended attention-score-based analysis highlights a shift in models' priority from evaluative to generative. The results raise important considerations for LLMs' deployment in high-stakes, emotionally sensitive contexts.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。