基于真人对话的多轮情感智能评测基准，更真实地评估语音语言模型的情感理解能力。
HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
- 用真实人类对话重构多轮情感追踪与因果推理为选择题，减少主观评分偏差。
- 发现多数模型在多轮情感追踪和隐含因果推理上表现不佳。
- 揭示模型在跨模态冲突中严重依赖文本、忽视语音信号的偏见问题。
评估语音语言模型（ALMs）的情感智能（EI）至关重要。然而，现有基准大多依赖合成语音，仅限单轮交互，且高度依赖开放式评分。本文提出HumDial-EIBench，一个全面的ALMs情感智能评测基准。该基准使用来自ICASSP 2026 HumDial Challenge的真实人类对话数据，将情感追踪与因果推理转化为带有对抗性干扰项的多项选择题，降低认知任务中的主观评分偏差；保留共情回复生成任务，并引入声学-语义冲突任务，评估模型在矛盾多模态信号下的鲁棒性。对八种ALMs的评估显示，多数模型在多轮情感追踪和隐含因果推理方面表现不佳；所有模型均表现出文本与声学共情解耦，且在跨模态冲突中存在严重的文本主导偏见。
原文摘要 · Abstract (English)
Evaluating the emotional intelligence (EI) of audio language models (ALMs) is critical. However, existing benchmarks mostly rely on synthesized speech, are limited to single-turn interactions, and depend heavily on open-ended scoring. This paper proposes HumDial-EIBench, a comprehensive benchmark for evaluating ALMs' EI. Using real-recorded human dialogues from the ICASSP 2026 HumDial Challenge, it reformulates emotional tracking and causal reasoning into multiple-choice questions with adversarial distractors, mitigating subjective scoring bias for cognitive tasks. It retains the generation of empathetic responses and introduces an acoustic-semantic conflict task to assess robustness against contradictory multimodal signals. Evaluations of eight ALMs reveal that most models struggle with multi-turn emotional tracking and implicit causal reasoning. Furthermore, all models exhibit decoupled textual and acoustic empathy, alongside a severe text-dominance bias during cross-modal conflicts.
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。