发表机构
School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EmoLASP结合语言模型与回答集编程，在IEMOCAP数据集上提升了情感预测性能，尤其对无微调的仅提示式大语言模型效果显著，可降低相关成本并保证预测一致性。
AI 中文摘要
对话情感识别越来越多地使用语言模型来解决，但这些模型可能不稳定，且微调或使用长对话历史进行提示的成本较高。我们提出EmoLASP，一个结合语言模型与回答集编程（Answer Set Programming，ASP）声明式推理的框架，用于预测对话中的VAD分数（效价-唤醒度-支配度）。在广泛使用的基准数据集IEMOCAP上，针对6个开源大语言模型（LLMs，参数规模3B至120B）和2个预训练语言模型（PLMs，BERT、RoBERTa）的实验显示，EmoLASP与单独使用语言模型相比，预测性能有所提升，即使LLMs/PLMs的提示或输入向量中未提供对话历史，该提升依然存在。仅使用提示的LLMs的提升最大，EmoLASP使用这些模型时无需任何微调。不过，对于已微调的PLMs，当提供对话历史后，推理器带来的增益很小。EmoLASP的LLM管道展示了使用推理方法确保情感预测一致性、降低微调成本以及使用长对话历史进行提示的成本的潜在优势。
英文摘要
Emotion recognition in conversations is increasingly tackled with language models, but these models can be unstable and expensive to fine-tune or to prompt with long dialogue histories. We propose EmoLASP, a framework that combines a language model with declarative reasoning via Answer Set Programming (ASP) to predict VAD scores (Valence-Arousal-Dominance) in conversations. Experiments on a widely used benchmark dataset (IEMOCAP) across six open-source LLMs (3B-120B) and two PLMs (BERT, RoBERTa) show that EmoLASP improves prediction performance compared to using the language model alone, even when the LLMs/PLMs are given no dialogue history in their prompts or input vectors. The gains are largest for prompt-only LLMs, which EmoLASP uses without any fine-tuning. However, for fine-tuned PLMs, the reasoner adds little once dialogue history is available. EmoLASP's LLM pipeline demonstrates the potential advantages of using a reasoning approach to ensure emotion prediction consistency and to reduce both the cost of fine-tuning and the cost of prompting with long dialogue histories.
Comments13 pages. Accepted to EMNLP 2026 Main Conference
