用逻辑推理提升对话情绪识别稳定性，降低大模型成本
EmoLASP: Emotion Recognition with Language Models and Answer Set Programming
- 结合语言模型与答案集编程进行情绪预测
- 在IEMOCAP数据集上优于纯语言模型，尤其无历史对话时
- 适合追求低成本、高一致性的情绪识别应用
对话中的情绪识别正越来越多地采用语言模型，但这些模型在微调或使用长对话历史提示时存在不稳定和高成本问题。我们提出EmoLASP框架，将语言模型与基于答案集编程（ASP）的声明式推理相结合，以预测对话中的VAD评分（效价-唤醒-主导性）。在广泛使用的基准数据集IEMOCAP上，针对六种开源LLM（3B-120B）和两种PLM（BERT, RoBERTa）的实验表明，即使不提供对话历史给语言模型，EmoLASP仍能提升预测性能。对于仅使用提示的LLM，增益最为显著，且无需任何微调。而对已微调的PLM，当有对话历史时，推理模块作用有限。EmoLASP的LLM流程展示了推理方法在保障情绪预测一致性及降低微调与长历史提示成本方面的潜力。
原文摘要 · Abstract (English)
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.
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。