Large Language Models (LLMs) excel academically but struggle with social intelligence tasks, such as creating good compromises. In this paper, we present methods for generating empathically neutral compromises between two opposing viewpoints. We first compared four different prompt engineering methods using Claude 3 Opus and a dataset of 2,400 contrasting views on shared places. A subset of the gen erated compromises was evaluated for acceptability in a 50-participant study. We found that the best method for generating compromises between two views used external empathic similarity between a compromise and each viewpoint as iterative feedback, outperforming stan dard Chain of Thought (CoT) reasoning. The results indicate that the use of empathic neutrality improves the acceptability of compromises. The dataset of generated compromises was then used to train two smaller foundation models via margin-based alignment of human preferences, improving efficiency and removing the need for empathy estimation during inference.

翻译：大型语言模型（LLMs）在学术任务上表现出色，但在社交智能任务（如生成优质妥协方案）上存在不足。本文提出在两种对立观点之间生成共情中性妥协方案的方法。首先，我们使用Claude 3 Opus模型和包含2400组关于共享场所的对比观点数据集，比较了四种不同的提示工程方法。通过一项50名参与者的研究评估了部分生成妥协方案的可接受性。研究发现，生成两种观点间妥协方案的最佳方法，是利用妥协方案与各观点之间的外部共情相似度作为迭代反馈，其表现优于标准思维链（CoT）推理。结果表明，采用共情中性可提升妥协方案的可接受性。随后，通过基于人类偏好的边界对齐方法，利用生成的妥协方案数据集训练两个较小的基础模型，既提升了效率，又消除了推理过程中共情估计的必要性。