Year: 2026
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institutions: University of Illinois Chicago, Toyota Research Institute
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7157019768
Cites:
Cited by:
Related to: