Generating Place-Based Compromises Between Two Points of View

TL;DR

This paper develops methods for generating socially acceptable, empathically neutral compromises between opposing viewpoints using LLMs, and trains smaller models for efficient compromise generation.

Contribution

It introduces a novel prompt engineering approach leveraging empathic similarity and trains smaller models with preference alignment, advancing social AI capabilities.

Findings

External empathic similarity feedback improves compromise quality.

The best method outperforms standard Chain of Thought reasoning.

Smaller models trained with preference data are more efficient.

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.