From We to Me: Theory Informed Narrative Shift with Abductive Reasoning
This research introduces a neurosymbolic approach using social science theory and abductive reasoning to improve narrative shift in Large Language Models. The method automatically extracts rules to guide LLMs through consistent narrative transformations, achieving a 55.88% improvement over zero-shot baselines for collectivistic to individualistic shifts with GPT-4o while maintaining 40.4% better semantic similarity. The approach demonstrates comparable improvements across multiple LLMs including Llama-4, Grok-4, and Deepseek-R1.
arXiv:2603.03320v1 Announce Type: cross
Abstract: Effective communication often relies on aligning a message with an audience's narrative and worldview. Narrative shift involves transforming text to reflect a different narrative framework while preserving its original core message--a task we demonstrate is significantly challenging for current Large Language Models (LLMs). To address this, we propose a neurosymbolic approach grounded in social science theory and abductive reasoning. Our method automatically extracts rules to abduce the specific story elements needed to guide an LLM through a consistent and targeted narrative transformation. Across multiple LLMs, abduction-guided transformed stories shifted the narrative while maintaining the fidelity with the original story. For example, with GPT-4o we outperform the zero-shot LLM baseline by 55.88% for collectivistic to individualistic narrative shift while maintaining superior semantic similarity with the original stories (40.4% improvement in KL divergence). For individualistic to collectivistic transformation, we achieve comparable improvements. We show similar performance across both directions for Llama-4, and Grok-4 and competitive performance for Deepseek-R1.