From We to Me: Theory Informed Narrative Shift with Abductive Reasoning

2026-02-10

arXiv.org

AI Summary

This study addresses the challenge large language models (LLMs) face in preserving both semantic fidelity and narrative coherence during cross-cultural narrative transfer, particularly when shifting between collectivist and individualist frameworks. To overcome this limitation, the authors propose a neuro-symbolic approach that integrates sociological narrative theory with abductive reasoning, enabling interpretable and high-fidelity cross-cultural narrative adaptation. The method automatically extracts narrative rules to guide LLMs in goal-directed transformation. Experimental results demonstrate a 55.88% improvement in narrative transfer performance on GPT-4o, a 40.4% enhancement in semantic fidelity (measured by KL divergence), and consistently superior outcomes across mainstream models including Llama-4, Grok-4, and Deepseek-R1, substantially surpassing the zero-shot transfer capabilities of current LLMs.

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.

Problem

• narrative shift
• Large Language Models
• abductive reasoning
• collectivistic to individualistic
• core message preservation

Innovation

• narrative shift
• abductive reasoning
• neurosymbolic approach
• large language models
• social science theory