From We to Me: Theory Informed Narrative Shift with Abductive Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912941186482176 |
|---|---|
| author | Patil, Jaikrishna Manojkumar Bavikadi, Divyagna Mukherji, Kaustuv Steward-Nolan, Ashby Allin, Peggy-Jean Awonuga, Tumininu Garland, Joshua Shakarian, Paulo |
| author_facet | Patil, Jaikrishna Manojkumar Bavikadi, Divyagna Mukherji, Kaustuv Steward-Nolan, Ashby Allin, Peggy-Jean Awonuga, Tumininu Garland, Joshua Shakarian, Paulo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03320 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From We to Me: Theory Informed Narrative Shift with Abductive Reasoning Patil, Jaikrishna Manojkumar Bavikadi, Divyagna Mukherji, Kaustuv Steward-Nolan, Ashby Allin, Peggy-Jean Awonuga, Tumininu Garland, Joshua Shakarian, Paulo Computation and Language Artificial Intelligence 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. |
| title | From We to Me: Theory Informed Narrative Shift with Abductive Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.03320 |