y0news
← Feed
Back to feed
🧠 AI Neutral

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

arXiv – CS AI|Jaikrishna Manojkumar Patil, Divyagna Bavikadi, Kaustuv Mukherji, Ashby Steward-Nolan, Peggy-Jean Allin, Tumininu Awonuga, Joshua Garland, Paulo Shakarian|
🤖AI Summary

Researchers developed a neurosymbolic approach using social science theory and abductive reasoning to help Large Language Models transform text narratives while preserving core messages. The method achieved 55.88% improvement over baseline performance with GPT-4o when shifting between collectivistic and individualistic narrative frameworks.

Key Takeaways
  • Current Large Language Models struggle significantly with narrative shift tasks that preserve original core messages.
  • A new neurosymbolic approach combining social science theory with abductive reasoning was developed to address this limitation.
  • The method achieved 55.88% improvement over zero-shot LLM baselines with GPT-4o for collectivistic to individualistic transformations.
  • Similar performance improvements were demonstrated across multiple LLMs including Llama-4, Grok-4, and Deepseek-R1.
  • The approach maintains superior semantic similarity with original stories while successfully shifting narrative frameworks.
Mentioned in AI
Models
GPT-4OpenAI
LlamaMeta
GrokxAI
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles