CLAILGOct 25, 2024

Can Stories Help LLMs Reason? Curating Information Space Through Narrative

arXiv:2410.19221v14 citationsh-index: 18Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)
Originality Incremental advance
AI Analysis

This addresses the challenge of enhancing LLM reasoning for complex problem-solving in domains like science and education, though it appears incremental as it builds on existing prompting techniques.

The paper tackled the problem of improving LLMs' ability to solve complex problems by incorporating narrative elements, and the result was that their Story of Thought approach consistently outperformed other techniques on physics, chemistry, math, and biology questions in GPQA and JEEBench datasets.

Narratives are widely recognized as a powerful tool for structuring information and facilitating comprehension of complex ideas in various domains such as science communication. This paper investigates whether incorporating narrative elements can assist Large Language Models (LLMs) in solving complex problems more effectively. We propose a novel approach, Story of Thought (SoT), integrating narrative structures into prompting techniques for problem-solving. This approach involves constructing narratives around problem statements and creating a framework to identify and organize relevant information. Our experiments show that using various LLMs with SoT consistently surpasses using them with other techniques on physics, chemistry, math, and biology questions in both the GPQA and JEEBench datasets. The narrative-based information curation process in SoT enhances problem comprehension by contextualizing critical in-domain information and highlighting causal relationships within the problem space.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes