Summary of Can Stories Help Llms Reason? Curating Information Space Through Narrative, by Vahid Sadiri Javadi et al.
Can Stories Help LLMs Reason? Curating Information Space Through Narrative
by Vahid Sadiri Javadi, Johanne R. Trippas, Yash Kumar Lal, Lucie Flek
First submitted to arxiv on: 25 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper explores whether incorporating narrative elements can improve Large Language Models’ (LLMs) ability to solve complex problems. A novel approach, Story of Thought (SoT), is proposed, which integrates narrative structures into prompting techniques for problem-solving. SoT constructs narratives around problem statements and creates a framework to identify and organize relevant information. The results show that using various LLMs with SoT consistently outperforms other techniques on physics, chemistry, math, and biology questions in the GPQA and JEEBench datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how we can make computers better at solving tricky problems by using stories to help them understand what’s going on. It proposes a new way of asking questions called Story of Thought (SoT), which uses stories to give computers clues about what they need to do. The results show that when computers are given these story-based hints, they do much better than if they’re just given the facts. This could be really useful for things like teaching science or helping doctors diagnose diseases. |
Keywords
» Artificial intelligence » Prompting
