Summary of Causal Micro-narratives, by Mourad Heddaya et al.
Causal Micro-Narratives
by Mourad Heddaya, Qingcheng Zeng, Chenhao Tan, Rob Voigt, Alexander Zentefis
First submitted to arxiv on: 7 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); 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 novel approach classifies sentence-level explanations of causes and effects in text, requiring only an ontology of causes and effects. The paper evaluates several large language models (LLMs) on a multi-label classification task using a human-annotated dataset from US news articles. A fine-tuned Llama 3.1 8B model achieves F1 scores of 0.87 for narrative detection and 0.71 for classification, despite challenges arising from linguistic ambiguity. The research establishes a framework for extracting causal micro-narratives with applications to social science research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a new way to understand short stories about what causes things to happen in the world. They used a special set of rules to look at sentences and figure out why something is happening or has happened. The scientists tested different computer models on this task, and one model called Llama 3.1 did really well. This new approach can help us learn more about the world by analyzing news articles and other texts. |
Keywords
» Artificial intelligence » Classification » Llama
