Summary of Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with Llms, by Mihir Parmar et al.
Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs
by Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon, Ryan A. Rossi, Trung Bui
First submitted to arxiv on: 5 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a novel approach to improve the coherence of extractive summaries generated by Large Language Models (LLMs). Currently, these summaries often exhibit incoherence, which is detrimental for summarization tasks. To address this issue, the authors create a human-annotated dataset consisting of coherent summaries for five publicly available datasets and natural language user feedback. This dataset is used to fine-tune LLMs with natural language human feedback, resulting in significant performance improvements (~10% Rouge-L) in terms of producing coherent summaries. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Extractive summarization is a crucial tool in natural language processing that helps us quickly summarize large amounts of text. But right now, the summaries generated by computers often don’t make sense. The researchers behind this paper want to change that. They created a special dataset with human-annotated summaries and feedback from users. This dataset will help train computer models to generate more coherent and readable summaries. Preliminary results are promising, showing improved performance in generating coherent summaries. |
Keywords
» Artificial intelligence » Natural language processing » Rouge » Summarization
