Summary of A Data-centric Approach to Generate Faithful and High Quality Patient Summaries with Large Language Models, by Stefan Hegselmann et al.
A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models
by Stefan Hegselmann, Shannon Zejiang Shen, Florian Gierse, Monica Agrawal, David Sontag, Xiaoyi Jiang
First submitted to arxiv on: 23 Feb 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 The paper investigates the potential of large language models to generate patient summaries based on doctors’ notes, exploring the effect of training data on the faithfulness and quality of generated summaries. It proposes a rigorous labeling protocol for errors in medical texts and releases a publicly available dataset of annotated hallucinations. The study shows that fine-tuning on hallucination-free data can effectively reduce hallucinations while preserving relevant information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores whether large language models can help patients understand their hospitalizations better. Doctors often have limited time to explain things, so machines might be able to fill this gap. Researchers developed a way to check if the summaries are accurate and tested it with two different types of language models. They found that training these models on correct information helps them create more reliable summaries. |
Keywords
* Artificial intelligence * Fine tuning * Hallucination
