Background Knowledge Grounding for Readable, Relevant, and Factual Biomedical Lay Summaries
Not on the map. Why?
Abstract (arXiv)
Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or relevance of the generated summaries. We develop a simple method for selecting grounding sources and integrating them with source documents. We then use the BioLaySum summarization dataset to evaluate the effects of different grounding sources on summary quality. We found that grounding source documents improves the relevance and readability of lay summaries but does not improve factuality of lay summaries. This continues to be true in zero-shot summarization settings where we hypothesized that grounding might be even more important for factual lay summaries.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 20 references that are in the map. First posted on arXiv 3 May 2023.
Builds on
16 of 20 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
- 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
- 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
- 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
- 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
- 2019ScispaCy: Fast and Robust Models for Biomedical Natural Language Processingcited by 244
- 2020GO FIGURE: A Meta Evaluation of Factuality in Summarizationcited by 75
- 2022Making Science Simple: Corpora for the Lay Summarisation of Scientific Literaturecited by 54
- 2021Paragraph-level Simplification of Medical Textscited by 52
4 more
- 2022Evaluating Factuality in Text Simplificationcited by 34
- 2022Retrieval augmentation of large language models for lay language generationcited by 21
- 2022Readability Controllable Biomedical Document Summarizationcited by 19
- 2022Factual Error Correction for Abstractive Summaries Using Entity Retrievalcited by 8
Built on by
Not cited yet.