Retrieval augmentation of large language models for lay language generation
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
The complex linguistic structures and specialized terminology of expert-authored content limit the accessibility of biomedical literature to the general public. Automated methods have the potential to render this literature more interpretable to readers with different educational backgrounds. Prior work has framed such lay language generation as a summarization or simplification task. However, adapting biomedical text for the lay public includes the additional and distinct task of background explanation: adding external content in the form of definitions, motivation, or examples to enhance comprehensibility. This task is especially challenging because the source document may not include the required background knowledge. Furthermore, background explanation capabilities have yet to be formally evaluated, and little is known about how best to enhance them. To address this problem, we introduce Retrieval-Augmented Lay Language (RALL) generation, which intuitively fits the need for external knowledge beyond that in expert-authored source documents. In addition, we introduce CELLS, the largest (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. To evaluate RALL, we augmented state-of-the-art text generation models with information retrieval of either term definitions from the UMLS and Wikipedia, or embeddings of explanations from Wikipedia documents. Of these, embedding-based RALL models improved summary quality and simplicity while maintaining factual correctness, suggesting that Wikipedia is a helpful source for background explanation in this context. We also evaluated the ability of both open-soure Large Language Model (Llama 2) and closed-source Large Language Model (GPT-4) in background explanation, with and without retrieval augmentation. Results indicate that these LLMs can generate simplified content, but that the summary quality is not ideal. Taken together, this work presents the first comprehensive study of background explanation for lay language generation, paving the path for disseminating scientific knowledge to a broader audience. Our code and data are publicly available at: https://github.com/LinguisticAnomalies/pls_retrieval.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“BART uses hidden state representations of text sequences that are encoded bi-directionally (as is the case with BERT Devlin et al. (2018)) to inform a decoder model that predicts the next word in the sequence (as is the case with GPT-series and related models e.g. Brown et al. (2020)).”
MethodLewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jégou, H. (2017) · arXiv · doi:10.48550/arxiv.1702.08734 · Cited by 4,140 · cited 1×
“The DPR model retrieves the top k documents z with the highest prior probability p ϕ ( z | s ) using the Maximum Inner Product Search method Johnson et al. (2019).”
MethodDense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101 · cited 5×
“Therefore, we applied a state-of-the-art abstractive summarization model – BART Lewis et al. (2020) – to our tasks.”
BackgroundMethodInfluentialBERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
Gururangan, S., Marasović, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.740 · Cited by 2,103
Inter-Coder Agreement for Computational Linguistics
Artstein, R., & Poesio, M. (2008) · Computational Linguistics · doi:10.1162/coli.07-034-r2 · Cited by 1,665 · cited 1×
“Cohen’s Kappa among the annotators is 0.74, indicating substantial agreement Artstein and Poesio (2008).”
BackgroundInfluentialMcNamara, D. S., Kintsch, E., Songer, N. B., & Kintsch, W. (1996) · Cognition and Instruction · doi:10.1207/s1532690xci1401_1 · Cited by 1,341 · cited 2×
“Furthermore, experiments in cognitive psychology have shown that providing explanatory content improves the recall of readers with limited domain knowledge Britton and G¨ulg¨oz (1991); McNamara et al. (1996).”
BackgroundA Discourse-Aware Attention Model for Abstractive Summarization of Long Documents
Cohan, A., Dernoncourt, F., Kim, D. S., Bui, T., Kim, S., Chang, W., & Goharian, N. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2097 · Cited by 658
SummEval: Re-evaluating Summarization Evaluation
Fabbri, A. R., Kryściński, W., McCann, B., Xiong, C., Socher, R., & Radev, D. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00373 · Cited by 587
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics
Pagnoni, A., Balachandran, V., & Tsvetkov, Y. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.383 · Cited by 197
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports
Zhang, Y., Merck, D., Tsai, E., Manning, C. D., & Langlotz, C. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.458 · Cited by 171
TLDR: Extreme Summarization of Scientific Documents
Cachola, I., Lo, K., Cohan, A., & Weld, D. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.428 · Cited by 169 · cited 1×
“Text summarization is a widely-studied research topic Cohan et al. (2018); Cachola et al. (2020); Devaraj et al. (2022).”
BackgroundLearning to Summarize Radiology Findings
Zhang, Y., Ding, D. Y., Qian, T., Manning, C. D., & Langlotz, C. P. (2018) · arXiv · doi:10.48550/arxiv.1809.04698 · Cited by 126
Learning to Summarize Radiology Findings
Zhang, Y., Ding, D. Y., Qian, T., Manning, C. D., & Langlotz, C. P. (2018) · Proceedings of the Ninth International Workshop on Health Text Mining and Information Analysis · doi:10.18653/v1/w18-5623 · Cited by 126 · cited 1×
“…mothers, but the presence of a virus’ RNA does not mean that intact virus is present... summarization of radiology reports Cai et al. (2021); Zhang et al. (2018, 2020), biomedical literature Wang et al. (2021); Plaza (2014); Cai et al. (2022) and medical dialogue Chintagunta et al. (2021);…”
BackgroundParagraph-level Simplification of Medical Texts
Devaraj, A., Marshall, I., Wallace, B., & Li, J. J. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.395 · Cited by 79
ChestXRayBERT: A Pretrained Language Model for Chest Radiology Report Summarization
Cai, X., Liu, S., Han, J., Yang, L., Liu, Z., & Liu, T. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3132724 · Cited by 72
Bui, D. D. A., Del Fiol, G., Hurdle, J. F., & Jonnalagadda, S. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.10.014 · Cited by 70 · cited 1×
“It has been a focus of research attention in the biomedical domain Mishra et al. (2014); Bui et al. (2016); Givchi et al. (2022), with applications including Abstract: Clinical reports of Zika Virus (ZIKV) RNA detection in breast milk have been described, but evidence conflicts as to whether this…”
BackgroundEvaluating Factuality in Text Simplification
Devaraj, A., Sheffield, W., Wallace, B., & Li, J. J. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.506 · Cited by 40
LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
Krishna, K., Bransom, E., Kuehl, B., Iyyer, M., Dasigi, P., Cohan, A., & Lo, K. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.121 · Cited by 29
LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization
Krishna, K., Bransom, E., Kuehl, B., Iyyer, M., Dasigi, P., Cohan, A., & Lo, K. (2023) · arXiv · doi:10.48550/arxiv.2301.13298 · Cited by 3 · cited 1×
“…the score of the target significantly lower than that of the source with p-value < 0.05 (paired t-test). lenge of sentence-level alignment in scientific summaries remains an active area of investigation Krishna et al. (2023), emphasizing the ongoing need for the advancement of alignment algorithms.”
BackgroundInfluential
Cited by
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267
“However, recently Chinese datasets such MedDG [29] and MedDialog-CN [28] have been proposed”
A Survey of Large Language Models in Medicine: Progress, Application, and Challenge
Zhou, H., Liu, F., Gu, B., Zou, X., Huang, J., Wu, J., Li, Y., Chen, S. S., Zhou, P., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05112 · Cited by 240
“Such a proactive approach is essential to prevent future confusion among healthcare professionals when interpreting medical records for diagnoses and medical procedures [130].”
BackgroundMethodApplication of large language models in medicine
Liu, F., Zhou, H., Gu, B., Zou, X., Huang, J., Wu, J., Li, Y., Chen, S. S., Hua, Y., Zhou, P., et al. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00279-5 · Cited by 94
Clinical insights: A comprehensive review of language models in medicine
Neveditsin, N., Lingras, P., & Mago, V. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000800 · Cited by 37
“…Radiology Reports [177], Improving Biomedical Text Readabil-ity [178], Anonymization of Medical Documents [179] PLS-Cochrane Reviews [175], CELLS [180], Pfizer Clinical Trial Data [173], MultiCohrane [181] fine-tuned BART [175], RALL [180], fine-tuned Llama [173,179] Conversation Mental Health…”
Large Language Models in Critical Care Medicine: Scoping Review
Shi, T., Ma, J., Yu, Z., Xu, H., Yang, R., Xiong, M., Xiao, M., Li, Y., Zhao, H., & Kong, G. (2025) · JMIR Medical Informatics · doi:10.2196/76326 · Cited by 21
Metadata
- Authors
- Guo, Y., Qiu, W., Leroy, G., Wang, S., & Cohen, T.
- Venue
- Journal of Biomedical Informatics
- Publisher
- Elsevier BV
- Published
- 2024-01
- Volume
- 149
- Pages
- 104580
- ISSN
- 1532-0464 (ISSN-L)
- OpenAlex
- W4390457872
- Cited by
- 48
- References
- 27
- FWCI
- 4.22
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.