ACL Findings2026
Enrich, Aggregate, and Generate: Three-stage Biomedical Data-to-Text Generation Using Large Language Models in Low-resource Scenarios
Yupian Lin, Guangya Yu, Yuang Bian, Cheng Yuan, Hui Luo, Tong Ruan
Abstract
Biomedical data-to-text generation aims at generating textual natural language descriptions that can fluently and precisely describe the biomedical structured data. However, biomedical data-to-text generation faces the dilemma of a lack of labeled data due to the privacy and scarcity of medical data. Large language models (LLMs) have demonstrated the ability to solve few-shot tasks through in-context learning (ICL). In this paper, we are the first to explore the performance of different LLMs in the biomedical data-to-text generation task. To address the issues of semantic sparsity and misinterpretation of numerical values in biomedical structured data, we propose an EAG (Enrich, Aggregate, and Generate) framework, a simple but efficient LLM-based three-stage biomedical D2T approach in low-resource scenarios. We conduct extensive evaluations of closed-source general LLMs, open-source general LLMs, and open-source medical LLMs. The results show that EAG framework provides good interpretability and superior performance, achieving state-of-the-art performance on the BioLeaflets dataset. The code and data will be released at https://github.com/FXLP/EAG.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on8
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-World Multi-Turn DialogueSonghua Yang, Hanjie Zhao, Senbin Zhu, Guangyu Zhou et al.AAAI 2024 · 227 citations
- Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat DataCanwen Xu, Daya Guo, Nan Duan, Julian J. McAuleyEMNLP 2023 · 112 citations
- BLEURT: Learning Robust Metrics for Text GenerationThibault Sellam, Dipanjan Das, Ankur P. ParikhACL 2020 · 40 citations
- Reinforcement Learning with Imbalanced Dataset for Data-to-Text Medical Report GenerationToru Nishino, Ryota Ozaki, Yohei Momoki, Tomoki Taniguchi et al.EMNLP Findings 2020 · 24 citations
Related papers
- Guiding Large Language Models for Biomedical Entity Linking via Restrictive and Contrastive DecodingZhenxi Lin, Ziheng Zhang, Jian Wu, Yefeng Zheng et al.EMNLP Findings 2025 · 3 citations
- Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text GenerationZdenek Kasner, Ondrej DusekACL 2024 · 10 citations
- Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language ModelsRan Xu, Hejie Cui, Yue Yu, Xuan Kan et al.ACL Findings 2024 · 24 citations
- ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language ModelsJiannan Xiang, Zhengzhong Liu, Yucheng Zhou, Eric P. Xing et al.EMNLP Findings 2022 · 7 citations
- Mixture of Soft Prompts for Controllable Data GenerationDerek Chen, Celine Lee, Yunan Lu, Domenic Rosati et al.EMNLP Findings 2023 · 8 citations
