ACL Findings2026
Safety-Aware Dialogue System for Postoperative Oral Cancer Care with Structured Clarification and a Clinically Curated Dataset
Tzu-Chi Liu, Hui-Ying Yang, Shiow-Ching Shun, Yu-Chi Chen, Lu-Yen Anny Chen, Yong-Sheng Chen
Abstract
Clinical dialogue systems are increasingly vital for patient education and follow-up care; however, effective responses often depend on the clinical context that patients often fail to provide in detail.Responding directly to vague messages can therefore lead to generic or clinically misaligned advice, a challenge that is particularly pronounced in post-op oral cancer (OC) care due to speech impairment and functional limitations.Moreover, postop OC patients often experience psychological distress, making safety-aware language more likely to arise in dialogue.Dialogue systems in this setting must therefore address both clarifying missing clinical context and ensuring psychological safety.We propose a safety-aware dialogue system that applies information-gain guided clarification before RAG-based response generation and screens user utterances for emotional distress and suicidal ideation.Expert evaluations show that the proposed system improves the quality and clinical appropriateness of generated responses relative to strong baselines, while the safety module closely aligns with expert judgments on clinically concerning utterances.Furthermore, we release a clinically curated Chinese post-op OC QA dataset with expertvalidated annotations, which we use throughout our experiments.* Code, data, and prompts are available at https://github. com/jonathan-tcliu/oral-cancer-dialogue-dataset.
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 on5
- Retrieval Augmentation Reduces Hallucination in ConversationKurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela et al.EMNLP Findings 2021 · 579 citations
- Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations
- Generating Clarifying Questions for Information RetrievalHamed Zamani, Susan T. Dumais, Nick Craswell, Paul N. Bennett et al.WWW 2020 · 238 citations
- MedDialog: Large-scale Medical Dialogue DatasetsGuangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang et al.EMNLP 2020 · 163 citations
- End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future DirectionsLibo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao et al.EMNLP 2023 · 12 citations
Related papers
- D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented ChatBinwei Yao, Chao Shi, Likai Zou, Lingfeng Dai et al.EMNLP 2022 · 23 citations
- CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health RecordsDongchen Li, Jitao Liang, Wei Li, Xiaoyu Wang et al.AAAI 2026 · 1 citation
- PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health SupportHao Sun, Zhenru Lin, Chujie Zheng, Siyang Liu et al.ACL Findings 2021 · 69 citations
- MidMed: Towards Mixed-Type Dialogues for Medical ConsultationXiaoming Shi, Zeming Liu, Chuan Wang, Haitao Leng et al.ACL 2023
- Towards semantic reliable clinical QA: Query pipeline optimization for cancer patient question answering systemsMaolin He, Rena Wei Gao, Mike Conway, Brian E. ChapmanACL Findings 2026
