Elamur Research⌕
☰
home / papers / 2026 / Conversational Assistants to Support Patients with Heart Failure: Comparing a Neurosymbolic Architecture with GPT

Conversational Assistants to Support Patients with Heart Failure: Comparing a Neurosymbolic Architecture with GPT

Summary

LLM-based chatbots are spreading into healthcare. However, their opacity and unreliable instruction-following make careful evaluation with real stakeholders essential. This paper compares two conversational assistants that tell heart-failure patients how much sodium a food contains. The study targets African American patients, who face higher heart-failure risk and greater salt sensitivity.

  • HFFood-NS is a task-oriented system. A T5-small dialogue state tracker, trained on 87k template-generated dialogues built from an annotated U.S. Food Data Central (USFDC) dataset, is coupled with symbolic rules. These rules look up sodium values and rescale them to the requested portion.
  • HFFood-GPT is a zero-shot GPT-4 assistant with retrieval over the same USFDC data. It is constrained to ask a single clarifying question per turn and to keep answers short.

Hospitalized patients used both systems in randomized order and filled in surveys before and after. This allowed analysis of both task performance and user experience. The authors conclude that each architecture offers strengths the other lacks. They argue for hybrid designs that pair LLM flexibility with symbolic control, a promising direction for high-stakes medical dialogue.

Key points

  • The within-subject study ran for about 6 months. Of 23 recruited hospitalized AA patients, 20 completed it (13 male, 7 female; mean age 58.75). Each participant asked each system about 5 foods.
  • A purely end-to-end T5-small model reached only 2% success at computing salt values, because sodium varies with preparation and portion. Adding neuro-symbolic rules solved database retrieval and arithmetic, for example scaling a 100 g USFDC entry to 2 pounds of collard greens.
  • HFFood-NS uses five slots: food, cook, type, foodweight, metric. It reports salt in mg, as a percentage of a 2000 mg daily limit, and in informal units (pinches/dashes), followed by range-based motivational messages.
  • The HFFood-GPT prompt ("Sodium Scout") enforces several limits:
    • replies under 40 words;
    • no health advice and no web search;
    • foods above 20% of the daily limit labeled not recommended, and those below 5% labeled favorable.
  • The surveys covered:
    • eHealth and health literacy;
    • ease of understanding answers and questions (1–5 scales);
    • preferred salt units;
    • system preference;
    • likelihood of future use.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/4tng9rshvsna

@inproceedings{tayal2026conversational,
  title = {{Conversational Assistants to Support Patients with Heart Failure: Comparing a Neurosymbolic Architecture with GPT}},
  author = {Tayal, Anuja and Salunke, Devika and Eugenio, Barbara Di and Allen-Meares, Paula G. and Abril, Eulalia P. and Garcia-Bedoya, Olga and Dickens, Carolyn A. and Boyd, Andrew D.},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4tng9rshvsna},
  url = {https://doi.org/10.63317/4tng9rshvsna}
}

References

49 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abubakar Abid, Ali Abdalla, Ali Rahman, and James Zou. 2019. Gradio: Hassle-free sharing and testing of ml models in the wild. arXiv preprint arXiv:1906.02569. — [arXiv:1906.02569](https://arxiv.org/abs/1906.02569) find
  2. Alabama Department of Public Health. n.d. Brief: Health literacy screening tool. Accessed: 2025-02-14. find
  3. Mohammad Rafayet Ali, Seyedeh Zahra Razavi, Raina Langevin, Abdullah Al Mamun, Benjamin Kane, Reza Rawassizadeh, Lenhart K Schubert, and Ehsan Hoque. 2020. A virtual conversational agent for teens with autism spectrum disorder: Experimental results and design lessons. In Proceedings of the 20th ACM… find
  4. Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, and Tom Mitchell. 2021. Conversational neuro-symbolic commonsense reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 4902–4911. find
  5. Satanjeev Banerjee and Alon Lavie. 2005. ME-TEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. As… find
  6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… find
  7. Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. 2018. Multi-WOZ - a large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language… find
  8. Pengshan Cai, Zonghai Yao, Fei Liu, Dakuo Wang, Meghan Reilly, Huixue Zhou, Lingxi Li, Yi Cao, Alok Kapoor, Adarsha Bajracharya, Dan Berlowitz, and Hong Yu. 2023. PaniniQA: Enhancing Patient Education Through Interactive Question Answering. Transactions of the Association for Computational Linguisti… find
  9. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… find our card
  10. Jan Deriu, Alvaro Rodrigo, Arantxa Otegi, Guillermo Echegoyen, Sophie Rosset, Eneko Agirre, and Mark Cieliebak. 2021. Survey on evaluation methods for dialogue systems. Artificial Intelligence Review, 54:755–810. find
  11. Victoria Vaughan Dickson and Barbara Riegel. 2009. Are we teaching what patients need to know? building skills in heart failure self-care. Heart & Lung, 38(3):253–261. find
  12. Itika Gupta, Barbara Di Eugenio, Devika Salunke, Andrew Boyd, Paula Allen-Meares, Carolyn Dickens, and Olga Garcia. 2020. Heart failure education of African American and Hispanic/Latino patients: Data collection and analysis. In Proceedings of the First Workshop on Natural Language Processing for Me… find
  13. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. Decoupling strategy and generation in negotiation dialogues. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2333– 2343. find our card
  14. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12). find our card
  15. Tom Knoll, Francesco Moramarco, Alex Papadopoulos Korfiatis, Rachel Young, Claudia Ruffini, Mark Perera, Christian Perstl, Ehud Reiter, Anya Belz, and Aleksandar Savkov. 2022. User-driven research of medical note generation software. In Proceedings of the 2022 Conference of the North American Chapte… find
  16. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics. find
  17. Andrew Cameron Morris, Viktoria Maier, and Phil D Green. 2004. From wer and ril to mer and wil: improved evaluation measures for connected speech recognition. In Interspeech, pages 2765– 2768. find
  18. Sanjoy Moulik. 2019. DIL-A Conversational Agent for Heart Failure Patients. Ph.D. thesis, The Claremont Graduate University. find
  19. A Nayak, AJ Hicks, and AA Morris. 2020. Understanding the complexity of heart failure risk and treatment in black patients. Circulation: Heart Failure, 13(8):e007264. find
  20. Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin. 2021. Investigating the limitations of transformers with simple arithmetic tasks. arXiv preprint arXiv:2102.13019. find
  21. Cameron D. Norman and Harvey A. Skinner. 2006. eHEALS: The eHealth Literacy Scale. Journal of Medical Internet Research, 8:e27. find
  22. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, Irwan Bello, Ja… find our card
  23. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, USA. Association for Computational Linguistics. find our card
  24. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, UIST ’23, New York, NY, USA. Ass… find
  25. Jing Qian, Hong Wang, Zekun Li, Shiyang Li, and Xifeng Yan. 2023. Limitations of language models in arithmetic and symbolic induction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9285–9298, Toronto, Canada. Association for… find
  26. Shuofei Qiao, Yixin Ou, Ningyu Zhang, Xiang Chen, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, and Huajun Chen. 2023. Reasoning with language model prompting: A survey. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5368–… find our card
  27. Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In Proceedings of the 40th International Conference on Machine Learning, ICML’23. JMLR.org. find our card
  28. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67. find
  29. Oscar J. Romero, Antian Wang, John Zimmerman, Aaron Steinfeld, and Anthony Tomasic. 2021. A task-oriented dialogue architecture via transformer neural language models and symbolic injection. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 438–… find
  30. Chandan Singh, Jeevana Priya Inala, Michel Galley, Rich Caruana, and Jianfeng Gao. 2024. Rethinking interpretability in the era of large language models. arXiv preprint arXiv:2402.01761. find
  31. Karen Sparck Jones and Julia R Galliers. 1995. Evaluating natural language processing systems: An analysis and review. Springer Science & Business Media. find
  32. Anuja Tayal, Barbara Di Eugenio, Devika Salunke, Andrew D. Boyd, Carolyn A. Dickens, Eulalia P. Abril, Olga Garcia-Bedoya, and Paula G. Allen-Meares. 2024. A neuro-symbolic approach to monitoring salt content in food. In Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4H… find
  33. Anuja Tayal, Devika Salunke, Barbara Di Eugenio, Paula Allen-Meares, Eulalia Puig Abril, Olga Garcia-Bedoya, Carolyn Dickens, and Andrew Boyd. 2025. Towards conversational assistants for health applications: using ChatGPT to generate conversations about heart failure. In Proceedings of the 26th Annu… find
  34. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. find
  35. USFDC. 2022. Us food data central. find
  36. Mina Valizadeh and Natalie Parde. 2022. The AI doctor is in: A survey of task-oriented dialogue systems for healthcare applications. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6638–6660, Dublin, Ireland. Association for C… find
  37. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30. find
  38. Marilyn A Walker, Diane J Litman, Candace A Kamm, and Alicia Abella. 1998. Evaluating spoken dialogue agents with paradise: Two case studies. Computer Speech & Language, 12(4):317–347. find
  39. Jinping Wang, Hyun Yang, Ruosi Shao, Saeed Abdullah, and S. Shyam Sundar. 2020. Alexa as coach: Leveraging smart speakers to build social agents that reduce public speaking anxiety. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, CHI ’20, page 1–13, New York, NY, USA… find
  40. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837. find our card
  41. Joseph Weizenbaum. 1966. Eliza—a computer program for the study of natural language communication between man and machine. Commun. ACM, 9(1):36–45. find
  42. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, and Karthik R Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In Thirty-seventh Conference on Neural Information Processing Systems. find
  43. Yi-Ting Yeh, Maxine Eskenazi, and Shikib Mehri. 2021. A comprehensive assessment of dialog evaluation metrics. In The First Workshop on Evaluations and Assessments of Neural Conversation Systems, pages 15–33, Online. Association for Computational Linguistics. find
  44. Taedong Yun, Eric Yang, Mustafa Safdari, Jong Ha Lee, Vaishnavi Vinod Kumar, S. Sara Mahdavi, Jonathan Amar, Derek Peyton, Reut Aharony, Andreas Michaelides, Logan Schneider, Isaac Galatzer-Levy, Yugang Jia, John Canny, Arthur Gretton, and Maja Matarić. 2025. Sleepless nights, sugary days: Creating… find
  45. Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, and Jing Xiao. 2020. Aligntts: Efficient feed-forward text-to-speech system without explicit alignment. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6714–6718. find
  46. Chao Zhang, Xin Shi, Xueqiao Zhang, Yifan Zhu, Yi Yang, and Yawei Luo. 2025. DecoupledESC: Enhancing emotional support generation via strategy-response decoupled preference optimization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 22189–22215, Suzhou, China. Assoc… find
  47. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36:46595– 46623. find
  48. Hongjian Zhou, Fenglin Liu, Boyang Gu, Xinyu Zou, Jinfa Huang, Jinge Wu, Yiru Li, Sam S. Chen, Peilin Zhou, Junling Liu, Yining Hua, Chengfeng Mao, Chenyu You, Xian Wu, Yefeng Zheng, Lei Clifton, Zheng Li, Jiebo Luo, and David A. Clifton. 2024. A survey of large language models in medicine: Progress… find
  49. Zhenpeng Zhou, Ahmad Beirami, Paul Crook, Pararth Shah, Rajen Subba, and Alborz Geramifard. 2020. Resource constrained dialog policy learning via differentiable inductive logic programming. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6775–6787, Barcelona,… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tayal-2026-conversational-assistants-support-patients-heart/