Yue Guo

yue/profile.jpg

614 E. Daniel Street

Room 4131

Champaign, IL 61820

Assistant Professor @ UIUC. Previously: UW/AI2/Google/MSR/JHU.

Assistant Professor, School of Information Sciences
Affiliate, Siebel School of Computing and Data Science
Affiliate, Health Care Engineering Systems Center

Hello! My research sits at the intersection of Health AI, Health Informatics, and Natural Language Processing (NLP). I develop reliable AI systems that make medical knowledge more useful in practice—from improving how health information is communicated to supporting guideline-informed clinical reasoning and decision-making. Recent work examines how language models can internalize clinical guidelines, learn from diagnostic experience, and ground their conclusions in evidence. My training in medicine, epidemiology, and health informatics shapes a translational approach centered on real clinical needs and careful evaluation.

Ongoing projects:

  • 🩺 Guideline-aligned clinical reasoning & decision support
  • 🏥 Accessible & personalized health information
  • 🤖 Trustworthy medical AI & evaluation

I will be recruiting multiple PhD and master students from the iSchool (primarily) and CS programs starting in Fall 2027. If you’re interested in working with me, please read through mentorship section carefully and complete the Google form. Please note that I will not be responding to emails regarding applications. I’m always excited to hear from motivated students! 🎓✨

news

Aug 24, 2026 Two of our papers have been accepted to Findings of EMNLP 2026! Does Accuracy Equal Evidence? studies reasoning faithfulness under KV-cache compression, while LONGQAEVAL develops reliable, resource-conscious evaluation methods for long-form clinical QA. Congratulations to the students and collaborators who made this work possible! 🎉
Jul 20, 2026 A clean sweep at COLM 2026: 3/3 papers accepted! ReLay studies the benefits and risks of personalized health summaries; MedConceal tests how well models uncover and address patients’ hidden concerns; and SEA learns reusable diagnostic rules through jointly optimized reasoning and dual memory. I’ll be in San Francisco for the conference—please say hello! 🌉🎉
May 26, 2026 MedGuideX turns clinical practice guidelines into executable decision logic for LLM training, improving average clinical-reasoning accuracy by 10.28% and producing physician-preferred rationales. 🩺
Apr 30, 2026 Two papers are now published in the Journal of Biomedical Informatics: PlainQAFact introduces a sentence-aware, retrieval-augmented metric for checking factual consistency in biomedical plain-language summaries, while our crowdsourced study finds that LLM summaries can feel as clear as human-written ones yet produce worse actual comprehension. Reliable health communication must measure both factuality and what readers truly understand. 🧭
Mar 29, 2026 Our new counterfactual multi-agent framework tests how changing individual clinical findings shifts competing diagnoses, improving diagnostic accuracy and making agent reasoning more evidence-grounded on complex cases. 🔄

selected publications

  1. Does Accuracy Equal Evidence? Reasoning Faithfulness under KV Cache Compression
    Mengting Ai, Jingrui He, and Yue Guo
    In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026
  2. MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning
    Yuhao Shen, Lang Cao, Simo Du, Yuqing Wang, Juexiao Zhou, Hao Peng, and Yue Guo
    arXiv preprint arXiv:2605.26567, 2026
  3. ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?
    Joey Chan, Yikun Han, Jingyuan Chen, Samuel Fang, Lauren D. Gryboski, Alexandra Lee, Sheel Tanna, Qingqing Zhu, Zhiyong Lu, Lucy Lu Wang, and Yue Guo
    In Conference on Language Modeling (COLM), 2026
  4. MedConceal: A Benchmark for Clinical Hidden-Concern Reasoning Under Partial Observability
    Yikun Han, Joey Chan, Jingyuan Chen, Mengting Ai, Simo Du, and Yue Guo
    In Conference on Language Modeling (COLM), 2026
  5. Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent
    Bingxuan Li, Simo Du, and Yue Guo
    In Conference on Language Modeling (COLM), 2026
  6. LONGQAEVAL: Designing Reliable Evaluations of Long-Form Clinical QA under Resource Constraints
    Federica Bologna, Tiffany Pan, Matthew Wilkens, Yue Guo, and Lucy Lu Wang
    In Findings of the Association for Computational Linguistics: EMNLP 2026, 2026