Elamur Research⌕
☰
home / authors / Zonghai Yao

Zonghai Yao

Zonghai Yao has 6 papers in our library, in 2023–2026, most of them on Language models & pretraining, Question answering, Evaluation & benchmarks; often with Hong Yu, Feiyun Ouyang, Junda Wang.

6 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 10 · 101 works · 375 citations OpenAlex, 2026-10-14

📄 6 works in our library · 🔗 Cited 49 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #7515

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of Massachusetts AmherstAmherst Center · United States2020–2026 · 77 papersEmploymentcurrent🔬Center for Health Optimization and Implementation ResearchBedford · United States2025–2026 · 14 paperscurrent🎓University of Massachusetts LowellLowell · United States2025–2026 · 5 paperscurrent🎓Amherst CollegeAmherst Center · United States2024–2026 · 3 paperscurrent🏥Edith Nourse Rogers Memorial Veterans HospitalBedford · United States2025–2026 · 2 paperscurrent🏥VA New England Healthcare SystemBedford · United States2025–2026 · 2 paperscurrent🔬Center for the Study of Healthcare Provider BehaviorLos Angeles · United States2026 · 1 papercurrent🎓Fudan UniversityShanghai · China2023–2024 · 3 papers🎓University of MinnesotaMinneapolis · United States2023–2024 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 13The field of science this work belongs to (OpenAlex fields).Computer Science · 5 worksMedicine · 4 worksHealth Informatics · 4 worksArtificial Intelligence · 5 worksArts and Humanities · 3 worksHealth Professions · 2 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 2 worksBiochemistry, Genetics and Molecular Biology · 1 workGeneral Health Professions · 1 workMolecular Biology · 1 workInformation Systems · 1 workHealth Information Management · 1 work

🧭 Topics 5Research subjects and languages the work is about.Question answering · 1 workEvaluation & benchmarks · 1 workInformation retrieval & search · 1 workLanguage models & pretraining · 1 workReasoning · 1 work

 Works by year

2020s

20263 papers20252 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. PaniniQA: Enhancing Patient Education Through Interactive Question Answering (2023 · 24 citations)
    Patients leaving hospital often struggle to grasp or remember their discharge instructions, and their misreadings usually go uncorrected. PaniniQA addresses this with a chatbot that quizzes patients about their own instructions. It follows the Prompt–Evaluate–Expand–Repeat (P.E.E.R.) cycle from Dialogic Reading.
  2. RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025 · 20 citations)
    Answering knowledge-heavy questions, especially in medicine, requires both several reasoning steps and facts that a pretrained model may lack or hold only in outdated form.
  3. Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty (2026 · 9 citations)
    Benchmarks for medical LLMs mostly reward correct answers. They rarely check whether a model should have declined to respond. The authors present MedAbstain, a benchmark and evaluation protocol for uncertainty and abstention in medical multiple-choice QA. They argue this discrete-choice format also models action…
  4. From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025 · 5 citations)
    LLMs are increasingly considered for clinical decision support, yet their skill at medical calculations, such as GFR or cardiovascular risk scores, is poorly measured.
  5. MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026 · 3 citations)
    Most medical LLM benchmarks, such as MedQA, rely on multiple-choice questions. These test what a model knows but not whether it can carry out a patient encounter. MedQA-CS fills this gap with an AI-SCE benchmark modeled on the OSCE format of the USMLE Step 2 CS exam, targeting the "shows how" tier of Miller's Pyramid.
  6. Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language Models (2026)
    Reinforcement learning with verifiable rewards improves LLM reasoning, but a single outcome reward at the end of a long chain makes it hard to tell which tokens mattered.

All works

8 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

  1. PaniniQA: Enhancing Patient Education Through Interactive Question AnsweringTransactions of the Association for Computational Linguistics (TACL)Pengshan Cai, Zonghai Yao, Fei Liu, et al.2023 · 24 citations
  2. RARE: Retrieval-Augmented Reasoning Enhancement for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Hieu Tran, Zonghai Yao, Zhichao Yang, et al.2025 · 20 citations
  3. Improving Formality Style Transfer with Context-Aware Rule Injection ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetZonghai Yao, Hong Yu2021 · 20 citations
  4. Knowing When to Abstain: Medical LLMs Under Clinical UncertaintyConference of the European Chapter of the Association for Computational Linguistics (EACL)Sravanthi Machcha, Sushrita Yerra, Sahil Gupta, et al.2026 · 9 citations
  5. From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical CalculationsConference on Empirical Methods in Natural Language Processing (EMNLP)Benlu Wang, Iris Xia, Yifan Zhang, et al.2025 · 5 citations
  6. MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical SkillsConference of the European Chapter of the Association for Computational Linguistics (EACL)Zonghai Yao, Zihao Zhang, Chaolong Tang, et al.2026 · 3 citations
  7. Exploiting Tree Structure for Credit Assignment in Reinforcement Learning with Large Language ModelsFindings of the Association for Computational LinguisticsHieu Tran, Zonghai Yao, Hong yu2026
  8. LLM-Based Multi-Agent Systems for Clinical Workflows: A Survey of AI Hospitals ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZonghai Yao, Hong yu2026

 Co-authors here

12 of 15 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 49 times (of the 149,439 papers whose bibliographies we read); 8 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zonghai-yao/