Fei Xia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fei Xia has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Meliha Yetisgen
University of Washington
7 shared publications - Asma Ben Abacha
Health and Life Sciences AI, Microsoft, Redmond, WA, USA.
6 shared publications - Wen-Wai Yim
Health AI, Microsoft, Redmond, WA, 98052, USA
5 shared publications - William D. Lewis
One Microsoft Way
5 shared publications - Zhaoyi Sun
University of Washington
5 shared publications Haotian Zhu
Insight Centre ADAPT Centre University of Galway University of Washington University of Washington Insight Centre University of Galway University of Washington
4 shared publications
Latest Publications
- 25 September 2026
- Published by Springer Nature
- p. 248-258
RADAR: A Multimodal Benchmark for 3D Image-Based Radiology Report Review
- 25 September 2026
- Published by Springer Nature
- p. 248-258
RADAR: A Multimodal Benchmark for 3D Image-Based Radiology Report Review
- Open Access
MORQA: Benchmarking Evaluation Metrics for Medical Open-Ended Question Answering
Evaluating natural language generation (NLG) systems in the medical domain presents unique challenges due to the critical demands for accuracy, relevance, and domain-specific expertise. Traditional automatic evaluation metrics, such as BLEU, ROUGE, and BERTScore, often fall short in distinguishing between high-quality outputs, especially given the open-ended nature of medical question answering (QA) tasks where multiple valid responses may exist. In this work, we introduce MORQA (Medical Open-Response QA), a new multilingual benchmark designed to assess the effectiveness of NLG evaluation metrics across three medical visual and text-based QA datasets in English and Chinese. Unlike prior resources, our datasets feature 2-4+ gold-standard answers authored by medical professionals, along with expert human ratings for three English and Chinese subsets. We benchmark both traditional metrics and large language model (LLM)-based evaluators, such as GPT-4 and Gemini, finding that LLM-based approaches significantly outperform traditional metrics in correlating with expert judgments. We further analyze factors driving this improvement, including LLMs' sensitivity to semantic nuances and robustness to variability among reference answers. Our results provide the first comprehensive, multilingual qualitative study of NLG evaluation in the medical domain, highlighting the need for human-aligned evaluation methods. All datasets and annotations will be publicly released to support future research.
Open AccessMORQA: Benchmarking Evaluation Metrics for Medical Open-Ended Question Answering
Evaluating natural language generation (NLG) systems in the medical domain presents unique challenges due to the critical demands for accuracy, relevance, and domain-specific expertise. Traditional automatic evaluation metrics, such as BLEU, ROUGE, and BERTScore, often fall short in distinguishing between high-quality outputs, especially given the open-ended nature of medical question answering (QA) tasks where multiple valid responses may exist. In this work, we introduce MORQA (Medical Open-Response QA), a new multilingual benchmark designed to assess the effectiveness of NLG evaluation metrics across three medical visual and text-based QA datasets in English and Chinese. Unlike prior resources, our datasets feature 2-4+ gold-standard answers authored by medical professionals, along with expert human ratings for three English and Chinese subsets. We benchmark both traditional metrics and large language model (LLM)-based evaluators, such as GPT-4 and Gemini, finding that LLM-based approaches significantly outperform traditional metrics in correlating with expert judgments. We further analyze factors driving this improvement, including LLMs' sensitivity to semantic nuances and robustness to variability among reference answers. Our results provide the first comprehensive, multilingual qualitative study of NLG evaluation in the medical domain, highlighting the need for human-aligned evaluation methods. All datasets and annotations will be publicly released to support future research.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 21452-21474
A Systematic Survey of Claim Verification: Corpora, Systems, and Case Studies
Zhaxi Zerong, Chenxi Li, Xinyi Liu, Ju-hui Chen, Fei Xia. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 21452-21474
Open AccessA Systematic Survey of Claim Verification: Corpora, Systems, and Case Studies
Zhaxi Zerong, Chenxi Li, Xinyi Liu, Ju-hui Chen, Fei Xia. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 133-141
Remedying Gender Bias in Open English Wordnet
John P. McCrae, Haotian Zhu, Fei Xia, Al Waskow, Kexin Gao. Proceedings of the 13th Global Wordnet Conference. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 133-141
Open AccessRemedying Gender Bias in Open English Wordnet
John P. McCrae, Haotian Zhu, Fei Xia, Al Waskow, Kexin Gao. Proceedings of the 13th Global Wordnet Conference. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 306-331
Tapping into Social Media in Crisis: A Survey
William D. Lewis, Haotian Zhu, Keaton Strawn, Fei Xia. Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 306-331
Open AccessTapping into Social Media in Crisis: A Survey
William D. Lewis, Haotian Zhu, Keaton Strawn, Fei Xia. Proceedings of the Fourth Workshop on NLP for Positive Impact (NLP4PI). 2025.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22539-22550
MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
Asma Ben Abacha, Wen-wai Yim, Yujuan Fu, Zhaoyi Sun, Meliha Yetisgen, Fei Xia, Thomas Lin. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22539-22550
Top Cited PapersOpen AccessMEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
Asma Ben Abacha, Wen-wai Yim, Yujuan Fu, Zhaoyi Sun, Meliha Yetisgen, Fei Xia, Thomas Lin. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 5235-5256
Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions
Yujuan Fu, Ozlem Uzuner, Meliha Yetisgen, Fei Xia. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 5235-5256
Open AccessDoes Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions
Yujuan Fu, Ozlem Uzuner, Meliha Yetisgen, Fei Xia. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 November 2024
- Published by Springer Nature
- p. 69-81
Emotion Cause Extraction in Conversations with Response Graphing
- 1 November 2024
- Published by Springer Nature
- p. 69-81
Emotion Cause Extraction in Conversations with Response Graphing
- 4 October 2024
- Published by Springer Nature
- p. 209-219
DermaVQA: A Multilingual Visual Question Answering Dataset for Dermatology
- 4 October 2024
- Published by Springer Nature
- p. 209-219
DermaVQA: A Multilingual Visual Question Answering Dataset for Dermatology
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6561-6573
Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition
Yuanhe Tian, Fei Xia, Yan Song. Findings of the Association for Computational Linguistics ACL 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6561-6573
Open AccessLearning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition
Yuanhe Tian, Fei Xia, Yan Song. Findings of the Association for Computational Linguistics ACL 2024. 2024.