DocLens: Multi-aspect Fine-grained Medical Text Evaluation
Open accessAbstract
Yiqing Xie, Sheng Zhang, Hao Cheng, Pengfei Liu, Zelalem Gero, Cliff Wong, Tristan Naumann, Hoifung Poon, Carolyn Rose. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DocLens mentioned the importance of the evaluation method to discriminate 'there is a focal lesion' from 'there is no focal lesion'.
“(2) in coherence with the issue raised in our negation removal session, Doclens29 mentioned the importance of the evaluation method to discriminate “there is a focal lesion” from “there is no focal lesion””
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [29]
Most recent LLM-based evaluation studies adopt sentence-level comparison when prompting GPT to adapt to the list-by-list nature of radiology reports.
“In recent LLM-based evaluation studies29,42–44, we found that (1) similar to the sentence pairing process of FORTE, most of them adopt sentence-level comparison when prompting GPT to adapt to the list-by-list nature of radiology reports”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [29]
Every recent LLM-based evaluation study aims to establish a more clinically precise, explainable, and generalizable metric.
“(3) most importantly, ranging from sentence-level precision and recall to error counting, every study aims to establish a more clinically precise, explainable, and generalizable metric.”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [29]
We utilized the DocLens metric, which employs GPT-4o mini to extract claims from generated reports, verify their presence in ground-truth reports, and compute a precision score for the generated content.
“For the LLM-as-a-judge evaluation, we utilized the DocLens metric, which employs GPT-4o mini to extract claims from generated reports, verify their presence in ground-truth reports, and compute a precision score for the generated content.”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [29]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 35
- Asma Ben Abacha and Dina Demner-Fushman. 2019. On the summarization of consumer health questions. In Proceedings of the 57th Annual Meeting of the As- sociation for Computational Linguistics, ACL 2019, Florence, Italy, July 28th -August 2.
- Griffin Adams, Emily Alsentzer, Mert Ketenci, Jason Zucker, and Noémie Elhadad. 2021. What's in a summary? laying the groundwork for advances in hospital-course summarization. In Proceedings of the 2021 Conference of the North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies, pages 4794-4811, Online. Association for Computational Linguistics. · DOI
- Isabelle Augenstein, Christina Lioma, Dongsheng Wang, Lucas Chaves Lima, Casper Hansen, Chris- tian Hansen, and Jakob Grue Simonsen. 2019. Mul- tiFC: A real-world multi-domain dataset for evidence- based fact checking of claims. In Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
- Asma Ben Abacha, Yassine Mrabet, Yuhao Zhang, Chai- tanya Shivade, Curtis Langlotz, and Dina Demner- Fushman. 2021. Overview of the MEDIQA 2021 shared task on summarization in the medical domain. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 74-85, Online. Associa- tion for Computational Linguistics. · DOI
- Asma Ben Abacha, Wen-wai Yim, Yadan Fan, and Thomas Lin. 2023a. An empirical study of clini- cal note generation from doctor-patient encounters. 2 Details can be found in https://learn. microsoft.com/en-us/azure/compliance/ offerings/offering-hipaa-us. In Proceedings of the 17th Conference of the Euro- pean Chapter of the Association for Computational Linguistics.
- Asma Ben Abacha, Wen-wai Yim, Yadan Fan, and Thomas Lin. 2023b. An empirical study of clini- cal note generation from doctor-patient encounters. In Proceedings of the 17th Conference of the Euro- pean Chapter of the Association for Computational Linguistics.
- Asma Ben Abacha, Wen-wai Yim, George Michalopou- los, and Thomas Lin. 2023c. An investigation of eval- uation methods in automatic medical note generation. In Findings of the Association for Computational Linguistics: ACL 2023.
- Jifan Chen, Aniruddh Sriram, Eunsol Choi, and Greg Durrett. 2022. Generating literal and implied sub- questions to fact-check complex claims. In Proceed- ings of the 2022 Conference on Empirical Methods in Natural Language Processing.
- Jean-Benoit Delbrouck, Pierre Chambon, Christian Bluethgen, Emily Tsai, Omar Almusa, and Curtis Langlotz. 2022. Improving the factual correctness of radiology report generation with semantic rewards. In Findings of the Association for Computational Linguistics: EMNLP 2022.
- Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, and Kelvin Guu. 2023a. RARR: Researching and revis- ing what language models say, using language mod- els. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
- Tianyu Gao, Howard Yen, Jiatong Yu, and Danqi Chen. 2023b. Enabling large language models to generate text with citations. In Proceedings of the 2023 Con- ference on Empirical Methods in Natural Language Processing and the 13th International Joint Con- ference on Natural Language Processing (EMNLP- IJCNLP).
- Bogdan Gliwa, Iwona Mochol, Maciej Biesek, and Alek- sander Wawer. 2019. SAMSum corpus: A human- annotated dialogue dataset for abstractive summariza- tion. In Proceedings of the 2nd Workshop on New Frontiers in Summarization.
- Rodney Hayward, Steven Asch, Mary Hogan, Timothy Hofer, and Eve Kerr. 2005. Sins of omission: getting too little medical care may be the greatest threat to patient safety. Journal of general internal medicine, 20:686-91.
- Or Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, and Yossi Matias. 2022. TRUE: Re-evaluating factual consistency evaluation. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering.
- Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2020. What dis- ease does this patient have? a large-scale open do- main question answering dataset from medical exams. arXiv preprint arXiv:2009.13081. · arXiv
- Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William Cohen, and Xinghua Lu. 2019. Pubmedqa: A dataset for biomedical research question answering. In Pro- ceedings of the 2019 Conference on Empirical Meth- ods in Natural Language Processing and the 9th In- ternational Joint Conference on Natural Language Processing (EMNLP-IJCNLP).
- Alistair Johnson, Tom Pollard, Lu Shen, Li-wei Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Celi, and Roger Mark. 2016. Mimic-iii, a freely accessible critical care database. Scientific Data, 3:160035. · DOI · Paper page
- Chin-Yew Lin. 2004. ROUGE: A package for auto- matic evaluation of summaries. In Text Summariza- tion Branches Out. Association for Computational Linguistics.
- Qiuhao Lu, Dejing Dou, and Thien Nguyen. 2022. Clin- icalT5: A generative language model for clinical text. In Findings of the Association for Computational Linguistics: EMNLP 2022.
- Yasuhide Miura, Yuhao Zhang, Emily Tsai, Curtis Lan- glotz, and Dan Jurafsky. 2021. Improving factual completeness and consistency of image-to-text radi- ology report generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
- Ani Nenkova and Rebecca Passonneau. 2004. Evaluat- ing content selection in summarization: The pyramid method. In Proceedings of the Human Language Technology Conference of the North American Chap- ter of the Association for Computational Linguistics: HLT-NAACL 2004, pages 145-152, Boston, Mas- sachusetts, USA. Association for Computational Lin- guistics.
- Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, and Douwe Kiela. 2020. Adversarial NLI: A new benchmark for natural language under- standing. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
- Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. Medmcqa: A large-scale multi- subject multi-choice dataset for medical domain ques- tion answering. In Proceedings of the Conference on Health, Inference, and Learning.
- Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2002. Bleu: a method for automatic evalu- ation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Compu- tational Linguistics.
- Alexey Romanov and Chaitanya Shivade. 2018. Lessons from natural language inference in the clini- cal domain. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Process- ing. 659
- Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020. BLEURT: Learning robust metrics for text genera- tion. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
- James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers).
- Dave Van Veen, Cara Van Uden, Maayane Attias, Anuj Pareek, Christian Bluethgen, Malgorzata Po- lacin, Wah Chiu, Jean-Benoit Delbrouck, Juan Zam- brano Chaves, Curtis Langlotz, Akshay Chaudhari, and John Pauly. 2023. RadAdapt: Radiology report summarization via lightweight domain adaptation of large language models. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks.
- William Yang Wang. 2017. "liar, liar pants on fire": A new benchmark dataset for fake news detection. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
- Dustin Wright, David Wadden, Kyle Lo, Bailey Kuehl, Arman Cohan, Isabelle Augenstein, and Lucy Lu Wang. 2022. Generating scientific claims for zero- shot scientific fact checking. In Proceedings of the 60th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 2448-2460, Dublin, Ireland. Association for Compu- tational Linguistics. · DOI
- Hongyi Yuan, Zheng Yuan, Ruyi Gan, Jiaxing Zhang, Yutao Xie, and Sheng Yu. 2022. BioBART: Pretrain- ing and evaluation of a biomedical generative lan- guage model. In Proceedings of the 21st Workshop on Biomedical Language Processing, pages 97-109, Dublin, Ireland. Association for Computational Lin- guistics. · DOI
- Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, and Matthew R. Gormley. 2021. Leveraging pretrained models for automatic summa- rization of doctor-patient conversations. In Find- ings of the Association for Computational Linguis- tics: EMNLP 2021, pages 3693-3712, Punta Cana, Dominican Republic. Association for Computational Linguistics. · DOI
- Yuhao Zhang, Derek Merck, Emily Tsai, Christopher D. Manning, and Curtis Langlotz. 2020b. Optimizing the factual correctness of a summary: A study of summarizing radiology reports. In Proceedings of the 58th Annual Meeting of the Association for Com- putational Linguistics.
- Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, and Jiawei Han. 2022. Towards a unified multi- dimensional evaluator for text generation. In Pro- ceedings of the 2022 Conference on Empirical Meth- ods in Natural Language Processing.
- Yongxin Zhou, Fabien Ringeval, and François Portet. 2023. A survey of evaluation methods of generated medical textual reports. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 447-459, Toronto, Canada. Association for Computational Linguistics. Input: Dialogue between the doctor and the patient · DOI
Cited by
Sorted by citations
Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review
Bedi, S., Liu, Y., Orr-Ewing, L., Dash, D., Koyejo, S., Callahan, A., Fries, J. A., Wornow, M., Swaminathan, A., Lehmann, L. S., et al. (2025) · JAMA · doi:10.1001/jama.2024.21700 · Cited by 662 · see citing works
Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation
Li, C.-Y., Chang, K.-J., Yang, C.-F., Wu, H.-Y., Chen, W., Bansal, H., Chen, L., Yang, Y.-P., Chen, Y.-C., Chen, S.-P., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-57426-0 · Cited by 75 · see citing works
“Then, we examined the caption efficacy by (1) adapting traditional evaluation metrics (2) proposing a clinical-oriented FORTE metric, (3) applying an external validation CQ500, and (4) conducting the linguistic-embedded Turing test.”
The evaluation illusion of large language models in medicine
Agrawal, M., Chen, I. Y., Gulamali, F., & Joshi, S. D. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01963-x · Cited by 59 · see citing works
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
Li, H., Dong, Q., Chen, J., Su, H., Zhou, Y., Ai, Q., Ye, Z., & Liu, Y. (2024) · arXiv · doi:10.48550/arxiv.2412.05579 · Cited by 40 · see citing works
Biomedical Natural Language Processing in the Era of Large Language Models
Usuyama, N., Wong, C., Zhang, S., Naumann, T., & Poon, H. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095406 · Cited by 21 · see citing works
Self-citationKelsall, J., Tan, X., Bergin, A., Chen, J., Waheed, M., Sorell, T., Procter, R., Liakata, M., Chim, J., & Chi, S. (2025) · AI & Society · doi:10.1007/s00146-025-02741-9 · Cited by 7 · see citing works
“These approaches aim to capture intrinsic properties of the texts in their own right (e.g. coherence, conciseness) (Yuan et al. 2021; Xie et al. 2024) or in relation to source materials and knowledge bases (e.g. factuality) (Scialom et al. 2021; Min et al. 2023), and better accommodate variations…”
A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework
Li, C., Akhtar, Z., Kwak, M., Ji, Y., Zhang, H., Obi, T., Ren, Y., Wu, X., Sivarajkumar, S., Lehmann, H. P., et al. (2026) · arXiv · doi:10.48550/arxiv.2604.25933 · Cited by 1 · see citing works
Liu, C., Luo, L., Lv, T., Zhuang, H., Yu, L., Wang, J., & Lin, H. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356827
“…of language inputs D input = { x i , y i } , a dataset D Fi , and a pre-set threshold τ # Extract the focus 4: # extract key phrase by TextRank 6: #Extract noun phrases K N from the original text 8: for each k n ∈ K N do 10: return to step3 # Creating an augmented dataset 19: end for base models.”
Dynamic alignment of large language models for evidence-grounded heart failure decision support
Liu, L., Dong, C., Ba, Y., Yan, H., Tang, X., Sun, Y., Chen, H., Shi, B., Yu, Q., & Zhang, S. (2026) · Digital Health · doi:10.1177/20552076261487568 · Cited by 1 · see citing works
Self-citationGISum: Gibbs Inspired Summarization Architecture for Traceable Medical Summarization
Eeswar, Y., Sreeshanth, K., & Suman, C. (2026) · International Conference on Emerging Techniques in Computational Intelligence (ICETCI) · doi:10.1109/icetci71772.2026.11710619
“Citation Recall (CIR) [15], [16] measures the proportion of critical evidence successfully captured: Maximizing CIR mathematically ensures that critical factual evidence is prioritized over narrative fluency.”
- Authors
- Xie, Y., Zhang, S., Cheng, H., Liu, P., Gero, Z., Wong, C., Naumann, T., Poon, H., & Rose, C.
- Affiliations
- Carnegie Mellon University (US)
- Microsoft (United States) (US)
- Shanghai Jiao Tong University (CN)
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 649-679
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402667136
- Cited by
- 8
- References
- 0
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 1
- FWCI
- 14.44
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- National Science Foundation (2222762)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Text Readability and Simplification
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- fine-grained evaluation, clinical text generation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
