---
title: "From Answers to Arguments — paper by Zhan et al. (2026)"
description: "Clinical LLMs often reach the right diagnosis through faulty reasoning, and standard benchmarks and training methods (SFT… 55 references."
authors: ["Chen Zhan", "Xiaoyu Tan", "Gengchen Ma", "Yu-Jie Xiong", "Xiaoyan Jiang", "Xihe Qiu"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.637/"
doi: "10.18653/v1/2026.acl-long.637"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhan-2026-answers-arguments-trustworthy-clinical-diagnostic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhan-2026-answers-arguments-trustworthy-clinical-diagnostic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/) / From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

# From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

**Authors:** Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong, Xiaoyan Jiang and Xihe Qiu · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.637/) · [PDF](https://aclanthology.org/2026.acl-long.637.pdf) · [DOI 10.18653/v1/2026.acl-long.637](https://doi.org/10.18653/v1/2026.acl-long.637) · [OpenAlex](https://openalex.org/W7166835163)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Clinical LLMs often reach the right diagnosis through faulty reasoning, and standard benchmarks and training methods (SFT, RL) mostly reward the final answer. The authors make the reasoning itself the target. They recast diagnosis as a Toulmin-style argument with six parts: case evidence, a ranked differential with rebuttals, pathophysiological warrants, backing principles, uncertainty qualifiers, and the final diagnosis. They also introduce T-Eval, a scorer that rates how well each part is built. Their training method, Curriculum Goal-Conditioned Learning (CGCL), is offline imitation learning in three stages that loosely follow a physician's training path:

1. Gather facts and draft a differential.
2. Defend the main hypothesis and refute the alternatives.
3. Write a qualified conclusion.

For each stage, a frozen strategy model proposes candidate outputs. T-Eval picks the best ones, they are merged into training trajectories, and the target model is fine-tuned on them. Each stage starts from the previous stage's weights. On MedCaseReasoning, CGCL reaches accuracy close to RL methods such as GRPO and improves reasoning quality, especially for smaller backbones. It does this with a simpler and more stable pipeline than RL.

## Key points
- **Argument structure:** diagnoses are written as A = {D, R, W, B, Q, Y}, built up across the curriculum. Stage 1 produces {D, R}, Stage 2 adds {W, B}, and Stage 3 adds {Q, Y}. Code is available at github.com/Leonard-zc/CGCL.
- **Ablation:** T-Eval TrustScore rises from 65.32 (Stage 1 only) to 69.84 (Stages 1+2) to 72.84 (full CGCL). Accuracy rises from 28.45 to 30.67 to 32.63.
- **Clinician study (50 test cases):**
  - CGCL scored a clinician TrustScore of 71.0, against 61.0 for GRPO.
  - Diagnostic accuracy was 53.3% for CGCL and 51.7% for GRPO.
  - Raters agreed moderately (ICC = 0.63), and T-Eval correlated with clinician judgments at Spearman ρ = 0.74.
- **Comparison with medical LLMs:** on 3B and 8B backbones, CGCL matches or beats medical and reasoning-specialized LLMs on TrustScore. In zero-shot out-of-distribution tests on MedFound, the same ranking holds.
- **Limitations:**
  - Results depend on the quality of the trajectory-generating model.
  - The system has not been tested in real clinical workflows.
  - Generating and fusing trajectories is computationally costly.

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

## Institutions

- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 163 works · 21,032 citations
- [Shanghai University of Engineering Science](https://md.research.elamur.ai/free/en/universities/shanghai-university-of-engineering-science/) — University, Shanghai, China · 2 works

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 214 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong, Xiaoyan Jiang and Xihe Qiu. 2026. From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhan2026answers,
  title = {{From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning}},
  author = {Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong, Xiaoyan Jiang and Xihe Qiu},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.637},
  url = {https://doi.org/10.18653/v1/2026.acl-long.637}
}
```

- [← previous From Annotated Clinical Narratives to Ontology: Structuring Brazilian Portuguese Clinical Data](https://md.research.elamur.ai/free/en/papers/oliveira-2026-annotated-clinical-narratives-ontology-structuring/)
- [next → From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons](https://md.research.elamur.ai/free/en/papers/ma-2026-ar-diffusion-efficiently-adapting-large/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/33/)

## References

55 references, 26 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob Mc-Grew, Josh Tobin, OpenAI Pieter Abbeel, and Wojciech Zaremba. 2017. [Hindsight experience replay](https://md.research.elamur.ai/free/en/papers/andrychowicz-2017-hindsight-experience-replay/). Advances in neural information processing systems, 30.
2. Elham Asgari, Nina Montaña-Brown, Magda Dubois, Saleh Khalil, Jasmine Balloch, Joshua Au Yeung, and Dominic Pimenta. 2025. A framework to assess clinical safety and hallucination rates of llms for medical text summarisation. npj Digital Medicine, 8(1):274. [find](https://scholar.google.com/scholar?q=Elham+Asgari%2C+Nina+Monta%C3%B1a%2DBrown%2C+Magda+Dubois%2C+Saleh+Khalil%2C+Jasmine+Balloch%2C+Joshua+Au+Yeung%2C+and+Dominic+Pimenta%2E+2025%2E+A+framework+to+assess+clinical+safety+and+hallucination+rates+of+llms+for+med)
3. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th annual international conference on machine learning, pages 41–48.
4. Luciano Caroprese, Eugenio Vocaturo, and Ester Zumpano. 2022. Argumentation approaches for ex-planaible ai in medical informatics. Intelligent Systems with Applications, 16:200109. [find](https://scholar.google.com/scholar?q=Luciano+Caroprese%2C+Eugenio+Vocaturo%2C+and+Ester+Zumpano%2E+2022%2E+Argumentation+approaches+for+ex%2Dplanaible+ai+in+medical+informatics%2E+Intelligent+Systems+with+Applications%2C+16%3A200109%2E)
5. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. 2024. [Huatuogpt-o1, towards medical complex reasoning with llms](https://md.research.elamur.ai/free/en/papers/chen-2024-huatuogpt-o1-towards-medical-complex/). arXiv preprint arXiv:2412.18925.
6. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2019. [Plug and play language models: A simple approach to controlled text generation](https://md.research.elamur.ai/free/en/papers/dathathri-2019-plug-play-language-models-simple/). arXiv preprint arXiv:1912.02164.
7. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
8. Sibel Erduran, Shirley Simon, and Jonathan Osborne. 2004. Tapping into argumentation: Developments in the application of toulmin’s argument pattern for studying science discourse. Science education, 88(6):915–933. [find](https://scholar.google.com/scholar?q=Sibel+Erduran%2C+Shirley+Simon%2C+and+Jonathan+Osborne%2E+2004%2E+Tapping+into+argumentation%3A+Developments+in+the+application+of+toulmin%E2%80%99s+argument+pattern+for+studying+science+discourse%2E+Science+education%2C+8)
9. Hamzah Noori Fejer, Ali Hadi Hasan, and Ahmed T Sadiq. 2022. A survey of toulmin argumentation approach for medical applications. International Journal of Online & Biomedical Engineering, 18(2). [find](https://scholar.google.com/scholar?q=Hamzah+Noori+Fejer%2C+Ali+Hadi+Hasan%2C+and+Ahmed+T+Sadiq%2E+2022%2E+A+survey+of+toulmin+argumentation+approach+for+medical+applications%2E+International+Journal+of+Online+%26+Biomedical+Engineering%2C+18%282%29%2E)
10. Dibya Ghosh, Abhishek Gupta, Ashwin Reddy, Justin Fu, Coline Devin, Benjamin Eysenbach, and Sergey Levine. 2019. Learning to reach goals via iterated supervised learning. arXiv preprint arXiv:1912.06088. — [arXiv:1912.06088](https://arxiv.org/abs/1912.06088) [find](https://scholar.google.com/scholar?q=Dibya+Ghosh%2C+Abhishek+Gupta%2C+Ashwin+Reddy%2C+Justin+Fu%2C+Coline+Devin%2C+Benjamin+Eysenbach%2C+and+Sergey+Levine%2E+2019%2E+Learning+to+reach+goals+via+iterated+supervised+learning%2E+arXiv+preprint+arXiv%3A1912%2E060)
11. Alex Graves, Marc G Bellemare, Jacob Menick, Remi Munos, and Koray Kavukcuoglu. 2017. Automated curriculum learning for neural networks. In international conference on machine learning, pages 1311– 1320. Pmlr. [find](https://scholar.google.com/scholar?q=Alex+Graves%2C+Marc+G+Bellemare%2C+Jacob+Menick%2C+Remi+Munos%2C+and+Koray+Kavukcuoglu%2E+2017%2E+Automated+curriculum+learning+for+neural+networks%2E+In+international+conference+on+machine+learning%2C+pages+1311%E2%80%93+13)
12. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. Deepseekr1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633–638. [find](https://scholar.google.com/scholar?q=Daya+Guo%2C+Dejian+Yang%2C+Haowei+Zhang%2C+Junxiao+Song%2C+Peiyi+Wang%2C+Qihao+Zhu%2C+Runxin+Xu%2C+Ruoyu+Zhang%2C+Shirong+Ma%2C+Xiao+Bi%2C+and+1+others%2E+2025%2E+Deepseekr1+incentivizes+reasoning+in+llms+through+reinforceme)
13. Paul Hager, Friederike Jungmann, Robbie Holland, Kunal Bhagat, Inga Hubrecht, Manuel Knauer, Jakob Vielhauer, Marcus Makowski, Rickmer Braren, Georgios Kaissis, and 1 others. 2024. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nature medicine, 30(… [find](https://scholar.google.com/scholar?q=Paul+Hager%2C+Friederike+Jungmann%2C+Robbie+Holland%2C+Kunal+Bhagat%2C+Inga+Hubrecht%2C+Manuel+Knauer%2C+Jakob+Vielhauer%2C+Marcus+Makowski%2C+Rickmer+Braren%2C+Georgios+Kaissis%2C+and+1+others%2E+2024%2E+Evaluation+and+miti)
14. Kexin Huang, Jaan Altosaar, and Rajesh Ranganath. 2019. [Clinicalbert: Modeling clinical notes and predicting hospital readmission](https://md.research.elamur.ai/free/en/papers/huang-2019-clinicalbert-modeling-clinical-notes-predicting/). arXiv preprint arXiv:1904.05342.
15. Xiao-huan Liu, Zhen-hua Lu, Tao Wang, and Fei Liu. 2024. Large language models facilitating modern molecular biology and novel drug development. Frontiers in Pharmacology, 15:1458739. [find](https://scholar.google.com/scholar?q=Xiao%2Dhuan+Liu%2C+Zhen%2Dhua+Lu%2C+Tao+Wang%2C+and+Fei+Liu%2E+2024%2E+Large+language+models+facilitating+modern+molecular+biology+and+novel+drug+development%2E+Frontiers+in+Pharmacology%2C+15%3A1458739%2E)
16. Di Jin, Eileen Pan, Nassim Oufattole, Wei-Hung Weng, Hanyi Fang, and Peter Szolovits. 2020. [What disease does this patient have? a large-scale open domain question answering dataset from medical exams](https://md.research.elamur.ai/free/en/papers/jin-2020-disease-this-patient-have-large/). Preprint, arXiv:2009.13081.
17. Xiaohong Liu, Hao Liu, Guoxing Yang, Zeyu Jiang, Shuguang Cui, Zhaoze Zhang, Huan Wang, Liyuan Tao, Yongchang Sun, Zhu Song, and 1 others. 2025. A generalist medical language model for disease diagnosis assistance. Nature medicine, 31(3):932–942. [find](https://scholar.google.com/scholar?q=Xiaohong+Liu%2C+Hao+Liu%2C+Guoxing+Yang%2C+Zeyu+Jiang%2C+Shuguang+Cui%2C+Zhaoze+Zhang%2C+Huan+Wang%2C+Liyuan+Tao%2C+Yongchang+Sun%2C+Zhu+Song%2C+and+1+others%2E+2025%2E+A+generalist+medical+language+model+for+disease+diagnos)
18. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. 2019. [Pubmedqa: A dataset for biomedical research question answering](https://md.research.elamur.ai/free/en/papers/jin-2019-pubmedqa-dataset-biomedical-research-question/). arXiv preprint arXiv:1909.06146.
19. Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Meiqi Guo, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, and 1 others. 2024. [Improve mathematical reasoning in language models by automated process supervision](https://md.research.elamur.ai/free/en/papers/luo-2024-improve-mathematical-reasoning-language-models/). arXiv preprint arXiv:2406.06592.
20. Hyunjung Ju, Ikseon Choi, and Bo Young Yoon. 2017. Do medical students generate sound arguments during small group discussions in problem-based learning?: an analysis of preclinical medical students’ argumentation according to a framework of hypothetico-deductive reasoning. Korean journal of medical… [find](https://scholar.google.com/scholar?q=Hyunjung+Ju%2C+Ikseon+Choi%2C+and+Bo+Young+Yoon%2E+2017%2E+Do+medical+students+generate+sound+arguments+during+small+group+discussions+in+problem%2Dbased+learning%3F%3A+an+analysis+of+preclinical+medical+students%E2%80%99+)
21. Timo Kaufmann, Paul Weng, Viktor Bengs, and Eyke Hüllermeier. 2024. [A survey of reinforcement learning from human feedback](https://md.research.elamur.ai/free/en/papers/kaufmann-2023-survey-reinforcement-learning-human-feedback/).
22. Tiffany H Kung, Morgan Cheatham, Arielle Medenilla, Czarina Sillos, Lorie De Leon, Camille Elepaño, Maria Madriaga, Rimel Aggabao, Giezel Diaz-Candido, James Maningo, and 1 others. 2023. [Performance of chatgpt on usmle: potential for ai-assisted medical education using large language models](https://md.research.elamur.ai/free/en/papers/kung-2023-performance-chatgpt-usmle-potential-ai/). PLoS di…
23. Tamera Lanham, Anna Chen, Ansh Radhakrishnan, Benoit Steiner, Carson Denison, Danny Hernandez, Dustin Li, Esin Durmus, Evan Hubinger, Jackson Kernion, and 1 others. 2023. [Measuring faithfulness in chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/lanham-2023-measuring-faithfulness-chain-thought-reasoning/). arXiv preprint arXiv:2307.13702.
24. John Lawrence and Chris Reed. 2020. [Argument mining: A survey](https://md.research.elamur.ai/free/en/papers/lawrence-2019-argument-mining-survey/). Computational linguistics, 45(4):765– 818.
25. Jinhyuk Lee, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, and Jaewoo Kang. 2020. [Biobert: a pre-trained biomedical language representation model for biomedical text mining](https://md.research.elamur.ai/free/en/papers/lee-2019-biobert-pre-trained-biomedical-language/). Bioinformatics, 36(4):1234–1240.
26. Yunxiang Li, Zihan Li, Kai Zhang, Ruilong Dan, Steve Jiang, and You Zhang. 2023. [Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge](https://md.research.elamur.ai/free/en/papers/li-2023-chatdoctor-medical-chat-model-fine/). Cureus, 15(6).
27. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
28. Liam G McCoy, Rajiv Swamy, Nidhish Sagar, Minjia Wang, Stephen Bacchi, Jie Ming Nigel Fong, Nigel CK Tan, Kevin Tan, Thomas A Buckley, Peter Brodeur, and 1 others. 2025. Assessment of large language models in clinical reasoning: A novel benchmarking study. NEJM AI, 2(10):AIdbp2500120. [find](https://scholar.google.com/scholar?q=Liam+G+McCoy%2C+Rajiv+Swamy%2C+Nidhish+Sagar%2C+Minjia+Wang%2C+Stephen+Bacchi%2C+Jie+Ming+Nigel+Fong%2C+Nigel+CK+Tan%2C+Kevin+Tan%2C+Thomas+A+Buckley%2C+Peter+Brodeur%2C+and+1+others%2E+2025%2E+Assessment+of+large+language+m)
29. Harsha Nori, Nicholas King, Scott Mayer McKinney, Dean Carignan, and Eric Horvitz. 2023. [Capabilities of gpt-4 on medical challenge problems](https://md.research.elamur.ai/free/en/papers/nori-2023-capabilities-gpt-4-medical-challenge/). arXiv preprint arXiv:2303.13375.
30. Rafał Obuchowicz, Julia Lasek, Marek Wodziński, Adam Piórkowski, Michał Strzelecki, and Karolina Nurzynska. 2025. Artificial intelligence-empowered radiology—current status and critical review. Diagnostics, 15(3):282. [find](https://scholar.google.com/scholar?q=Rafa%C5%82+Obuchowicz%2C+Julia+Lasek%2C+Marek+Wodzin%CC%81ski%2C+Adam+Pi%C3%B3rkowski%2C+Micha%C5%82+Strzelecki%2C+and+Karolina+Nurzynska%2E+2025%2E+Artificial+intelligence%2Dempowered+radiology%E2%80%94current+status+and+critical+review%2E+Diagn)
31. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2022. [Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering](https://md.research.elamur.ai/free/en/papers/pal-2022-medmcqa-large-scale-multi-subject/). In Conference on health, inference, and learning, pages 248–260. PMLR.
32. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. [find](https://scholar.google.com/scholar?q=Qwen%2C+%3A%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+)
33. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741.
34. Martin Riedmiller, Roland Hafner, Thomas Lampe, Michael Neunert, Jonas Degrave, Tom Wiele, Vlad Mnih, Nicolas Heess, and Jost Tobias Springenberg. 2018. Learning by playing solving sparse reward tasks from scratch. In International conference on machine learning, pages 4344–4353. PMLR. [find](https://scholar.google.com/scholar?q=Martin+Riedmiller%2C+Roland+Hafner%2C+Thomas+Lampe%2C+Michael+Neunert%2C+Jonas+Degrave%2C+Tom+Wiele%2C+Vlad+Mnih%2C+Nicolas+Heess%2C+and+Jost+Tobias+Springenberg%2E+2018%2E+Learning+by+playing+solving+sparse+reward+tasks)
35. Tom Schaul, Daniel Horgan, Karol Gregor, and David Silver. 2015. Universal value function approximators. In International conference on machine learning, pages 1312–1320. PMLR. [find](https://scholar.google.com/scholar?q=Tom+Schaul%2C+Daniel+Horgan%2C+Karol+Gregor%2C+and+David+Silver%2E+2015%2E+Universal+value+function+approximators%2E+In+International+conference+on+machine+learning%2C+pages+1312%E2%80%931320%2E+PMLR%2E)
36. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
37. Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, and 1 others. 2023. [Large language models encode clinical knowledge](https://md.research.elamur.ai/free/en/papers/singhal-2022-large-language-models-encode-clinical/). Nature, 620(7972):172–180.
38. Petru Soviany, Radu Tudor Ionescu, Paolo Rota, and Nicu Sebe. 2022. Curriculum learning: A survey. International Journal of Computer Vision, 130(6):1526– 1565. [find](https://scholar.google.com/scholar?q=Petru+Soviany%2C+Radu+Tudor+Ionescu%2C+Paolo+Rota%2C+and+Nicu+Sebe%2E+2022%2E+Curriculum+learning%3A+A+survey%2E+International+Journal+of+Computer+Vision%2C+130%286%29%3A1526%E2%80%93+1565%2E)
39. Songtao Tan, Xin Xin, and Di Wu. 2024. Chatgpt in medicine: prospects and challenges: a review article. International journal of surgery, 110(6):3701–3706. [find](https://scholar.google.com/scholar?q=Songtao+Tan%2C+Xin+Xin%2C+and+Di+Wu%2E+2024%2E+Chatgpt+in+medicine%3A+prospects+and+challenges%3A+a+review+article%2E+International+journal+of+surgery%2C+110%286%29%3A3701%E2%80%933706%2E)
40. Stephen E Toulmin. 2003. The uses of argument. Cambridge university press. [find](https://scholar.google.com/scholar?q=Stephen+E+Toulmin%2E+2003%2E+The+uses+of+argument%2E+Cambridge+university+press%2E)
41. Tao Tu, Mike Schaekermann, Anil Palepu, Khaled Saab, Jan Freyberg, Ryutaro Tanno, Amy Wang, Brenna Li, Mohamed Amin, Yong Cheng, and 1 others. 2025. Towards conversational diagnostic artificial intelligence. Nature, pages 1–9. [find](https://scholar.google.com/scholar?q=Tao+Tu%2C+Mike+Schaekermann%2C+Anil+Palepu%2C+Khaled+Saab%2C+Jan+Freyberg%2C+Ryutaro+Tanno%2C+Amy+Wang%2C+Brenna+Li%2C+Mohamed+Amin%2C+Yong+Cheng%2C+and+1+others%2E+2025%2E+Towards+conversational+diagnostic+artificial+intell)
42. Miles Turpin, Julian Michael, Ethan Perez, and Samuel Bowman. 2023. [Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting](https://md.research.elamur.ai/free/en/papers/turpin-2023-language-models-don-t-always/). Advances in Neural Information Processing Systems, 36:74952–74965.
43. Alexandros Vassiliades, Nick Bassiliades, and Theodore Patkos. 2021. Argumentation and explainable artificial intelligence: a survey. The Knowledge Engineering Review, 36:e5. [find](https://scholar.google.com/scholar?q=Alexandros+Vassiliades%2C+Nick+Bassiliades%2C+and+Theodore+Patkos%2E+2021%2E+Argumentation+and+explainable+artificial+intelligence%3A+a+survey%2E+The+Knowledge+Engineering+Review%2C+36%3Ae5%2E)
44. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
45. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
46. Juncheng Wu, Wenlong Deng, Xingxuan Li, Sheng Liu, Taomian Mi, Yifan Peng, Ziyang Xu, Yi Liu, Hyunjin Cho, Chang-In Choi, and 1 others. 2025a. Medreason: Eliciting factual medical reasoning steps in llms via knowledge graphs. arXiv preprint arXiv:2504.00993. — [arXiv:2504.00993](https://arxiv.org/abs/2504.00993) [find](https://scholar.google.com/scholar?q=Juncheng+Wu%2C+Wenlong+Deng%2C+Xingxuan+Li%2C+Sheng+Liu%2C+Taomian+Mi%2C+Yifan+Peng%2C+Ziyang+Xu%2C+Yi+Liu%2C+Hyunjin+Cho%2C+Chang%2DIn+Choi%2C+and+1+others%2E+2025a%2E+Medreason%3A+Eliciting+factual+medical+reasoning+steps+in+l)
47. Kevin Wu, Eric Wu, Rahul Thapa, Kevin Wei, Angela Zhang, Arvind Suresh, Jacqueline J Tao, Min Woo Sun, Alejandro Lozano, and James Zou. 2025b. Medcasereasoning: Evaluating and learning diagnostic reasoning from clinical case reports. arXiv preprint arXiv:2505.11733. — [arXiv:2505.11733](https://arxiv.org/abs/2505.11733) [find](https://scholar.google.com/scholar?q=Kevin+Wu%2C+Eric+Wu%2C+Rahul+Thapa%2C+Kevin+Wei%2C+Angela+Zhang%2C+Arvind+Suresh%2C+Jacqueline+J+Tao%2C+Min+Woo+Sun%2C+Alejandro+Lozano%2C+and+James+Zou%2E+2025b%2E+Medcasereasoning%3A+Evaluating+and+learning+diagnostic+reas)
48. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+inf)
49. Erlan Yu, Xuehong Chu, Wanwan Zhang, Xiangbin Meng, Yaodong Yang, Xunming Ji, and Chuanjie Wu. 2025. Large language models in medicine: Applications, challenges, and future directions. International Journal of Medical Sciences, 22(11):2792. [find](https://scholar.google.com/scholar?q=Erlan+Yu%2C+Xuehong+Chu%2C+Wanwan+Zhang%2C+Xiangbin+Meng%2C+Yaodong+Yang%2C+Xunming+Ji%2C+and+Chuanjie+Wu%2E+2025%2E+Large+language+models+in+medicine%3A+Applications%2C+challenges%2C+and+future+directions%2E+International+J)
50. Zhenghang Yuan, Lichao Mou, Qi Wang, and Xiao Xiang Zhu. 2022. From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data. IEEE transactions on geoscience and remote sensing, 60:1–11. [find](https://scholar.google.com/scholar?q=Zhenghang+Yuan%2C+Lichao+Mou%2C+Qi+Wang%2C+and+Xiao+Xiang+Zhu%2E+2022%2E+From+easy+to+hard%3A+Learning+language%2Dguided+curriculum+for+visual+question+answering+on+remote+sensing+data%2E+IEEE+transactions+on+geoscie)
51. Jaehoon Yun, Jiwoong Sohn, Jungwoo Park, Hyunjae Kim, Xiangru Tang, Yanjun Shao, Yonghoe Koo, Minhyeok Ko, Qingyu Chen, Mark Gerstein, and 1 others. 2025. Med-prm: Medical reasoning models with stepwise, guideline-verified process rewards. arXiv preprint arXiv:2506.11474. [find](https://scholar.google.com/scholar?q=Jaehoon+Yun%2C+Jiwoong+Sohn%2C+Jungwoo+Park%2C+Hyunjae+Kim%2C+Xiangru+Tang%2C+Yanjun+Shao%2C+Yonghoe+Koo%2C+Minhyeok+Ko%2C+Qingyu+Chen%2C+Mark+Gerstein%2C+and+1+others%2E+2025%2E+Med%2Dprm%3A+Medical+reasoning+models+with+stepwi)
52. Kaiyan Zhang, Sihang Zeng, Ermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Haoxin Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, Xingtai Lv, Hu Jinfang, Zhiyuan Liu, and Bowen Zhou. 2024. Ultramedical: Building specialized generalists in biomedicine. [find](https://scholar.google.com/scholar?q=Kaiyan+Zhang%2C+Sihang+Zeng%2C+Ermo+Hua%2C+Ning+Ding%2C+Zhang%2DRen+Chen%2C+Zhiyuan+Ma%2C+Haoxin+Li%2C+Ganqu+Cui%2C+Biqing+Qi%2C+Xuekai+Zhu%2C+Xingtai+Lv%2C+Hu+Jinfang%2C+Zhiyuan+Liu%2C+and+Bowen+Zhou%2E+2024%2E+Ultramedical%3A+Buildi)
53. Danna Zheng, Danyang Liu, Mirella Lapata, and Jeff Z Pan. 2024a. Trustscore: Reference-free evaluation of llm response trustworthiness. arXiv preprint arXiv:2402.12545. — [arXiv:2402.12545](https://arxiv.org/abs/2402.12545) [find](https://scholar.google.com/scholar?q=Danna+Zheng%2C+Danyang+Liu%2C+Mirella+Lapata%2C+and+Jeff+Z+Pan%2E+2024a%2E+Trustscore%3A+Reference%2Dfree+evaluation+of+llm+response+trustworthiness%2E+arXiv+preprint+arXiv%3A2402%2E12545%2E+%E2%80%94+%5BarXiv%3A2402%2E12545%5D%28https%3A%2F%2Far)
54. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024b. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). arXiv preprint arXiv:2403.13372.
55. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, and 1 others. 2022. [Least-to-most prompting enables complex reasoning in large language models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/). arXiv preprint arXiv:2205.10625.

*Updated 2 November 2026*