---
title: "Simulating Student Interactions for Virtual — Thuy 2026"
description: "Estimating the difficulty of new exam questions usually requires pretesting them on real learners."
authors: ["Arthur Thuy", "Luca Benedetto", "Ekaterina Loginova", "Dries F. Benoit"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.815/"
doi: "10.63317/5m57qocfb6ph"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/thuy-2026-simulating-student-interactions-virtual-pretesting/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/thuy-2026-simulating-student-interactions-virtual-pretesting/)

[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/9/) / Simulating Student Interactions for Virtual Pretesting with In-Context Learning

# Simulating Student Interactions for Virtual Pretesting with In-Context Learning

**Authors:** Arthur Thuy, Luca Benedetto, Ekaterina Loginova, Dries F. Benoit · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.815/) · [PDF](https://aclanthology.org/2026.lrec-1.815.pdf) · [DOI 10.63317/5m57qocfb6ph](https://doi.org/10.63317/5m57qocfb6ph) · [OpenAlex](https://openalex.org/W7160210867)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Estimating the difficulty of new exam questions usually requires pretesting them on real learners. This is slow and costly, and it exposes test content. Virtual pretesting replaces those learners with LLM-generated answers, but earlier zero-shot role-playing matched real response patterns poorly. The authors propose an in-context learning framework with two stages. First, a reasoning model (o4-mini) labels past student–question interactions with the skills behind correct answers and the misconceptions behind wrong ones. This works on multiple-choice logs (DBE-KT22, database systems) or on open-ended writing (FCE essays, applied to English reading comprehension). Second, an LLM role-plays a prototypical student at one of five proficiency levels, given these labels and earlier interactions as context. The simulated answers are then fed into IRT to estimate item difficulty. Single models often fail to use the added context. However, pooling simulations from several models lowers difficulty-estimation RMSE by up to 30%. The method needs far fewer real records than supervised fine-tuning, though agreement with genuine learners remains limited.

## Key points
- Two-step pipeline: (1) an LLM extracts skills and misconceptions from previous interactions; (2) role-play simulation is conditioned on that information, with IRT applied to the resulting synthetic response dataset.
- Skill and misconception extraction uses GPT-o4-mini ("o4-mini-2025-04-16") at temperature 1.0. Labels for skills start with "Understands" and labels for misconceptions with "Confuses".
- Two personas are compared, each with and without context. In the student persona, the model answers as the learner. In the teacher persona, the model predicts how the learner would answer. Both use a five-level scale running from Fundamental Awareness to Expert.
- Questions are split into train/validation/test, and the same student IDs can appear across splits. This allows an optional knowledge-tracing-style check of how well individual students are replicated.
- Main result: a multi-model ensemble with relevant context cuts difficulty RMSE by up to 30% compared with non-contextual and single contextual models. Code and prompts are available at github.com/arthur-thuy/LLM-virtual-pretesting.

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

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

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

```bibtex
@inproceedings{thuy2026simulating,
  title = {{Simulating Student Interactions for Virtual Pretesting with In-Context Learning}},
  author = {Thuy, Arthur and Benedetto, Luca and Loginova, Ekaterina and Benoit, Dries F.},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5m57qocfb6ph},
  url = {https://doi.org/10.63317/5m57qocfb6ph}
}
```

- [← previous Simplify-Pro: A Two-level and Progressive LLM-based Framework for Auto Long Text Simplification](https://md.research.elamur.ai/free/en/papers/zhou-2026-simplify-pro-two-level-progressive/)
- [next → SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech](https://md.research.elamur.ai/free/en/papers/sofalas-2026-sinfos-parallel-dataset-translating-sinhala/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/)

## References

36 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ghodai Abdelrahman, Sherif Abdelfattah, Qing Wang, and Yu Lin. 2022. Dbe-kt22: A knowledge tracing dataset based on online student evaluation. arXiv preprint arXiv:2208.12651. — [arXiv:2208.12651](https://arxiv.org/abs/2208.12651) [find](https://scholar.google.com/scholar?q=Ghodai+Abdelrahman%2C+Sherif+Abdelfattah%2C+Qing+Wang%2C+and+Yu+Lin%2E+2022%2E+Dbe%2Dkt22%3A+A+knowledge+tracing+dataset+based+on+online+student+evaluation%2E+arXiv+preprint+arXiv%3A2208%2E12651%2E+%E2%80%94+%5BarXiv%3A2208%2E12651%5D%28htt)
2. Gati V Aher, Rosa I Arriaga, and Adam Tauman Kalai. 2023. Using large language models to simulate multiple humans and replicate human subject studies. In International conference on machine learning, pages 337–371. PMLR. [find](https://scholar.google.com/scholar?q=Gati+V+Aher%2C+Rosa+I+Arriaga%2C+and+Adam+Tauman+Kalai%2E+2023%2E+Using+large+language+models+to+simulate+multiple+humans+and+replicate+human+subject+studies%2E+In+International+conference+on+machine+learning%2C+)
3. Samah AlKhuzaey, Floriana Grasso, Terry R. Payne, and Valentina Tamma. 2021. A Systematic Review of Data-Driven Approaches to Item Difficulty Prediction. In Ido Roll, Danielle McNamara, Sergey Sosnovsky, Rose Luckin, and Vania Dimitrova, editors, Artificial Intelligence in Education, volume 12748, p… [find](https://scholar.google.com/scholar?q=Samah+AlKhuzaey%2C+Floriana+Grasso%2C+Terry+R%2E+Payne%2C+and+Valentina+Tamma%2E+2021%2E+A+Systematic+Review+of+Data%2DDriven+Approaches+to+Item+Difficulty+Prediction%2E+In+Ido+Roll%2C+Danielle+McNamara%2C+Sergey+Sosnovs)
4. Yigal Attali, Luis Saldivia, Carol Jackson, Fred Schuppan, and Wilbur Wanamaker. 2014. Estimating item difficulty with comparative judgments. ETS Research Report Series, 2014(2):1–8. [find](https://scholar.google.com/scholar?q=Yigal+Attali%2C+Luis+Saldivia%2C+Carol+Jackson%2C+Fred+Schuppan%2C+and+Wilbur+Wanamaker%2E+2014%2E+Estimating+item+difficulty+with+comparative+judgments%2E+ETS+Research+Report+Series%2C+2014%282%29%3A1%E2%80%938%2E)
5. Lisa Beinborn, Torsten Zesch, and Iryna Gurevych. 2015. Candidate evaluation strategies for improved difficulty prediction of language tests. In Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 1–11, Denver, Colorado. Association for Computation… [find](https://scholar.google.com/scholar?q=Lisa+Beinborn%2C+Torsten+Zesch%2C+and+Iryna+Gurevych%2E+2015%2E+Candidate+evaluation+strategies+for+improved+difficulty+prediction+of+language+tests%2E+In+Proceedings+of+the+Tenth+Workshop+on+Innovative+Use+of+)
6. Luca Benedetto. 2023. A quantitative study of nlp approaches to question difficulty estimation. In International Conference on Artificial Intelligence in Education, pages 428–434. Springer. [find](https://scholar.google.com/scholar?q=Luca+Benedetto%2E+2023%2E+A+quantitative+study+of+nlp+approaches+to+question+difficulty+estimation%2E+In+International+Conference+on+Artificial+Intelligence+in+Education%2C+pages+428%E2%80%93434%2E+Springer%2E)
7. Luca Benedetto, Giovanni Aradelli, Antonia Donvito, Alberto Lucchetti, Andrea Cappelli, and Paula Buttery. 2024. Using LLMs to simulate students’ responses to exam questions. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11351–11368, Miami, Florida, USA. Association… [find](https://scholar.google.com/scholar?q=Luca+Benedetto%2C+Giovanni+Aradelli%2C+Antonia+Donvito%2C+Alberto+Lucchetti%2C+Andrea+Cappelli%2C+and+Paula+Buttery%2E+2024%2E+Using+LLMs+to+simulate+students%E2%80%99+responses+to+exam+questions%2E+In+Findings+of+the+Associ)
8. Luca Benedetto, Andrea Cappelli, Roberto Turrin, and Paolo Cremonesi. 2020. R2DE: A NLP approach to estimating IRT parameters of newly generated questions. In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, pages 412–421, Frankfurt Germany. ACM. [find](https://scholar.google.com/scholar?q=Luca+Benedetto%2C+Andrea+Cappelli%2C+Roberto+Turrin%2C+and+Paolo+Cremonesi%2E+2020%2E+R2DE%3A+A+NLP+approach+to+estimating+IRT+parameters+of+newly+generated+questions%2E+In+Proceedings+of+the+Tenth+International+Co)
9. Luca Benedetto, Paolo Cremonesi, Andrew Caines, Paula Buttery, Andrea Cappelli, Andrea Giussani, and Roberto Turrin. 2023. A survey on recent approaches to question difficulty estimation from text. ACM Computing Surveys, 55(9):1–37. [find](https://scholar.google.com/scholar?q=Luca+Benedetto%2C+Paolo+Cremonesi%2C+Andrew+Caines%2C+Paula+Buttery%2C+Andrea+Cappelli%2C+Andrea+Giussani%2C+and+Roberto+Turrin%2E+2023%2E+A+survey+on+recent+approaches+to+question+difficulty+estimation+from+text%2E+AC)
10. Molly Crockett and Lisa Messeri. 2023. Should large language models replace human participants? [find](https://scholar.google.com/scholar?q=Molly+Crockett+and+Lisa+Messeri%2E+2023%2E+Should+large+language+models+replace+human+participants%3F)
11. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. [find](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2018%2E+Bert%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+arXiv+preprint+arXiv%3A1810%2E04805%2E)
12. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, and Zhifang Sui. 2024. A survey on in-context learning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1107–1128, Miami… [find](https://scholar.google.com/scholar?q=Qingxiu+Dong%2C+Lei+Li%2C+Damai+Dai%2C+Ce+Zheng%2C+Jingyuan+Ma%2C+Rui+Li%2C+Heming+Xia%2C+Jingjing+Xu%2C+Zhiyong+Wu%2C+Baobao+Chang%2C+Xu+Sun%2C+Lei+Li%2C+and+Zhifang+Sui%2E+2024%2E+A+survey+on+in%2Dcontext+learning%2E+In+Proceeding) [our card](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/)
13. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv e-prints, pages arXiv– 2407. [find](https://scholar.google.com/scholar?q=Abhimanyu+Dubey%2C+Abhinav+Jauhri%2C+Abhinav+Pandey%2C+Abhishek+Kadian%2C+Ahmad+Al%2DDahle%2C+Aiesha+Letman%2C+Akhil+Mathur%2C+Alan+Schelten%2C+Amy+Yang%2C+Angela+Fan%2C+et+al%2E+2024%2E+The+llama+3+herd+of+models%2E+arXiv+e%2Dpri)
14. Wanyong Feng, Peter Tran, Stephen Sireci, and Andrew S. Lan. 2025. Reasoning and Sampling-Augmented MCQ Difficulty Prediction via LLMs. In Alexandra I. Cristea, Erin Walker, Yu Lu, Olga C. Santos, and Seiji Isotani, editors, Artificial Intelligence in Education, volume 15880, pages 31–45. Springer N… [find](https://scholar.google.com/scholar?q=Wanyong+Feng%2C+Peter+Tran%2C+Stephen+Sireci%2C+and+Andrew+S%2E+Lan%2E+2025%2E+Reasoning+and+Sampling%2DAugmented+MCQ+Difficulty+Prediction+via+LLMs%2E+In+Alexandra+I%2E+Cristea%2C+Erin+Walker%2C+Yu+Lu%2C+Olga+C%2E+Santos%2C+and)
15. Le An Ha, Victoria Yaneva, Peter Baldwin, and Janet Mee. 2019. Predicting the difficulty of multiple choice questions in a high-stakes medical exam. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 11–20, Florence, Italy. Association for… [find](https://scholar.google.com/scholar?q=Le+An+Ha%2C+Victoria+Yaneva%2C+Peter+Baldwin%2C+and+Janet+Mee%2E+2019%2E+Predicting+the+difficulty+of+multiple+choice+questions+in+a+high%2Dstakes+medical+exam%2E+In+Proceedings+of+the+Fourteenth+Workshop+on+Innova)
16. Ronald K Hambleton, Hariharan Swaminathan, and H Jane Rogers. 1991. Fundamentals of item response theory, volume 2. Sage. [find](https://scholar.google.com/scholar?q=Ronald+K+Hambleton%2C+Hariharan+Swaminathan%2C+and+H+Jane+Rogers%2E+1991%2E+Fundamentals+of+item+response+theory%2C+volume+2%2E+Sage%2E)
17. Jacqueline Harding, William D’Alessandro, NG Laskowski, and Robert Long. 2024. Ai language models cannot replace human research participants. Ai & Society, 39(5):2603–2605. [find](https://scholar.google.com/scholar?q=Jacqueline+Harding%2C+William+D%E2%80%99Alessandro%2C+NG+Laskowski%2C+and+Robert+Long%2E+2024%2E+Ai+language+models+cannot+replace+human+research+participants%2E+Ai+%26+Society%2C+39%285%29%3A2603%E2%80%932605%2E)
18. Fu-Yuan Hsu, Hahn-Ming Lee, Tao-Hsing Chang, and Yao-Ting Sung. 2018. Automated estimation of item difficulty for multiple-choice tests: An application of word embedding techniques. Information Processing & Management, 54(6):969– 984. [find](https://scholar.google.com/scholar?q=Fu%2DYuan+Hsu%2C+Hahn%2DMing+Lee%2C+Tao%2DHsing+Chang%2C+and+Yao%2DTing+Sung%2E+2018%2E+Automated+estimation+of+item+difficulty+for+multiple%2Dchoice+tests%3A+An+application+of+word+embedding+techniques%2E+Information+Proces)
19. Suzanne Lane, Mark R Raymond, Thomas M Haladyna, et al. 2016. Handbook of test development, volume 2. Routledge New York, NY. [find](https://scholar.google.com/scholar?q=Suzanne+Lane%2C+Mark+R+Raymond%2C+Thomas+M+Haladyna%2C+et+al%2E+2016%2E+Handbook+of+test+development%2C+volume+2%2E+Routledge+New+York%2C+NY%2E)
20. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474. [find](https://scholar.google.com/scholar?q=Patrick+Lewis%2C+Ethan+Perez%2C+Aleksandra+Piktus%2C+Fabio+Petroni%2C+Vladimir+Karpukhin%2C+Naman+Goyal%2C+Heinrich+K%C3%BCttler%2C+Mike+Lewis%2C+Wen%2Dtau+Yih%2C+Tim+Rockt%C3%A4schel%2C+et+al%2E+2020%2E+Retrieval%2Daugmented+generation+f)
21. Naiming Liu, Shashank Sonkar, and Richard Baraniuk. 2025. Do llms make mistakes like students? exploring natural alignments between language models and human error patterns. In International Conference on Artificial Intelligence in Education, pages 364–377. Springer. [find](https://scholar.google.com/scholar?q=Naiming+Liu%2C+Shashank+Sonkar%2C+and+Richard+Baraniuk%2E+2025%2E+Do+llms+make+mistakes+like+students%3F+exploring+natural+alignments+between+language+models+and+human+error+patterns%2E+In+International+Conferenc)
22. Ekaterina Loginova, Luca Benedetto, Dries Benoit, and Paolo Cremonesi. 2021. Towards the application of calibrated transformers to the unsupervised estimation of question difficulty from text. In RANLP 2021, pages 846–855. INCOMA. [find](https://scholar.google.com/scholar?q=Ekaterina+Loginova%2C+Luca+Benedetto%2C+Dries+Benoit%2C+and+Paolo+Cremonesi%2E+2021%2E+Towards+the+application+of+calibrated+transformers+to+the+unsupervised+estimation+of+question+difficulty+from+text%2E+In+RANL)
23. Hotaka Maeda. 2025. Field-testing multiple-choice questions with ai examinees: English grammar items. Educational and Psychological Measurement, 85(2):221–244. [find](https://scholar.google.com/scholar?q=Hotaka+Maeda%2E+2025%2E+Field%2Dtesting+multiple%2Dchoice+questions+with+ai+examinees%3A+English+grammar+items%2E+Educational+and+Psychological+Measurement%2C+85%282%29%3A221%E2%80%93244%2E)
24. Andrew Mullooly, Øistein Andersen, Luca Benedetto, Paula Buttery, Andrew Caines, Mark JF Gales, Yasin Karatay, Kate Knill, Adian Liusie, Vatsal Raina, et al. 2023. The cambridge multiple-choice questions reading dataset. [find](https://scholar.google.com/scholar?q=Andrew+Mullooly%2C+%C3%98istein+Andersen%2C+Luca+Benedetto%2C+Paula+Buttery%2C+Andrew+Caines%2C+Mark+JF+Gales%2C+Yasin+Karatay%2C+Kate+Knill%2C+Adian+Liusie%2C+Vatsal+Raina%2C+et+al%2E+2023%2E+The+cambridge+multiple%2Dchoice+questi)
25. Jae-Woo Park, Seong-Jin Park, Hyun-Sik Won, and Kang-Min Kim. 2024. Large language models are students at various levels: Zero-shot question difficulty estimation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8157–8177, Miami, Florida, USA. Association for Computat… [find](https://scholar.google.com/scholar?q=Jae%2DWoo+Park%2C+Seong%2DJin+Park%2C+Hyun%2DSik+Won%2C+and+Kang%2DMin+Kim%2E+2024%2E+Large+language+models+are+students+at+various+levels%3A+Zero%2Dshot+question+difficulty+estimation%2E+In+Findings+of+the+Association+for+C)
26. Andreas Säuberli, Diego Frassinelli, and Barbara Plank. 2025. Do llms give psychometrically plausible responses in educational assessments? arXiv preprint arXiv:2506.09796. [find](https://scholar.google.com/scholar?q=Andreas+S%C3%A4uberli%2C+Diego+Frassinelli%2C+and+Barbara+Plank%2E+2025%2E+Do+llms+give+psychometrically+plausible+responses+in+educational+assessments%3F+arXiv+preprint+arXiv%3A2506%2E09796%2E)
27. Shuanghong Shen, Qi Liu, Zhenya Huang, Yonghe Zheng, Minghao Yin, Minjuan Wang, and Enhong Chen. 2024. A survey of knowledge tracing: Models, variants, and applications. IEEE Transactions on Learning Technologies, 17:1858–1879. [find](https://scholar.google.com/scholar?q=Shuanghong+Shen%2C+Qi+Liu%2C+Zhenya+Huang%2C+Yonghe+Zheng%2C+Minghao+Yin%2C+Minjuan+Wang%2C+and+Enhong+Chen%2E+2024%2E+A+survey+of+knowledge+tracing%3A+Models%2C+variants%2C+and+applications%2E+IEEE+Transactions+on+Learning+)
28. Arthur Thuy, Ekaterina Loginova, and Dries F Benoit. 2024. Active learning to guide labeling efforts for question difficulty estimation. arXiv preprint arXiv:2409.09258. — [arXiv:2409.09258](https://arxiv.org/abs/2409.09258) [find](https://scholar.google.com/scholar?q=Arthur+Thuy%2C+Ekaterina+Loginova%2C+and+Dries+F+Benoit%2E+2024%2E+Active+learning+to+guide+labeling+efforts+for+question+difficulty+estimation%2E+arXiv+preprint+arXiv%3A2409%2E09258%2E+%E2%80%94+%5BarXiv%3A2409%2E09258%5D%28https%3A%2F%2Fa)
29. Arthur Thuy, Ekaterina Loginova, and Dries F Benoit. 2025. Ordinality in discrete-level question difficulty estimation: Introducing balanced drps and orderedlogitnn. In Second Workshop on Automated Evaluation of Learning and Assessment Content, volume Vol. 4006. [find](https://scholar.google.com/scholar?q=Arthur+Thuy%2C+Ekaterina+Loginova%2C+and+Dries+F+Benoit%2E+2025%2E+Ordinality+in+discrete%2Dlevel+question+difficulty+estimation%3A+Introducing+balanced+drps+and+orderedlogitnn%2E+In+Second+Workshop+on+Automated+Ev)
30. Masaki Uto, Yuto Tomikawa, and Ayaka Suzuki. 2025. Question difficulty prediction based on virtual test-takers and item response theory. In Workshop on Automated Evaluation of Learning and Assessment Content, volume Vol. 3772. [find](https://scholar.google.com/scholar?q=Masaki+Uto%2C+Yuto+Tomikawa%2C+and+Ayaka+Suzuki%2E+2025%2E+Question+difficulty+prediction+based+on+virtual+test%2Dtakers+and+item+response+theory%2E+In+Workshop+on+Automated+Evaluation+of+Learning+and+Assessment+)
31. Wim J Van der Linden and Cees AW Glas. 2000. Computerized adaptive testing: Theory and practice. Springer. [find](https://scholar.google.com/scholar?q=Wim+J+Van+der+Linden+and+Cees+AW+Glas%2E+2000%2E+Computerized+adaptive+testing%3A+Theory+and+practice%2E+Springer%2E)
32. Lev Semenovich Vygotsky and Michael Cole. 1978. Mind in society: Development of higher psychological processes. Harvard university press. [find](https://scholar.google.com/scholar?q=Lev+Semenovich+Vygotsky+and+Michael+Cole%2E+1978%2E+Mind+in+society%3A+Development+of+higher+psychological+processes%2E+Harvard+university+press%2E)
33. Victoria Yaneva, Peter Baldwin, Janet Mee, et al. 2019. Predicting the difficulty of multiple choice questions in a high-stakes medical exam. In Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 11–20. [find](https://scholar.google.com/scholar?q=Victoria+Yaneva%2C+Peter+Baldwin%2C+Janet+Mee%2C+et+al%2E+2019%2E+Predicting+the+difficulty+of+multiple+choice+questions+in+a+high%2Dstakes+medical+exam%2E+In+Proceedings+of+the+Fourteenth+Workshop+on+Innovative+Us)
34. Victoria Yaneva, Peter Baldwin, Janet Mee, et al. 2020. Predicting item survival for multiple choice questions in a high-stakes medical exam. In Proceedings of The 12th Language Resources and Evaluation Conference, pages 6812–6818. [find](https://scholar.google.com/scholar?q=Victoria+Yaneva%2C+Peter+Baldwin%2C+Janet+Mee%2C+et+al%2E+2020%2E+Predicting+item+survival+for+multiple+choice+questions+in+a+high%2Dstakes+medical+exam%2E+In+Proceedings+of+The+12th+Language+Resources+and+Evaluati)
35. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Anfeng+Li%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Gao%2C+Chengen+Huang%2C+Chenxu+Lv%2C+Chujie+Zheng%2C+Dayiheng+Liu%2C+Fan+Zhou%2C+Fei+Huang%2C+Feng+Hu%2C+Hao+Ge%2C+Haoran+Wei%2C+Hua) [our card](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/)
36. Helen Yannakoudakis, Ted Briscoe, and Ben Medlock. 2011. A new dataset and method for automatically grading esol texts. In Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pages 180–189. [find](https://scholar.google.com/scholar?q=Helen+Yannakoudakis%2C+Ted+Briscoe%2C+and+Ben+Medlock%2E+2011%2E+A+new+dataset+and+method+for+automatically+grading+esol+texts%2E+In+Proceedings+of+the+49th+annual+meeting+of+the+association+for+computational+l) [our card](https://md.research.elamur.ai/free/en/papers/yannakoudakis-2011-new-dataset-method-automatically-grading/)