Elamur Research⌕
☰
home / papers / 2026 / PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors

PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors

Paper · 2026 · Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva et al.

Summary

LLM tutors usually treat all learners alike, even though pedagogical research suggests that the best teaching strategy depends on a student's personality. The authors first looked at a real deployment: a GPT-4o tutor used for language learning at an Italian high school. Its 281 anonymized chat logs show that the tutor almost always fell back on plain question answering, whatever the student was like.

To address this, the paper draws on learning-sciences literature to build a taxonomy that pairs low and high levels of each Big Five (OCEAN) trait with suitable teaching strategies. Strategies are kept only if they work in one-on-one LLM tutoring. In the PATS framework, LLM-simulated students with assigned personality profiles converse with an LLM tutor, which identifies the student's traits and picks a matching strategy. The simulations cover two educational tasks, one of which is image description.

Human teachers consistently preferred PATS dialogues over two baselines, and LLM judges agreed. PATS also drew more often on rarer, high-impact strategies such as role-play. The work shows that pedagogical theory can be built into LLM tutors through prompting, though some classroom strategies cannot be transferred this way.

Key points

  • The taxonomy links 17 teaching strategies to high and low levels of the OCEAN traits. A trait counts as "high" when its score exceeds 3 on the 44-item, 1–5 scale Big Five survey.
  • The real-world grounding study was run with the Minerva Research Association at Instituto Pindemonte (Verona, Italy) in March 2025. It involved 7 teachers, 110 students aged 16–21, and 281 chat logs. The 10 most common personality profiles were extracted from this data.
  • The classroom GPT-4o tutor relied mainly on question answering, which led to relatively low student engagement.
  • Teachers and LLM annotators favoured PATS, especially on motivation, empathy, and proactive support.
  • The annotated dataset is released under the MIT license, together with a demo (github.com/donya-rooein/PATS).

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

🎓University of ZurichZurich · Switzerland78 works · 12,260 citations🎓ETH ZurichZurich · Switzerland72 works · 5,176 citations🎓Bocconi UniversityMilan · Italy28 works · 3,077 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksInformation Systems · 1,437 worksComputer Science Applications · 102 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva, Yuan Qin, Debora Nozza, Mrinmaya Sachan and Dirk Hovy. 2026. PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.219

@inproceedings{rooein2026pats,
  title = {{PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors}},
  author = {Donya Rooein, Sankalan Pal Chowdhury, Mariia Eremeeva, Yuan Qin, Debora Nozza, Mrinmaya Sachan and Dirk Hovy},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.219},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.219}
}

References

83 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Lin-Miao L Agler, Kelley Stricklin, and Larisa K Alfsen. 2020. Using personality-based propensity as a guide for teaching practice. Journal of Curriculum and Teaching, 9(3):45. find
  2. Khaleel Alarbi, Mohanad Halaweh, Hassan Tairab, Najeh Rajeh Alsalhi, Nagaletchimee Annamalai, and Fatima Aldarmaki. 2024. Making a revolution in physics learning in high schools with chatgpt: A case study in uae. Eurasia Journal of Mathematics, Science and Technology Education, 20(9):em2499. find
  3. Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, et al. 2023. Gemini: a family of highly capable multimodal models. page arXiv:2312.11805.
  4. H. S. Barrows. 1986. A taxonomy of problem-based learning methods. Medical Education, 20(6):481– 486. find
  5. Benjamin S. Bell and Steve W. Kozlowski. 2008. Active learning: Effects of core training design elements on self-regulatory processes, learning, and adaptability. Journal of Applied Psychology, 93(2):296–316. find
  6. Matthew L. Bernacki, Meghan J. Greene, and Nikki G. Lobczowski. 2021. A systematic review of research on personalized learning: Personalized by whom, to what, how, and for what purpose(s)? Educational Psychology Review, 33(4):1675–1715. find
  7. Temi Bidjerano and David Yun Dai. 2007. The relationship between the big-five model of personality and self-regulated learning strategies. Learning and Individual Differences, 17(1):69–81. find
  8. Gregory J. Boyle. 1995. Myers-briggs type indicator (mbti): Some psychometric limitations. Humanities & Social Sciences papers, 30. find
  9. Vittorio V Busato, Frans J Prins, Jan J Elshout, and Christiaan Hamaker. 1998. The relation between learning styles, the big five personality traits and achievement motivation in higher education. Personality and Individual Differences, 26(1):129–140. find
  10. Paul Chandler and John Sweller. 1991. Cognitive load theory and the format of instruction. Cognition and Instruction, 8(4):293–332. find
  11. Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jinheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S Yu, et al. 2025. Llm agents for education: Advances and applications. arXiv preprint arXiv:2503.11733. find
  12. Gary J. Conti and Rita C. McNeil. 2024. The association of personality characteristics with learning strategy preferences. Journal of Education and Learning. find
  13. Mir Mohammad Seyed Danesh and Mir Mortazavi Soolmaz. 2010. Relationship between distance education and staff’s personality. In 2010 4th International Conference on Distance Learning and Education, pages 63–65. IEEE. find
  14. J M Digman. 1990. Personality structure: Emergence of the five-factor model. Annual Review of Psychology, 41(Volume 41, 1990):417–440. find
  15. 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, page arXiv:2407.21783.
  16. Richard Felder. 1988. Learning and teaching styles in engineering education. Journal of Engineering Education -Washington-, 78:674–681. find
  17. Mehmet Firat. 2022. Exploring the relationship between personality traits and e-learning autonomy of distance education students. Open Praxis, 14(4):280–290. find
  18. Alex Graf. 2023. Exploring the role of personalization in adaptive learning environments. International Journal Software Engineering and Computer Science (IJSECS), 3(2):50–56. find
  19. Juho Hamari, Jonna Koivisto, and Harri Sarsa. 2014. Does gamification work? – a literature review of empirical studies on gamification. In 2014 47th Hawaii International Conference on System Sciences, pages 3025–3034. IEEE. find
  20. Rick Harrington and Donald A Loffredo. 2010. Mbti personality type and other factors that relate to preference for online versus face-to-face instruction. The Internet and Higher Education, 13(1-2):89–95. find
  21. Gaole He, Gianluca Demartini, and Ujwal Gadiraju. 2025. Plan-then-execute: An empirical study of user trust and team performance when using llm agents as a daily assistant. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, CHI ’25, page 1–22. ACM. find
  22. Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Ming Liu, Zerui Chen, and Bing Qin. 2024. Planning like human: A dual-process framework for dialogue planning. arXiv preprint arXiv:2406.05374. find
  23. Joy He-Yueya, Noah D. Goodman, and Emma Brunskill. 2024. Evaluating and optimizing educational content with large language model judgments. find
  24. Tiancheng Hu and Nigel Collier. 2024. Quantifying the persona effect in LLM simulations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10289–10307, Bangkok, Thailand. Association for Computational Linguistics.
  25. Yuxuan Huang. 2024. Orca: Enhancing role-playing abilities of large language models by integrating personality traits. find
  26. Mikael Jensen. 2015. Personality traits, learning and academic achievements. Journal of Education and Learning, 4(4):91–118. find
  27. Hang Jiang, Xiajie Zhang, Xubo Cao, Cynthia Breazeal, Deb Roy, and Jad Kabbara. 2024. Personallm: Investigating the ability of large language models to express personality traits. find
  28. Hyoungwook Jin, Minju Yoo, Jeongeon Park, Yokyung Lee, Xu Wang, and Juho Kim. 2025. Teachtune: Reviewing pedagogical agents against diverse student profiles with simulated students. find
  29. Neil D. Fleming and Colleen Mills. 1992. Not another inventory, rather a catalyst for reflection. To Improve the Academy, 11(1):137–155. find
  30. Oliver P John, Laura P Naumann, and Christopher J Soto. 2008. Paradigm shift to the integrative big five trait taxonomy. Handbook of personality: Theory and research, 3(2):114–158. find
  31. Arthur C Graesser, Katja Wiemer-Hastings, Peter Wiemer-Hastings, and Roger Kreuz. 1999. Autotutor: A simulation of a human tutor. Cognitive Systems Research, 1(1):35–51. find
  32. Irina Jurenka, Markus Kunesch, Kevin R McKee, Daniel Gillick, Shaojian Zhu, Sara Wiltberger, Shubham Milind Phal, Katherine Hermann, Daniel Kasenberg, Avishkar Bhoopchand, et al. 2024. Towards responsible development of generative ai for education: An evaluation-driven approach. arXiv preprint arXiv… find
  33. David Kolb. 1984. Experiential learning: Experience as the source of learning and development. Journal of Business Ethics, 1. find
  34. Meera Komarraju and Steven J Karau. 2005. The relationship between the big five personality traits and academic motivation. Personality and individual differences, 39(3):557–567. find
  35. Xinyi Lu and Xu Wang. 2024. Generative students: Using llm-simulated student profiles to support question item evaluation. In Proceedings of the Eleventh ACM Conference on Learning @ Scale, L@S ’24, page 16–27, New York, NY, USA. Association for Computing Machinery. find
  36. Yiping Ma, Shiyu Hu, Xuchen Li, Yipei Wang, Shiqing Liu, and Kang Hao Cheong. 2024. Students rather than experts: A new ai for education pipeline to model more human-like and personalised early adolescences. find
  37. Meera Komarraju, Steven J. Karau, and Ronald R. Schmeck. 2009. Role of the big five personality traits in predicting college students’ academic motivation and achievement. Learning and Individual Differences, 19(1):47–52. find
  38. Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Tanmay Sinha, Manu Kapur, Iryna Gurevych, and Mrinmaya Sachan. 2023. Mathdial: A dialogue tutoring dataset with rich pedagogical properties grounded in math reasoning problems. arXiv preprint arXiv:2305.14536.
  39. Meera Komarraju, Steven J. Karau, Ronald R. Schmeck, and Alen Avdic. 2011. The big five personality traits, learning styles, and academic achievement. Personality and Individual Differences, 51(4):472–477. Digit Ratio (2D:4D) and Individual Differences Research. find
  40. Julia M. Markel, Steven G. Opferman, James A. Landay, and Chris Piech. 2023. Gpteach: Interactive ta training with gpt-based students. In Proceedings of the Tenth ACM Conference on Learning @ Scale, L@S ’23, page 226–236, New York, NY, USA. Association for Computing Machinery. find
  41. William K Lawrence. 2015. Learning and personality: The experience of introverted reflective learners in a world of extroverts. Cambridge Scholars Publishing. find
  42. Hang Li, Tianlong Xu, Chaoli Zhang, Eason Chen, Jing Liang, Xing Fan, Haoyang Li, Jiliang Tang, and Qingsong Wen. 2024. Bringing generative ai to adaptive learning in education. find
  43. Wenkai Li, Jiarui Liu, Andy Liu, Xuhui Zhou, Mona T. Diab, and Maarten Sap. 2025. BIG5-CHAT: Shaping LLM personalities through training on human-grounded data. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 20434– 20471, Vien…
  44. Ben Liu, Jihai Zhang, Fangquan Lin, Xu Jia, and Min Peng. 2025. One size doesn’t fit all: A personalized conversational tutoring agent for mathematics instruction. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 2401–2410, New York, NY, USA. Association for Computing Machin… find
  45. Naiming Liu, Shashank Sonkar, Zichao Wang, Simon Woodhead, and Richard G Baraniuk. 2023. Novice learner and expert tutor: Evaluating math reasoning abilities of large language models with misconceptions. arXiv preprint arXiv:2310.02439.
  46. Zhengyuan Liu, Stella Xin Yin, Geyu Lin, and Nancy F. Chen. 2024. Personality-aware student simulation for conversational intelligent tutoring systems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 626– 642, Miami, Florida, USA. Association for Comp… find
  47. Daria Martynova, Jakub Macina, Nico Daheim, Nilay Yalcin, Xiaoyu Zhang, and Mrinmaya Sachan. 2025. Can LLMs effectively simulate human learners? teachers’ insights from tutoring LLM students. In Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025… find
  48. Laura J. Massa and Richard E. Mayer. 2006. Testing the ati hypothesis: Should multimedia instruction accommodate verbalizer-visualizer cognitive style? Learning and Individual Differences, 16(4):321–335. find
  49. Kaushal Kumar Maurya, Kv Aditya Srivatsa, Kseniia Petukhova, and Ekaterina Kochmar. 2025. Unifying AI tutor evaluation: An evaluation taxonomy for pedagogical ability assessment of LLM-powered AI tutors. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association… find
  50. Robert R. McCrae and Paul T. Jr. Costa. 1999. A five-factor theory of personality. In Lawrence A. Pervin and Oliver P. John, editors, Handbook of Personality: Theory and Research, 2 edition, pages 139–153. Guilford Press. find
  51. Antonija Mitrovic, Stellan Ohlsson, and Devon K. Barrow. 2013. The effect of positive feedback in a constraint-based intelligent tutoring system. Computers & Education, 60(1):264–272. find
  52. Laurie Murphy, Nina B Eduljee, Karen Croteau, and Suzanne Parkman. 2017. Extraversion and introversion personality type and preferred teaching and classroom participation: A pilot study. Journal of Psychosocial Research, 12(2):437–450. find
  53. OpenAI. 2024. Gpt-4 technical report.
  54. OpenAI. 2025. Bring ai to campus at scale, accessed: 2025-05-14. find
  55. Sayantan Pal, Souvik Das, and Rohini K. Srihari. 2024. Beyond discrete personas: Personality modeling through journal intensive conversations. find
  56. Keyu Pan and Yawen Zeng. 2023. Do llms possess a personality? making the mbti test an amazing evaluation for large language models.
  57. Romain Puech, Jakub Macina, Julia Chatain, Mrinmaya Sachan, and Manu Kapur. 2025. Towards the pedagogical steering of large language models for tutoring: A case study with modeling productive failure. In Findings of the Association for Computational Linguistics: ACL 2025, pages 26291–26311, Vienna,… find
  58. Boele De Raad and Henri C. Schouwenburg. 1996. Personality in learning and education: a review. European Journal of Personality, 10(5):303–336. find
  59. Ayu Retny, I Ketut Agus Jayaputra, and Ni Made Rat-miningsih. 2017. The effect of role play technique and personality types on the speaking competency of the eleventh grade students of s wira harapan tegal-jaya. International Journal of Language and Literature, 1(2):121–132. find
  60. Jennifer Robison, Scott McQuiggan, and James Lester. 2010. Developing empirically based student personality profiles for affective feedback models. In Intelligent Tutoring Systems: 10th International Conference, ITS 2010, Pittsburgh, PA, USA, June 14-18, 2010, Proceedings, Part I 10, pages 285–295.… find
  61. Donya Rooein. 2019. Data-driven edu chatbots. In Companion Proceedings of The 2019 World Wide Web Conference, WWW ’19, page 46–49, New York, NY, USA. Association for Computing Machinery. find
  62. Donya Rooein, Devis Bianchini, Francesco Leotta, Massimo Mecella, Paolo Paolini, and Barbara Pernici. 2022. achat-wf: Generating conversational agents for teaching business process models. Software and Systems Modeling, pages 1–24. find
  63. Donya Rooein, Paul Röttger, Anastassia Shaitarova, and Dirk Hovy. 2024. Beyond flesch-kincaid: Prompt-based metrics improve difficulty classification of educational texts. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), pages 54–67, Mexi… find
  64. Barak Rosenshine. 2012. Principles of instruction: Research-based strategies that all teachers should know. American Educator, 36(1). find
  65. Alexander Scarlatos, Naiming Liu, Jaewook Lee, Richard Baraniuk, and Andrew Lan. 2025. Training LLM-Based Tutors to Improve Student Learning Outcomes in Dialogues, page 251–266. Springer Nature Switzerland. find
  66. Robin Schmucker, Meng Xia, Amos Azaria, and Tom Mitchell. 2024. Ruffle&riley: Insights from designing and evaluating a large language model-based conversational tutoring system. find
  67. Shashank Sonkar, Naiming Liu, Debshila Basu Mallick, and Richard G. Baraniuk. 2023. Class: A design framework for building intelligent tutoring systems based on learning science principles. find
  68. John Sweller. 1988. Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2):257–285. find
  69. Karl K Szpunar, Novall Y Khan, and Daniel L Schacter. 2013. Interpolated memory tests reduce mind wandering and improve learning of online lectures. Proceedings of the National Academy of Sciences, 110(16):6313–6317. find
  70. Robert P Tett, Margaret J Toich, and S Burak Ozkum. 2021. Trait activation theory: A review of the literature and applications to five lines of personality dynamics research. Annual Review of Organizational Psychology and Organizational Behavior, 8(1):199– 233. find
  71. Ahmed Tlili, Fathi Essalmi, Mohamed Jemni, Nian-Shing Chen, et al. 2016. Role of personality in computer based learning. Computers in Human Behavior, 64:805–813. find
  72. Janneke van de Pol, Monique Volman, and Jos Beishuizen. 2010. Scaffolding in teacher–student interaction: A decade of research. Educational Psychology Review, 22(3):271–296. find
  73. Teun A. van Dijk and Walter Kintsch. 1983. Strategies of discourse comprehension. Academic Press. find
  74. Kurt VanLehn, Brett van de Sande, Robert Shelby, and Sophia Gershman. 2010. The Andes Physics Tutoring System: An Experiment in Freedom, pages 421–443. Springer Berlin Heidelberg, Berlin, Heidelberg. find
  75. Alessandro Vanzo, Sankalan Pal Chowdhury, and Mrinmaya Sachan. 2024. Gpt-4 as a homework tutor can improve student engagement and learning outcomes. ArXiv, abs/2409.15981. find
  76. Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee-Peng Lim. 2023a. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:2305.04091. find
  77. Lingzhi Wang, Mrinmaya Sachan, Xingshan Zeng, and Kam-Fai Wong. 2023b. Strategize before teaching: A conversational tutoring system with pedagogy self-distillation. arXiv preprint arXiv:2302.13496. find
  78. Yixuan Weng, Shizhu He, Kang Liu, Shengping Liu, and Jun Zhao. 2024. Controllm: Crafting diverse personalities for language models. find
  79. Haein Yeo, Taehyeong Noh, Seungwan Jin, and Kyungsik Han. 2025. PADO: Personality-induced multi-agents for detecting OCEAN in human-generated texts. In Proceedings of the 31st International Conference on Computational Linguistics, pages 5719–5736, Abu Dhabi, UAE. Association for Computational Lingui… find
  80. Zheyuan Zhang, Daniel Zhang-Li, Jifan Yu, Linlu Gong, Jinchang Zhou, Zhanxin Hao, Jianxiao Jiang, Jie Cao, Huiqin Liu, Zhiyuan Liu, Lei Hou, and Juanzi Li. 2025. Simulating classroom education with LLM-empowered agents. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of…
  81. Barry J. Zimmerman and Anastasia Kitsantas. 2014. Comparing students’ self-discipline and self-regulation measures and their prediction of academic achievement. Contemporary Educational Psychology, 39(2):145–155. find
  82. Xiaoyi Zuo, LuLu Zhao, Yue Li, Wanting He, Chengfu Yu, and Zhenhai Wang. 2024. Psychological mechanisms of english academic stress and academic burnout: the mediating role of rumination and moderating effect of neuroticism. Frontiers in psychology, 15:1309210. find
  83. Thorsten Zylowski and Matthias Wölfel. 2023. An NLP analysis of ChatGPT‘s personality simulation capabilities and implications for human-centric explainable AI interfaces. In Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023), pages 168–177, Onlin… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rooein-2026-pats-personality-aware-teaching-strategies/