Elamur Research⌕
☰
home / papers / 2026 / AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment

AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment

Paper · 2026 · Yixuan Wang, Yue Huang, Hong Qian et al.

Summary

Context-based tests are an established way to measure human creative thinking. Future-oriented problem scenarios in the tradition of the Future Problem Solving Program are a common example. Writing such long-form contexts is slow expert work. Plain LLM prompting tends to produce texts with too few embedded assessment cues, weak coherence and little stylistic variety.

AlphaContext automates this design process in four stages:

  • HyperTree Outline Planner: encodes expert outlining rules as a hypertree and plans the outline top-down.
  • MCTS-based Context Generator: fills the outline sentence by sentence, balancing overall structure against local text quality.
  • Evolutionary Context Optimizer: applies MAP-Elites to build an archive of varied, high-quality versions.
  • Assessment-Guided Evolution Refiner: simulates participants with different answering styles and returns weak contexts for further evolution.

Inputs are title–theme pairs written by experts (the CreaTE dataset). The system outperforms strong LLM and structured baselines by roughly 8% on average and aligns more closely with expert-designed contexts. A real-world human study supports its practical validity. This gives a scalable source of assessment material for testing both people and LLMs.

Key points

  • The pipeline follows a plan–generate–evolve scheme combining a rule-guided hypertree, sentence-level MCTS, MAP-Elites quality–diversity search and virtual-participant refinement.

  • The reported average improvement is about 8% across 6 quality metrics (abstract), while the conclusion mentions 7 evaluation dimensions. Human–LLM preference agreement is used to justify automated judging.

  • Cost per context:

    MethodTime (s)Tokens (k)
    AlphaContext226.99 (~6 min)12.89
    Gemini-3.0-Pro-Preview46.313.29
    GPT-5.123.502.36

    Manual expert design takes at least a week. AlphaContext runs on a locally deployed open-source model.

  • New resource: CreaTE, a set of expert-authored title–theme inputs containing no personal data. The human validation study was IRB-approved (HR2-0478-2025), with consent from participants and guardians.

  • Limitations: the work covers only future-oriented contexts and a small curated input set. Planned extensions include other domains, age groups and languages, plus distilling the system into lightweight generators.

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

🎓East China Normal UniversityShanghai · China50 works · 2,174 citations🎓Shanghai Innovation InstituteShanghai · China24 works · 262 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPsychology · 1,552 worksExperimental and Cognitive Psychology · 870 works

Cite

Cite as Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou and Jiajun Guo. 2026. AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment. 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. DOI 10.18653/v1/2026.acl-long.1261

@inproceedings{wang2026alphacontext,
  title = {{AlphaContext: An Evolutionary Tree-based Psychometric Context Generator for Creativity Assessment}},
  author = {Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou and Jiajun Guo},
  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.1261},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1261}
}

References

40 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. T.M. Amabile. 1983. The social psychology of creativity: A componential conceptualization. Journal of Personality and Social Psychology, 45(2):357. find
  2. T.M. Amabile. 2018. Creativity in context: Update to the social psychology of creativity. Routledge. find
  3. Minwook Bae and Hyounghun Kim. 2024. Collective critics for creative story generation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18784–18819, Miami, FL, USA. find
  4. Yushi Bai, Jiajie Zhang, Xin Lv, Linzhi Zheng, Siqi Zhu, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2025. Longwriter: Unleashing 10,000+ word generation from long context llms. In Proceedings of the 13th International Conference on Learning Representations, Singapore.
  5. B. Barbot, R.W. Hass, and R. Reiter-Palmon. 2019a. Creativity assessment in psychological research:(re) setting the standards. Psychology of Aesthetics, Creativity, and the Arts, 13(2):233. find
  6. Baptiste Barbot, Richard W Hass, and Roni Reiter-Palmon. 2019b. Creativity assessment in psychological research:(re)setting the standards. Psychology of Aesthetics, Creativity, and the Arts, 13(2):233. find
  7. R.E. Beaty and D.R. Johnson. 2021. Automating creativity assessment with semdis: An open platform for computing semantic distance. Behavior Research Methods, 53(2):757–780. find
  8. R.E. Beaty, D.R. Johnson, D.C. Zeitlen, and B. Forth-mann. 2022. Semantic distance and the alternate uses task: Recommendations for reliable automated assessment of originality. Creativity Research Journal, 34(3):245–260. find
  9. Ronald A Beghetto. 2021. There is no creativity without uncertainty: Dubito ergo creo. Journal of Creativity, 31:100005. find
  10. Ronald A Beghetto and Garrett J Jaeger. 2022. Uncertainty: A catalyst for creativity, learning and development. Creativity Theory and Action in Education, 6. find
  11. M. Benedek, C. Mühlmann, E. Jauk, and A.C. Neubauer. 2013. Assessment of divergent thinking by means of the subjective top-scoring method: Effects of the number of top-ideas and time-on-task on reliability and validity. Psychology of Aesthetics, Creativity, and the Arts, 7(4):341. find
  12. Jérôme Guegan, Julien Nelson, and Todd Lubart. 2017. The relationship between contextual cues in virtual environments and creative processes. Cyberpsychology, Behavior, and Social Networking, 20(3):202– 206. find
  13. Jiajun Guo and Sarah Woulfin. 2016. Twenty-first century creativity: An investigation of how the partnership for 21st century instructional framework reflects the principles of creativity. Roeper Review, 38(3):153–161. find
  14. Antonio Laverghetta Jr., Simone Luchini, Averie Lin-nell, Roni Reiter-Palmon, and Roger E. Beaty. 2024. The creative psychometric item generator: a framework for item generation and validation using large language models. In Proceedings of the 3rd Workshop on Artificial Intelligence and Creativity c… find
  15. Brandon Koh and Angela K-y Leung. 2019. A time for creativity: How future-oriented schemas facilitate creativity. Journal of Experimental Social Psychology, 84:103816. find
  16. A.B. Crabbe. 1989. The future problem solving program. Educational Leadership, 7(1):27–29. find
  17. Hye-Kyung Lee. 2022. Rethinking creativity: Creative industries, ai and everyday creativity. Media, Culture & Society, 44(3):601–612. find
  18. Anne Borland Crabbe. 1982. Creating a brighter future: An update on the future problem solving program. Journal for the Education of the Gifted, 5(1):2–11. find
  19. Kuang-Huei Lee, Ian Fischer, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, and Xinyun Chen. 2025. Evolving deeper LLM thinking. arXiv preprint, arXiv:2501.09891. find
  20. Angela Fan, Mike Lewis, and Yann N. Dauphin. 2019. Strategies for structuring story generation. In Proceedings of the 57th Conference of the Association for Computational Linguistics, pages 2650–2660, Florence, Italy. find
  21. Xinyu Fang, Zhijian Chen, Kai Lan, Lixin Ma, Shengyuan Ding, Yingji Liang, Xiangyu Zhao, Farong Wen, Zicheng Zhang, Guofeng Zhang, Haodong Duan, Kai Chen, and Dahua Lin. 2025. Creation-mmbench: Assessing context-aware creative intelligence in MLLM. arXiv preprint, abs/2503.14478. — [arXiv:2503.14478](https://arxiv.org/abs/2503.14478) find
  22. Yi Feng, Mingyang Song, Jiaqi Wang, Zhuang Chen, Guanqun Bi, Minlie Huang, Liping Jing, and Jian Yu. 2025. SS-GEN: A social story generation framework with large language models. In AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, pages 1300–1308, Philadelphia, P… find
  23. D.C. Funder and D.J. Ozer. 2019. Evaluating effect size in psychological research: Sense and nonsense. Advances in Methods and Practices in Psychological Science, 2(2):156–168. find
  24. G.E. Gignac and E.T. Szodorai. 2016. Effect size guidelines for individual differences researchers. Personality and Individual Differences, 102:74–78. find
  25. Jiaming Li, Yukun Chen, Ziqiang Liu, Minghuan Tan, Lei Zhang, Yunshui Li, Run Luo, Longze Chen, Jing Luo, Ahmadreza Argha, Hamid Alinejad-Rokny, Wei Zhou, and Min Yang. 2025a. STORYTELLER: an enhanced plot-planning framework for coherent and cohesive story generation. In Findings of the Association… find
  26. Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E. Gonzalez, and Ion Stoica. 2025b. From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline. In Forty-second International Conference on Machine Learning, Vancouver, BC, Canada.
  27. Luchini, Simone A, Maliakkal, Nadine T, DiStefano, Paul V, Laverghetta Jr, Antonio, Patterson, John D, Beaty, Roger E, and Roni Reiter-Palmon. 2025. Automated scoring of creative problem solving with large language models: A comparison of originality and quality ratings. Psychology of Aesthetics, Cr… find
  28. Aidan Mclaughlin, James Campbell, Anuja Uppuluri, and Yiming Yang. 2024. Aidanbench: Stress-testing language model creativity on open-ended questions. In NeurIPS 2024 Workshop on Language Gamification. find
  29. Peter Meusburger. 2009. Milieus of creativity: The role of places, environments, and spatial contexts. Milieus of creativity: An interdisciplinary approach to spatiality of creativity, 2:97–153. find
  30. Michael D Mumford, Robert Martin, Samantha Elliott, and Tristan McIntosh. 2018. Creative thinking in the real world. The nature of human creativity, pages 147–65. find
  31. Alexander Novikov, Ngân Vu, Marvin Eisenberger, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, Sergey Shirobokov, Borislav Kozlovskii, Francisco J. R. Ruiz, Abbas Mehrabian, M. Pawan Kumar, Abigail See, Swarat Chaudhuri, George Holland, Alex Davies, Sebastian Nowozin, Pushmeet Kohli, and Matej Bal… — AlphaEvolve: A coding agent for scientific and algorithmic discovery
  32. Shawn M Okuda, Mark A Runco, and Dale E Berger. 1991. Creativity and the finding and solving of real-world problems. Journal of Psychoeducational assessment, 9(1):45–53. find
  33. Kai Ruan, Xuan Wang, Jixiang Hong, and Hao Sun. 2024. Liveideabench: Evaluating llms’ scientific creativity and idea generation with minimal context. arXiv e-prints, pages arXiv–2412. find
  34. M.A. Runco and S. Acar. 2012. Divergent thinking as an indicator of creative potential. Creativity Research Journal, 24(1):66–75. find
  35. Xueyang Wang, Wei Liu, Kaixiang Zhuang, Cheng Liu, Jingyi Zhang, Li Fan, Qunlin Chen, and Jiang Qiu. 2025a. Neural representations of noncen-tral events during narrative encoding predict subsequent story ending originality. Science Advances, 11(17):eadu5251. find
  36. Yixuan Wang, Jiale Feng, Yue Huang, Xuruo Pan, Zhongjing Huang, Zhi Liu, and Hong Qian. 2025b. A style-aware polytomous diagnostic model for individual traits. In Proceedings of the 28th European Conference on Artificial Intelligence, pages 2698– 2705, Bologna, Italy. find
  37. Hongqiu Wu, Weiqi Wu, Tianyang Xu, Jiameng Zhang, and Hai Zhao. 2025a. Towards enhanced immersion and agency for llm-based interactive drama. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, pages 11166– 11182, Vienna, Austria. find
  38. Shirley Wu, Michel Galley, Baolin Peng, Hao Cheng, Gavin Li, Yao Dou, Weixin Cai, James Zou, Jure Leskovec, and Jianfeng Gao. 2025b. Collabllm: From passive responders to active collaborators. In Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. find
  39. Kevin Yang, Dan Klein, Nanyun Peng, and Yuandong Tian. 2023. DOC: improving long story coherence with detailed outline control. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, pages 3378–3465, Toronto, Canada.
  40. Mark A Runco and Garrett J Jaeger. 2012. The standard definition of creativity. Creativity research journal, 24(1):92–96. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-alphacontext-evolutionary-tree-based-psychometric/