---
title: "Query-Focused Individual Simulation with Progressive Persona"
description: "The authors study a cold-start variant of this task. 27 references. Among them: 0."
authors: ["Weiwen SU", "Naoki Yoshinaga", "Masashi Toyoda"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1686/"
doi: "10.18653/v1/2026.findings-acl.1686"
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/su-2026-query-focused-individual-simulation-progressive/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/su-2026-query-focused-individual-simulation-progressive/)

[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/40/) / Query-Focused Individual Simulation with Progressive Persona Completion

# Query-Focused Individual Simulation with Progressive Persona Completion

**Authors:** [Weiwen SU](https://md.research.elamur.ai/free/en/authors/weiwen-su/), [Naoki Yoshinaga](https://md.research.elamur.ai/free/en/authors/naoki-yoshinaga/) and [Masashi Toyoda](https://md.research.elamur.ai/free/en/authors/masashi-toyoda/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.1686/) · [PDF](https://aclanthology.org/2026.findings-acl.1686.pdf) · [DOI 10.18653/v1/2026.findings-acl.1686](https://doi.org/10.18653/v1/2026.findings-acl.1686) · [OpenAlex](https://openalex.org/W7166849889)

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

## Summary

LLM-based simulators that predict how a specific person would answer usually rely on detailed profiles, which are rarely available for ordinary people. The authors study a cold-start variant of this task. Only a minimal persona (gender, age, relation to the asker) is known in advance. For each query, the system works out which additional traits matter and asks the requesting user to supply them.

Two strategies are compared. One requests a fixed set of predicted dimensions in a single round. The other is a progressive loop that asks for the single most important missing trait at each step and stops once the model's self-reported confidence indicates enough has been gathered. For reproducibility, the human informant is replaced by an LLM agent that reads the earlier dialogue between the two people.

On PICQ-drama and new queries drawn from the Nagoya University Conversation Corpus, a handful of query-specific traits (at most five) gives simulation quality on par with rich profiles extracted from dialogue history. The progressive variant needs even fewer requests while keeping or improving quality. This suggests personalization can be made cheaper and more practical.

## Key points

- Evaluation data: PICQ-drama (built from TVShowGuess scripts, with annotated choice questions and missing persona dimensions) plus newly extracted queries from NUCC. Code is released at github.com/NioHww/PICQ-simulation.
- Simulators and predictors include GPT-4.1 and Qwen3-32B. Each query comes with up to 20 turns of dialogue context, and baselines include context-only simulation and query-agnostic personas.
- Confidence-based stopping was compared with forcing five acquisition rounds. Collecting persona values past a certain point did not reliably improve quality.
- In a perturbation test, randomly deleting one acquired persona value consistently lowered quality. This indicates the collected traits genuinely contribute to the simulation.
- Clustering confidence trajectories with k-means (k = 3) revealed three patterns:
  - the most common, where confidence saturates within one or two steps;
  - gradual confidence growth;
  - a small group with persistently low or unstable confidence.

*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

- [The University of Tokyo](https://md.research.elamur.ai/free/en/universities/the-university-of-tokyo/) — University, Tokyo, Japan · 90 works · 9,156 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Weiwen SU, Naoki Yoshinaga and Masashi Toyoda. 2026. Query-Focused Individual Simulation with Progressive Persona Completion. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{su2026query,
  title = {{Query-Focused Individual Simulation with Progressive Persona Completion}},
  author = {Weiwen SU, Naoki Yoshinaga and Masashi Toyoda},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1686},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1686}
}
```

- [← previous QueerGen: How LLMs Reflect Societal Norms on Gender and Sexuality in Sentence Completion Task](https://md.research.elamur.ai/free/en/papers/sosto-2026-queergen-how-llms-reflect-societal/)
- [next → Question and Response Dynamics in Public Service Encounters](https://md.research.elamur.ai/free/en/papers/siskou-2026-question-response-dynamics-public-service/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/40/)

## References

27 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yun-Shiuan Chuang, Krirk Nirunwiroj, Zach Studdiford, Agam Goyal, Vincent V. Frigo, Sijia Yang, Dhavan V. Shah, Junjie Hu, and Timothy T. Rogers. 2024. Beyond demographics: Aligning role-playing LLM-based agents using human belief networks. In Findings of the Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Yun%2DShiuan+Chuang%2C+Krirk+Nirunwiroj%2C+Zach+Studdiford%2C+Agam+Goyal%2C+Vincent+V%2E+Frigo%2C+Sijia+Yang%2C+Dhavan+V%2E+Shah%2C+Junjie+Hu%2C+and+Timothy+T%2E+Rogers%2E+2024%2E+Beyond+demographics%3A+Aligning+role%2Dplaying+LLM%2Db)
2. Zhuoyun Du, Lujie Zheng, Renjun Hu, Yuyang Xu, Xiawei Li, Ying Sun, Wei Chen, Jian Wu, Haolei Cai, and Haochao Ying. 2025. [LLMs can simulate standardized patients via agent coevolution](https://md.research.elamur.ai/free/en/papers/du-2025-llms-can-simulate-standardized-patients/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)…
3. Itsuko Fujimura, Shoju Chiba, and Mieko Ohso. 2012. Lexical and grammatical features of spoken and written japanese in contrast: Exploring a lexical profiling approach to comparing spoken and written corpora. In Proceedings of the VIIth GSCP International Conference. Speech and Corpora, pages 393–39… [find](https://scholar.google.com/scholar?q=Itsuko+Fujimura%2C+Shoju+Chiba%2C+and+Mieko+Ohso%2E+2012%2E+Lexical+and+grammatical+features+of+spoken+and+written+japanese+in+contrast%3A+Exploring+a+lexical+profiling+approach+to+comparing+spoken+and+written+)
4. Silin Gao, Beatriz Borges, Soyoung Oh, Deniz Bayazit, Saya Kanno, Hiromi Wakaki, Yuki Mitsufuji, and Antoine Bosselut. 2023. PeaCoK: Persona commonsense knowledge for consistent and engaging narratives. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volum… [find](https://scholar.google.com/scholar?q=Silin+Gao%2C+Beatriz+Borges%2C+Soyoung+Oh%2C+Deniz+Bayazit%2C+Saya+Kanno%2C+Hiromi+Wakaki%2C+Yuki+Mitsufuji%2C+and+Antoine+Bosselut%2E+2023%2E+PeaCoK%3A+Persona+commonsense+knowledge+for+consistent+and+engaging+narrative)
5. Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu. 2025. [Scaling synthetic data creation with 1,000,000,000 personas](https://md.research.elamur.ai/free/en/papers/ge-2024-scaling-synthetic-data-creation-1/). Preprint, arXiv:2406.20094.
6. Tiancheng Hu and Nigel Collier. 2024. [Quantifying the persona effect in LLM simulations](https://md.research.elamur.ai/free/en/papers/hu-2024-quantifying-persona-effect-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.
7. Zhengyu Hu, Jianxun Lian, Zheyuan Xiao, Max Xiong, Yuxuan Lei, Tianfu Wang, Kaize Ding, Ziang Xiao, Nicholas Jing Yuan, and Xing Xie. 2025. Population-aligned persona generation for LLM-based social simulation. Preprint, arXiv:2509.10127. — [arXiv:2509.10127](https://arxiv.org/abs/2509.10127) [find](https://scholar.google.com/scholar?q=Zhengyu+Hu%2C+Jianxun+Lian%2C+Zheyuan+Xiao%2C+Max+Xiong%2C+Yuxuan+Lei%2C+Tianfu+Wang%2C+Kaize+Ding%2C+Ziang+Xiao%2C+Nicholas+Jing+Yuan%2C+and+Xing+Xie%2E+2025%2E+Population%2Daligned+persona+generation+for+LLM%2Dbased+social+s)
8. Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, and Xiaohang Dong. 2024. Better zero-shot reasoning with role-play prompting. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language… [find](https://scholar.google.com/scholar?q=Aobo+Kong%2C+Shiwan+Zhao%2C+Hao+Chen%2C+Qicheng+Li%2C+Yong+Qin%2C+Ruiqi+Sun%2C+Xin+Zhou%2C+Enzhi+Wang%2C+and+Xiaohang+Dong%2E+2024%2E+Better+zero%2Dshot+reasoning+with+role%2Dplay+prompting%2E+In+Proceedings+of+the+2024+Confer)
9. Ang Li, Haozhe Chen, Hongseok Namkoong, and Tianyi Peng. 2025. LLM generated persona is a promise with a catch. In First Workshop on Social Simulation with LLMs. [find](https://scholar.google.com/scholar?q=Ang+Li%2C+Haozhe+Chen%2C+Hongseok+Namkoong%2C+and+Tianyi+Peng%2E+2025%2E+LLM+generated+persona+is+a+promise+with+a+catch%2E+In+First+Workshop+on+Social+Simulation+with+LLMs%2E)
10. Man Tik Ng, Hui Tung Tse, Jen tse Huang, Jingjing Li, Wenxuan Wang, and Michael R. Lyu. 2024. How well can LLMs echo us? evaluating AI chatbots’ role-play ability with ECHO. Preprint, arXiv:2404.13957. — [arXiv:2404.13957](https://arxiv.org/abs/2404.13957) [find](https://scholar.google.com/scholar?q=Man+Tik+Ng%2C+Hui+Tung+Tse%2C+Jen+tse+Huang%2C+Jingjing+Li%2C+Wenxuan+Wang%2C+and+Michael+R%2E+Lyu%2E+2024%2E+How+well+can+LLMs+echo+us%3F+evaluating+AI+chatbots%E2%80%99+role%2Dplay+ability+with+ECHO%2E+Preprint%2C+arXiv%3A2404%2E13957)
11. OpenAI. 2024. [GPT-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv:2303.08774.
12. Preprint, Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S. Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, UIST ’23, New York, NY… [find](https://scholar.google.com/scholar?q=Preprint%2C+Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S%2E+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceeding)
13. Joon Sung Park, Carolyn Q. Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, and Michael S. Bernstein. 2024. Generative agent simulations of 1,000 people. Preprint, arXiv:2411.10109. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Carolyn+Q%2E+Zou%2C+Aaron+Shaw%2C+Benjamin+Mako+Hill%2C+Carrie+Cai%2C+Meredith+Ringel+Morris%2C+Robb+Willer%2C+Percy+Liang%2C+and+Michael+S%2E+Bernstein%2E+2024%2E+Generative+agent+simulations+of+1%2C000+peop)
14. QwenTeam. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
15. Yiting Ran, Xintao Wang, Rui Xu, Xinfeng Yuan, Jiaqing Liang, Yanghua Xiao, and Deqing Yang. 2024. Capturing minds, not just words: Enhancing role-playing language models with personality-indicative data. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14566– 14576, M… [find](https://scholar.google.com/scholar?q=Yiting+Ran%2C+Xintao+Wang%2C+Rui+Xu%2C+Xinfeng+Yuan%2C+Jiaqing+Liang%2C+Yanghua+Xiao%2C+and+Deqing+Yang%2E+2024%2E+Capturing+minds%2C+not+just+words%3A+Enhancing+role%2Dplaying+language+models+with+personality%2Dindicative+d)
16. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
17. Yisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, and Jeffrey Stanton. 2022. TVShowGuess: Character comprehension in stories as speaker guessing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pag… [find](https://scholar.google.com/scholar?q=Yisi+Sang%2C+Xiangyang+Mou%2C+Mo+Yu%2C+Shunyu+Yao%2C+Jing+Li%2C+and+Jeffrey+Stanton%2E+2022%2E+TVShowGuess%3A+Character+comprehension+in+stories+as+speaker+guessing%2E+In+Proceedings+of+the+2022+Conference+of+the+North)
18. Shoetsu Sato, Naoki Yoshinaga, Masashi Toyoda, and Masaru Kitsuregawa. 2017. Modeling situations in neural chat bots. In Proceedings of ACL 2017, Student Research Workshop, pages 120–127, Vancouver, Canada. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shoetsu+Sato%2C+Naoki+Yoshinaga%2C+Masashi+Toyoda%2C+and+Masaru+Kitsuregawa%2E+2017%2E+Modeling+situations+in+neural+chat+bots%2E+In+Proceedings+of+ACL+2017%2C+Student+Research+Workshop%2C+pages+120%E2%80%93127%2C+Vancouver%2C+C)
19. Yunfan Shao, Linyang Li, Junqi Dai, and Xipeng Qiu. 2023. [Character-LLM: A trainable agent for role-playing](https://md.research.elamur.ai/free/en/papers/shao-2023-character-llm-trainable-agent-role/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13153–13187, Singapore. Association for Computational Linguistics.
20. Weiwen Su, Yuhan Zhou, Zihan Wang, Naoki Yoshinaga, and Masashi Toyoda. 2026. [Is he extroverted? identifying missing relevant personas for faithful user simulation](https://md.research.elamur.ai/free/en/papers/su-2026-is-he-extroverted-identifying-missing/). In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Resea…
21. Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, and Christopher Manning. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. In Proceedings of the 2023 Conferen… [find](https://scholar.google.com/scholar?q=Katherine+Tian%2C+Eric+Mitchell%2C+Allan+Zhou%2C+Archit+Sharma%2C+Rafael+Rafailov%2C+Huaxiu+Yao%2C+Chelsea+Finn%2C+and+Christopher+Manning%2E+2023%2E+Just+ask+for+calibration%3A+Strategies+for+eliciting+calibrated+confid)
22. Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, and Junran Peng. 2024. [RoleLLM: Benchmarking, eliciting, and enhancing role-playing abilities of large la…](https://md.research.elamur.ai/free/en/papers/wang-2023-rolellm-benchmarking-eliciting-enhancing-role/)
23. Tao Wu, Jingyuan Chen, Wang Lin, Mengze Li, Yumeng Zhu, Ang Li, Kun Kuang, and Fei Wu. 2025. [Embracing imperfection: Simulating students with diverse cognitive levels using LLM-based agents](https://md.research.elamur.ai/free/en/papers/wu-2025-embracing-imperfection-simulating-students-diverse/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa…
24. Miao Xiong, Zhiyuan Hu, Xinyang Lu, YIFEI LI, Jie Fu, Junxian He, and Bryan Hooi. 2024. Can LLMs express their uncertainty? an empirical evaluation of confidence elicitation in LLMs. In International Conference on Learning Representations, volume 2024, pages 23650–23678. [find](https://scholar.google.com/scholar?q=Miao+Xiong%2C+Zhiyuan+Hu%2C+Xinyang+Lu%2C+YIFEI+LI%2C+Jie+Fu%2C+Junxian+He%2C+and+Bryan+Hooi%2E+2024%2E+Can+LLMs+express+their+uncertainty%3F+an+empirical+evaluation+of+confidence+elicitation+in+LLMs%2E+In+International+)
25. Xinfeng Yuan, Siyu Yuan, Yuhan Cui, Tianhe Lin, Xintao Wang, Rui Xu, Jiangjie Chen, and Deqing Yang. 2024. Evaluating character understanding of large language models via character profiling from fictional works. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processi… [find](https://scholar.google.com/scholar?q=Xinfeng+Yuan%2C+Siyu+Yuan%2C+Yuhan+Cui%2C+Tianhe+Lin%2C+Xintao+Wang%2C+Rui+Xu%2C+Jiangjie+Chen%2C+and+Deqing+Yang%2E+2024%2E+Evaluating+character+understanding+of+large+language+models+via+character+profiling+from+fict)
26. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. [Personalizing dialogue agents: I have a dog, do you have pets too?](https://md.research.elamur.ai/free/en/papers/zhang-2018-personalizing-dialogue-agents-i-have/) In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204–2213, Melbou…
27. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025. GA-S 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8950–8970, Vienna, Austria. Association for Computa… [find](https://scholar.google.com/scholar?q=Yunyao+Zhang%2C+Zikai+Song%2C+Hang+Zhou%2C+Wenfeng+Ren%2C+Yi%2DPing+Phoebe+Chen%2C+Junqing+Yu%2C+and+Wei+Yang%2E+2025%2E+GA%2DS+3+%3A+Comprehensive+social+network+simulation+with+group+agents%2E+In+Findings+of+the+Associatio)

*Updated 1 November 2026*