---
title: "Graph-Based Alternatives to LLMs for Human Simulation (2026)"
description: "They propose GEMS (Graph-basEd Models for Human Simulation), which treats the task as link prediction on a… 95 references."
authors: ["Joseph Suh", "Suhong Moon", "Serina Chang"]
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.2157/"
doi: "10.18653/v1/2026.acl-long.2157"
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/suh-2026-graph-based-alternatives-llms-human/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/suh-2026-graph-based-alternatives-llms-human/)

[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/31/) / Graph-Based Alternatives to LLMs for Human Simulation

# Graph-Based Alternatives to LLMs for Human Simulation

**Authors:** [Joseph Suh](https://md.research.elamur.ai/free/en/authors/joseph-suh/), [Suhong Moon](https://md.research.elamur.ai/free/en/authors/suhong-moon/) and [Serina Chang](https://md.research.elamur.ai/free/en/authors/serina-y-chang/) · **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.2157/) · [PDF](https://aclanthology.org/2026.acl-long.2157.pdf) · [DOI 10.18653/v1/2026.acl-long.2157](https://doi.org/10.18653/v1/2026.acl-long.2157) · [OpenAlex](https://openalex.org/W7166829756)

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

## Summary
Most work on simulating human behaviour relies on large language models, even when a person only picks one answer from a fixed list, as with a poll item or a test question. The authors ask whether such close-ended simulation actually needs an LLM. They propose GEMS (Graph-basEd Models for Human Simulation), which treats the task as link prediction on a heterogeneous graph. Its nodes are demographic subgroups, individuals and question–option "choices", connected by membership and response edges. A heterogeneous GNN encoder (variants of RGCN, GAT, GraphSAGE) learns node embeddings, and a dot-product decoder with a softmax over a question's options ranks the candidate answers. For questions never seen in training, a small learned projection maps frozen LLM representations of the choice text into the GNN embedding space. GEMS was tested on OpinionQA, Twin-2K and a grammar-skills test dataset against prompted and fine-tuned LLMs. It equals or beats the strongest baselines while using about a thousand times fewer parameters. This makes human simulation cheaper, more transparent and less exposed to pretraining leakage and bias.

## Key points
- **Three evaluation settings:** imputing missing responses, predicting answers of new individuals, and predicting answers to new questions.
- **Use of text representations:** the first two settings need no language representations at all. Only the new-question setting uses the LLM-to-GNN projection (after Sheng et al., 2025).
- **Baselines:** zero-shot, few-shot, chain-of-thought prompting and supervised fine-tuning of LLMs up to roughly 10B parameters.
- **Efficiency:** GEMS needs about 10³ fewer parameters and up to 10² less compute than the LLM baselines.
- **Data and limitations:** Three datasets are used: OpinionQA (Santurkar et al., 2023), Twin-2K (Toubia et al., 2025), and a grammar-test replication of the Dunning-Kruger effect that draws on Jansen et al. (2021) and Binz et al. (2025). All participants are US-based, so other languages and countries remain untested. Code is available at github.com/schang-lab/gems.

*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 California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) — University, Berkeley, United States · 175 works · 227,440 citations

📚 Shelves (5): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Joseph Suh, Suhong Moon and Serina Chang. 2026. Graph-Based Alternatives to LLMs for Human Simulation. 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{suh2026graph,
  title = {{Graph-Based Alternatives to LLMs for Human Simulation}},
  author = {Joseph Suh, Suhong Moon and Serina Chang},
  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.2157},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2157}
}
```

- [← previous Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations](https://md.research.elamur.ai/free/en/papers/luo-2026-graph-assisted-large-language-models/)
- [next → Graph-Based Phonetic Error Correction of Noisy ASR](https://md.research.elamur.ai/free/en/papers/singh-2026-graph-based-phonetic-error-correction/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/31/)

## References

95 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pew Research Center. 2024. Issues and the 2024 election. [https://www.pewresearch.org/politics/](https://www.pewresearch.org/politics/) 2024/09/09/issues-and-the-2024-election/. Accessed: 2026-01-06. [↗](https://www.pewresearch.org/politics/)
2. Anastasios N Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I Jordan, and Tijana Zrnic. 2023. Prediction-powered inference. Science, 382(6671):669–674. [find](https://scholar.google.com/scholar?q=Anastasios+N+Angelopoulos%2C+Stephen+Bates%2C+Clara+Fannjiang%2C+Michael+I+Jordan%2C+and+Tijana+Zrnic%2E+2023%2E+Prediction%2Dpowered+inference%2E+Science%2C+382%286671%29%3A669%E2%80%93674%2E)
3. Jacy Reese Anthis, Ryan Liu, Sean M Richardson, Austin C Kozlowski, Bernard Koch, James Evans, Erik Brynjolfsson, and Michael Bernstein. 2025. Llm social simulations are a promising research method. arXiv preprint arXiv:2504.02234. — [arXiv:2504.02234](https://arxiv.org/abs/2504.02234) [find](https://scholar.google.com/scholar?q=Jacy+Reese+Anthis%2C+Ryan+Liu%2C+Sean+M+Richardson%2C+Austin+C+Kozlowski%2C+Bernard+Koch%2C+James+Evans%2C+Erik+Brynjolfsson%2C+and+Michael+Bernstein%2E+2025%2E+Llm+social+simulations+are+a+promising+research+method%2E+a)
4. Artificial Societies Artificial Societies. 2025. Artificial societies — company profile. [https://www.ycombinator.com/companies/](https://www.ycombinator.com/companies/) artificial-societies. Accessed: 2025-09-21. [↗](https://www.ycombinator.com/companies/)
5. Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. [Layer normalization](https://md.research.elamur.ai/free/en/papers/ba-2016-layer-normalization/). arXiv preprint arXiv:1607.06450.
6. Peter W Battaglia, Jessica B Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez, Vinicius Zambaldi, Mateusz Malinowski, Andrea Tacchetti, David Raposo, Adam Santoro, Ryan Faulkner, et al. 2018. [Relational inductive biases, deep learning, and graph networks](https://md.research.elamur.ai/free/en/papers/battaglia-2018-relational-inductive-biases-deep-learning/). arXiv preprint arXiv:1806.01261.
7. Moshe Ben-Akiva, Joan Walker, Adriana T Bernardino, Dinesh A Gopinath, Taka Morikawa, and Amalia Polydoropoulou. 2002. Integration of choice and latent variable models. Perpetual motion: Travel behaviour research opportunities and application challenges, 2002:431–470. [find](https://scholar.google.com/scholar?q=Moshe+Ben%2DAkiva%2C+Joan+Walker%2C+Adriana+T+Bernardino%2C+Dinesh+A+Gopinath%2C+Taka+Morikawa%2C+and+Amalia+Polydoropoulou%2E+2002%2E+Integration+of+choice+and+latent+variable+models%2E+Perpetual+motion%3A+Travel+behavi)
8. Rianne van den Berg, Thomas N Kipf, and Max Welling. 2017. Graph convolutional matrix completion. arXiv preprint arXiv:1706.02263. [find](https://scholar.google.com/scholar?q=Rianne+van+den+Berg%2C+Thomas+N+Kipf%2C+and+Max+Welling%2E+2017%2E+Graph+convolutional+matrix+completion%2E+arXiv+preprint+arXiv%3A1706%2E02263%2E)
9. Federico Bianchi, Patrick John Chia, Mert Yuksekgonul, Jacopo Tagliabue, Dan Jurafsky, and James Zou. 2024. How well can llms negotiate? negotiationarena platform and analysis. arXiv preprint arXiv:2402.05863. [find](https://scholar.google.com/scholar?q=Federico+Bianchi%2C+Patrick+John+Chia%2C+Mert+Yuksekgonul%2C+Jacopo+Tagliabue%2C+Dan+Jurafsky%2C+and+James+Zou%2E+2024%2E+How+well+can+llms+negotiate%3F+negotiationarena+platform+and+analysis%2E+arXiv+preprint+arXiv%3A24)
10. Marcel Binz, Elif Akata, Matthias Bethge, Franziska Brändle, Fred Callaway, Julian Coda-Forno, Peter Dayan, Can Demircan, Maria K Eckstein, Noémi Éltető, et al. 2025. A foundation model to predict and capture human cognition. Nature, pages 1–8. [find](https://scholar.google.com/scholar?q=Marcel+Binz%2C+Elif+Akata%2C+Matthias+Bethge%2C+Franziska+Br%C3%A4ndle%2C+Fred+Callaway%2C+Julian+Coda%2DForno%2C+Peter+Dayan%2C+Can+Demircan%2C+Maria+K+Eckstein%2C+No%C3%A9mi+%C3%89lteto%CC%8B%2C+et+al%2E+2025%2E+A+foundation+model+to+predict+an)
11. James Bisbee, Joshua D. Clinton, Cassy Dorff, Brenton Kenkel, and Jennifer M. Larson. 2024. Synthetic replacements for human survey data? the perils of large language models. Political Analysis. [find](https://scholar.google.com/scholar?q=James+Bisbee%2C+Joshua+D%2E+Clinton%2C+Cassy+Dorff%2C+Brenton+Kenkel%2C+and+Jennifer+M%2E+Larson%2E+2024%2E+Synthetic+replacements+for+human+survey+data%3F+the+perils+of+large+language+models%2E+Political+Analysis%2E)
12. Runjin Chen, Tong Zhao, Ajay Jaiswal, Neil Shah, and Zhangyang Wang. 2024. Llaga: Large language and graph assistant. arXiv preprint arXiv:2402.08170. — [arXiv:2402.08170](https://arxiv.org/abs/2402.08170) [find](https://scholar.google.com/scholar?q=Runjin+Chen%2C+Tong+Zhao%2C+Ajay+Jaiswal%2C+Neil+Shah%2C+and+Zhangyang+Wang%2E+2024%2E+Llaga%3A+Large+language+and+graph+assistant%2E+arXiv+preprint+arXiv%3A2402%2E08170%2E+%E2%80%94+%5BarXiv%3A2402%2E08170%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E0)
13. Myra Cheng, Tiziano Piccardi, and Diyi Yang. 2023. Compost: Characterizing and evaluating caricature in llm simulations. In EMNLP. [find](https://scholar.google.com/scholar?q=Myra+Cheng%2C+Tiziano+Piccardi%2C+and+Diyi+Yang%2E+2023%2E+Compost%3A+Characterizing+and+evaluating+caricature+in+llm+simulations%2E+In+EMNLP%2E)
14. Eric Chu, Jacob Andreas, Stephen Ansolabehere, and Deb Roy. 2023. Language models trained on media diets can predict public opinion. arXiv preprint arXiv:2303.16779. — [arXiv:2303.16779](https://arxiv.org/abs/2303.16779) [find](https://scholar.google.com/scholar?q=Eric+Chu%2C+Jacob+Andreas%2C+Stephen+Ansolabehere%2C+and+Deb+Roy%2E+2023%2E+Language+models+trained+on+media+diets+can+predict+public+opinion%2E+arXiv+preprint+arXiv%3A2303%2E16779%2E+%E2%80%94+%5BarXiv%3A2303%2E16779%5D%28https%3A%2F%2Farxiv)
15. Chunyuan Deng, Yilun Zhao, Yuzhao Heng, Yitong Li, Jiannan Cao, Xiangru Tang, and Arman Cohan. 2024. Unveiling the spectrum of data contamination in language models: A survey from detection to remediation. arXiv preprint arXiv:2406.14644. — [arXiv:2406.14644](https://arxiv.org/abs/2406.14644) [find](https://scholar.google.com/scholar?q=Chunyuan+Deng%2C+Yilun+Zhao%2C+Yuzhao+Heng%2C+Yitong+Li%2C+Jiannan+Cao%2C+Xiangru+Tang%2C+and+Arman+Cohan%2E+2024%2E+Unveiling+the+spectrum+of+data+contamination+in+language+models%3A+A+survey+from+detection+to+remedia)
16. Ricardo Dominguez-Olmedo, Moritz Hardt, and Celestine Mendler-Dünner. 2023. Questioning the survey responses of large language models. arXiv preprint arXiv:2306.07951. — [arXiv:2306.07951](https://arxiv.org/abs/2306.07951) [find](https://scholar.google.com/scholar?q=Ricardo+Dominguez%2DOlmedo%2C+Moritz+Hardt%2C+and+Celestine+Mendler%2DD%C3%BCnner%2E+2023%2E+Questioning+the+survey+responses+of+large+language+models%2E+arXiv+preprint+arXiv%3A2306%2E07951%2E+%E2%80%94+%5BarXiv%3A2306%2E07951%5D%28https%3A%2F%2Farx)
17. 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](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
18. Expected Parrot Expected Parrot. 2025. Expected parrot. [https://www.expectedparrot.com/](https://www.expectedparrot.com/). Accessed: 2025-09-21. [↗](https://www.expectedparrot.com/)
19. Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In The world wide web conference, pages 417–426. [find](https://scholar.google.com/scholar?q=Wenqi+Fan%2C+Yao+Ma%2C+Qing+Li%2C+Yuan+He%2C+Eric+Zhao%2C+Jiliang+Tang%2C+and+Dawei+Yin%2E+2019%2E+Graph+neural+networks+for+social+recommendation%2E+In+The+world+wide+web+conference%2C+pages+417%E2%80%93426%2E)
20. Shangbin Feng, Taylor Sorensen, Yuhan Liu, Jillian Fisher, Chan Young Park, Yejin Choi, and Yulia Tsvetkov. 2024. [Modular pluralism: Pluralistic alignment via multi-LLM collaboration](https://md.research.elamur.ai/free/en/papers/feng-2024-modular-pluralism-pluralistic-alignment-multi/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4151–4171.
21. Matthias Fey and Jan Eric Lenssen. 2019. [Fast graph representation learning with pytorch geometric](https://md.research.elamur.ai/free/en/papers/fey-2019-fast-graph-representation-learning-pytorch/). arXiv preprint arXiv:1903.02428.
22. Chen Gao, Xiaochong Lan, Nian Li, Yuan Yuan, Jingtao Ding, Zhilun Zhou, Fengli Xu, and Yong Li. 2024. Large language models empowered agent-based modeling and simulation: a survey and perspectives. Humanities and Social Sciences Communications, 11(1259). [find](https://scholar.google.com/scholar?q=Chen+Gao%2C+Xiaochong+Lan%2C+Nian+Li%2C+Yuan+Yuan%2C+Jingtao+Ding%2C+Zhilun+Zhou%2C+Fengli+Xu%2C+and+Yong+Li%2E+2024%2E+Large+language+models+empowered+agent%2Dbased+modeling+and+simulation%3A+a+survey+and+perspectives%2E+Hu)
23. William H Greene and David A Hensher. 2003. A latent class model for discrete choice analysis: contrasts with mixed logit. Transportation Research Part B: Methodological, 37(8):681–698. [find](https://scholar.google.com/scholar?q=William+H+Greene+and+David+A+Hensher%2E+2003%2E+A+latent+class+model+for+discrete+choice+analysis%3A+contrasts+with+mixed+logit%2E+Transportation+Research+Part+B%3A+Methodological%2C+37%288%29%3A681%E2%80%93698%2E)
24. Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [find](https://scholar.google.com/scholar?q=Guillaume+Lample%2C+Lucile+Saulnier%2C+et+al%2E+2023%2E+Mistral+7b%2E+arXiv+preprint+arXiv%3A2310%2E06825%2E)
25. Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. [Inductive representation learning on large graphs](https://md.research.elamur.ai/free/en/papers/hamilton-2017-inductive-representation-learning-large-graphs/). Advances in neural information processing systems, 30.
26. Minwoo Kang, Suhong Moon, Seung Hyeong Lee, Ayush Raj, Joseph Suh, and David M Chan. 2025. Higher-order binding of language model virtual personas: a study on approximating political partisan misperceptions. arXiv preprint arXiv:2504.11673. — [arXiv:2504.11673](https://arxiv.org/abs/2504.11673) [find](https://scholar.google.com/scholar?q=Minwoo+Kang%2C+Suhong+Moon%2C+Seung+Hyeong+Lee%2C+Ayush+Raj%2C+Joseph+Suh%2C+and+David+M+Chan%2E+2025%2E+Higher%2Dorder+binding+of+language+model+virtual+personas%3A+a+study+on+approximating+political+partisan+misperce)
27. Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 639–648. [find](https://scholar.google.com/scholar?q=Xiangnan+He%2C+Kuan+Deng%2C+Xiang+Wang%2C+Yan+Li%2C+Yongdong+Zhang%2C+and+Meng+Wang%2E+2020%2E+Lightgcn%3A+Simplifying+and+powering+graph+convolution+network+for+recommendation%2E+In+Proceedings+of+the+43rd+Internation)
28. Jaehyung Kim and Yiming Yang. 2025. Few-shot personalization of llms with mis-aligned responses. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 11943–11974. [find](https://scholar.google.com/scholar?q=Jaehyung+Kim+and+Yiming+Yang%2E+2025%2E+Few%2Dshot+personalization+of+llms+with+mis%2Daligned+responses%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas+Chapter+of+the+Association+for+Com)
29. Xiaoxin He, Xavier Bresson, Thomas Laurent, Adam Perold, Yann LeCun, and Bryan Hooi. 2023. Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning. arXiv preprint arXiv:2305.19523. [find](https://scholar.google.com/scholar?q=Xiaoxin+He%2C+Xavier+Bresson%2C+Thomas+Laurent%2C+Adam+Perold%2C+Yann+LeCun%2C+and+Bryan+Hooi%2E+2023%2E+Harnessing+explanations%3A+Llm%2Dto%2Dlm+interpreter+for+enhanced+text%2Dattributed+graph+representation+learning%2E+ar)
30. Junsol Kim, James Evans, and Aaron Schein. 2025. Linear representations of political perspective emerge in large language models. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Junsol+Kim%2C+James+Evans%2C+and+Aaron+Schein%2E+2025%2E+Linear+representations+of+political+perspective+emerge+in+large+language+models%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations)
31. Zihao He, Minh Duc Chu, Rebecca Dorn, Siyi Guo, and Kristina Lerman. 2024. Community-cross-instruct: Unsupervised instruction generation for aligning large language models to online communities. arXiv preprint arXiv:2406.12074. [find](https://scholar.google.com/scholar?q=Zihao+He%2C+Minh+Duc+Chu%2C+Rebecca+Dorn%2C+Siyi+Guo%2C+and+Kristina+Lerman%2E+2024%2E+Community%2Dcross%2Dinstruct%3A+Unsupervised+instruction+generation+for+aligning+large+language+models+to+online+communities%2E+arXiv)
32. Luke Hewitt, Ashwini Ashokkumar, Isaias Ghezae, and Robb Willer. 2024. Predicting results of social science experiments using large language models. Technical report, Stanford University and New York University. [find](https://scholar.google.com/scholar?q=Luke+Hewitt%2C+Ashwini+Ashokkumar%2C+Isaias+Ghezae%2C+and+Robb+Willer%2E+2024%2E+Predicting+results+of+social+science+experiments+using+large+language+models%2E+Technical+report%2C+Stanford+University+and+New+York+)
33. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
34. Zhengyu Hu, Yichuan Li, Zhengyu Chen, Jingang Wang, Han Liu, Kyumin Lee, and Kaize Ding. 2024. Let’s ask gnn: Empowering large language model for graph in-context learning. arXiv preprint arXiv:2410.07074. [find](https://scholar.google.com/scholar?q=Zhengyu+Hu%2C+Yichuan+Li%2C+Zhengyu+Chen%2C+Jingang+Wang%2C+Han+Liu%2C+Kyumin+Lee%2C+and+Kaize+Ding%2E+2024%2E+Let%E2%80%99s+ask+gnn%3A+Empowering+large+language+model+for+graph+in%2Dcontext+learning%2E+arXiv+preprint+arXiv%3A2410%2E0)
35. Angel Hsing-Chi Hwang, Michael S Bernstein, S Shyam Sundar, Renwen Zhang, Manoel Horta Ribeiro, Yingdan Lu, Serina Chang, Tongshuang Wu, Aimei Yang, Dmitri Williams, et al. 2025. Human subjects research in the age of generative ai: Opportunities and challenges of applying llm-simulated data to hci s… [find](https://scholar.google.com/scholar?q=Angel+Hsing%2DChi+Hwang%2C+Michael+S+Bernstein%2C+S+Shyam+Sundar%2C+Renwen+Zhang%2C+Manoel+Horta+Ribeiro%2C+Yingdan+Lu%2C+Serina+Chang%2C+Tongshuang+Wu%2C+Aimei+Yang%2C+Dmitri+Williams%2C+et+al%2E+2025%2E+Human+subjects+resear)
36. EunJeong Hwang, Bodhisattwa Prasad Majumder, and Niket Tandon. 2023. [Aligning language models to user opinions](https://md.research.elamur.ai/free/en/papers/hwang-2023-aligning-language-models-user-opinions/). arXiv preprint arXiv:2305.14929.
37. Rachel A Jansen, Anna N Rafferty, and Thomas L Griffiths. 2021. A rational model of the dunning– kruger effect supports insensitivity to evidence in low performers. Nature Human Behaviour, 5(6):756–763. [find](https://scholar.google.com/scholar?q=Rachel+A+Jansen%2C+Anna+N+Rafferty%2C+and+Thomas+L+Griffiths%2E+2021%2E+A+rational+model+of+the+dunning%E2%80%93+kruger+effect+supports+insensitivity+to+evidence+in+low+performers%2E+Nature+Human+Behaviour%2C+5%286%29%3A756%E2%80%9376)
38. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Diederik P Kingma and Jimmy Ba. 2014. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). arXiv preprint arXiv:1412.6980.
39. Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308. [find](https://scholar.google.com/scholar?q=Thomas+N+Kipf+and+Max+Welling%2E+2016%2E+Variational+graph+auto%2Dencoders%2E+arXiv+preprint+arXiv%3A1611%2E07308%2E)
40. Akaash Kolluri, Shengguang Wu, Joon Sung Park, and Michael S. Bernstein. 2025. Finetuning llms for human behavior prediction in social science experiments. [find](https://scholar.google.com/scholar?q=Akaash+Kolluri%2C+Shengguang+Wu%2C+Joon+Sung+Park%2C+and+Michael+S%2E+Bernstein%2E+2025%2E+Finetuning+llms+for+human+behavior+prediction+in+social+science+experiments%2E)
41. Maximilian Kreutner, Marlene Lutz, and Markus Strohmaier. 2025. Persona-driven simulation of voting behavior in the european parliament with large language models. arXiv preprint arXiv:2506.11798. [find](https://scholar.google.com/scholar?q=Maximilian+Kreutner%2C+Marlene+Lutz%2C+and+Markus+Strohmaier%2E+2025%2E+Persona%2Ddriven+simulation+of+voting+behavior+in+the+european+parliament+with+large+language+models%2E+arXiv+preprint+arXiv%3A2506%2E11798%2E)
42. Stefan Krsteski, Giuseppe Russo, Serina Chang, Robert West, and Kristina Gligorić. 2025. Valid survey simulations with limited human data: The roles of prompting, fine-tuning, and rectification. arXiv preprint arXiv:2510.11408. [find](https://scholar.google.com/scholar?q=Stefan+Krsteski%2C+Giuseppe+Russo%2C+Serina+Chang%2C+Robert+West%2C+and+Kristina+Gligoric%CC%81%2E+2025%2E+Valid+survey+simulations+with+limited+human+data%3A+The+roles+of+prompting%2C+fine%2Dtuning%2C+and+rectification%2E+arXi)
43. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the 29th symposium on operating systems principles, pages 611–626.
44. Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Balaji+Lakshminarayanan%2C+Alexander+Pritzel%2C+and+Charles+Blundell%2E+2017%2E+Simple+and+scalable+predictive+uncertainty+estimation+using+deep+ensembles%2E+Advances+in+neural+information+processing+systems%2C+3)
45. Ang Li, Haozhe Chen, Hongseok Namkoong, and Tianyi Peng. 2025. Llm generated persona is a promise with a catch. arXiv preprint arXiv:2503.16527. — [arXiv:2503.16527](https://arxiv.org/abs/2503.16527) [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+arXiv+preprint+arXiv%3A2503%2E16527%2E+%E2%80%94+%5BarXiv%3A2503%2E16527%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E16527%29)
46. Cheng Li, Mengzhuo Chen, Jindong Wang, Sunayana Sitaram, and Xing Xie. 2024. [Culturellm: Incorporating cultural differences into large language models](https://md.research.elamur.ai/free/en/papers/li-2024-culturellm-incorporating-cultural-differences-large/). Advances in Neural Information Processing Systems, 37:84799–84838.
47. Gechun Lin and Christopher Lucas. 2023. An introduction to neural networks for the social sciences. Oxford Handbook of Engaged Methodological Pluralism in Political Science. [find](https://scholar.google.com/scholar?q=Gechun+Lin+and+Christopher+Lucas%2E+2023%2E+An+introduction+to+neural+networks+for+the+social+sciences%2E+Oxford+Handbook+of+Engaged+Methodological+Pluralism+in+Political+Science%2E)
48. Jiachang Liu, Dinghan Shen, Yizhe Zhang, Bill Dolan, Lawrence Carin, and Weizhu Chen. 2021. [What makes good in-context examples for gpt- 3 ?](https://md.research.elamur.ai/free/en/papers/liu-2022-what-makes-good-context-examples/) arXiv preprint arXiv:2101.06804.
49. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2017%2E+Decoupled+weight+decay+regularization%2E+arXiv+preprint+arXiv%3A1711%2E05101%2E)
50. Yao Lu, Max Bartolo, Alastair Moore, Sebastian Riedel, and Pontus Stenetorp. 2022. [Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity](https://md.research.elamur.ai/free/en/papers/lu-2022-fantastically-ordered-prompts-where-find/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
51. Benjamin S Manning, Kehang Zhu, and John J Horton. 2024. Automated social science: Language models as scientist and subjects. Technical report, National Bureau of Economic Research. [find](https://scholar.google.com/scholar?q=Benjamin+S+Manning%2C+Kehang+Zhu%2C+and+John+J+Horton%2E+2024%2E+Automated+social+science%3A+Language+models+as+scientist+and+subjects%2E+Technical+report%2C+National+Bureau+of+Economic+Research%2E)
52. Daniel McFadden and Kenneth Train. 2000. Mixed mnl models for discrete response. Journal of applied Econometrics, 15(5):447–470. [find](https://scholar.google.com/scholar?q=Daniel+McFadden+and+Kenneth+Train%2E+2000%2E+Mixed+mnl+models+for+discrete+response%2E+Journal+of+applied+Econometrics%2C+15%285%29%3A447%E2%80%93470%2E)
53. Suhong Moon, Marwa Abdulhai, Minwoo Kang, Joseph Suh, Widyadewi Soedarmadji, Eran Kohen Behar, and David M Chan. 2024. Virtual personas for language models via an anthology of backstories. In Proceedings of the 2024 conference on empirical methods in natural language processing, pages 19864–19897. [find](https://scholar.google.com/scholar?q=Suhong+Moon%2C+Marwa+Abdulhai%2C+Minwoo+Kang%2C+Joseph+Suh%2C+Widyadewi+Soedarmadji%2C+Eran+Kohen+Behar%2C+and+David+M+Chan%2E+2024%2E+Virtual+personas+for+language+models+via+an+anthology+of+backstories%2E+In+Proceedi)
54. OpenAI. 2025. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). Preprint, arXiv:2508.10925.
55. 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. arXiv preprint arXiv:2411.10109. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Carolyn+Q+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+Bernstein%2E+2024%2E+Generative+agent+simulations+of+1%2C000+people)
56. PersonaLLM’25. 2026. Workshop on llm persona modeling @ neurips 2025. [https://personallmworkshop.github.io/](https://personallmworkshop.github.io/). Accessed: 2026-01-05. [↗](https://personallmworkshop.github.io/)
57. PewResearch. 2018. America trends panel waves. Retrieved February 06, 2025, from [https://www.pewsocialtrends.org/dataset](https://www.pewsocialtrends.org/dataset). [↗](https://www.pewsocialtrends.org/dataset)
58. Yao Qu and Jue Wang. 2024. Performance and biases of large language models in public opinion simulation. Humanities and Social Sciences Communications, 11(1):1–13. [find](https://scholar.google.com/scholar?q=Yao+Qu+and+Jue+Wang%2E+2024%2E+Performance+and+biases+of+large+language+models+in+public+opinion+simulation%2E+Humanities+and+Social+Sciences+Communications%2C+11%281%29%3A1%E2%80%9313%2E)
59. Vahid Rahimzadeh, Erfan Moosavi Monazzah, Mohammad Taher Pilehvar, and Yadollah Yaghoobzadeh. 2025. Synthia: Synthetic yet naturally tailored human-inspired personas. arXiv preprint arXiv:2507.14922. — [arXiv:2507.14922](https://arxiv.org/abs/2507.14922) [find](https://scholar.google.com/scholar?q=Vahid+Rahimzadeh%2C+Erfan+Moosavi+Monazzah%2C+Mohammad+Taher+Pilehvar%2C+and+Yadollah+Yaghoobzadeh%2E+2025%2E+Synthia%3A+Synthetic+yet+naturally+tailored+human%2Dinspired+personas%2E+arXiv+preprint+arXiv%3A2507%2E14922%2E+)
60. Xubin Ren, Wei Wei, Lianghao Xia, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, and Chao Huang. 2024. Representation learning with large language models for recommendation. In Proceedings of the ACM web conference 2024, pages 3464–3475. [find](https://scholar.google.com/scholar?q=Xubin+Ren%2C+Wei+Wei%2C+Lianghao+Xia%2C+Lixin+Su%2C+Suqi+Cheng%2C+Junfeng+Wang%2C+Dawei+Yin%2C+and+Chao+Huang%2E+2024%2E+Representation+learning+with+large+language+models+for+recommendation%2E+In+Proceedings+of+the+ACM+)
61. David M Rothschild, James Brand, Hope Schroeder, and Jenny Wang. 2024. Opportunities and risks of llms in survey research. Available at SSRN. [find](https://scholar.google.com/scholar?q=David+M+Rothschild%2C+James+Brand%2C+Hope+Schroeder%2C+and+Jenny+Wang%2E+2024%2E+Opportunities+and+risks+of+llms+in+survey+research%2E+Available+at+SSRN%2E)
62. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. [Whose opinions do language models reflect?](https://md.research.elamur.ai/free/en/papers/santurkar-2023-whose-opinions-language-models-reflect/) In International Conference on Machine Learning, pages 29971–30004. PMLR.
63. Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference, pages 593–607. Springer. [find](https://scholar.google.com/scholar?q=Michael+Schlichtkrull%2C+Thomas+N+Kipf%2C+Peter+Bloem%2C+Rianne+Van+Den+Berg%2C+Ivan+Titov%2C+and+Max+Welling%2E+2018%2E+Modeling+relational+data+with+graph+convolutional+networks%2E+In+European+semantic+web+conferen)
64. Melanie Sclar, Yejin Choi, Yulia Tsvetkov, and Alane Suhr. 2024. Quantifying language models’ sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Melanie+Sclar%2C+Yejin+Choi%2C+Yulia+Tsvetkov%2C+and+Alane+Suhr%2E+2024%2E+Quantifying+language+models%E2%80%99+sensitivity+to+spurious+features+in+prompt+design+or%3A+How+i+learned+to+start+worrying+about+prompt+formatt)
65. Leheng Sheng, An Zhang, Yi Zhang, Yuxin Chen, Xiang Wang, and Tat-Seng Chua. 2025. Language representations can be what recommenders need: Findings and potentials. In ICLR. [find](https://scholar.google.com/scholar?q=Leheng+Sheng%2C+An+Zhang%2C+Yi+Zhang%2C+Yuxin+Chen%2C+Xiang+Wang%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Language+representations+can+be+what+recommenders+need%3A+Findings+and+potentials%2E+In+ICLR%2E)
66. Shivalika Singh, Angelika Romanou, Clémentine Fourrier, David I Adelani, Jian Gang Ngui, Daniel Vila-Suero, Peerat Limkonchotiwat, Kelly Marchisio, Wei Qi Leong, Yosephine Susanto, et al. 2024. [Global mmlu: Understanding and addressing cultural and linguistic biases in multilingual evaluation](https://md.research.elamur.ai/free/en/papers/singh-2025-global-mmlu-understanding-addressing-cultural/). arXiv…
67. SocialSim’25. 2025. Social simulation with llms @ colm 2025. [https://sites.google.com/view/](https://sites.google.com/view/) social-sims-with-llms. Accessed: 2025-09-21. [↗](https://sites.google.com/view/)
68. Joseph Suh, Erfan Jahanparast, Suhong Moon, Minwoo Kang, and Serina Chang. 2025. [Language model fine-tuning on scaled survey data for predicting distributions of public opinions](https://md.research.elamur.ai/free/en/papers/suh-2025-language-model-fine-tuning-scaled/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages…
69. Yuanfu Sun, Zhengnan Ma, Yi Fang, Jing Ma, and Qiaoyu Tan. 2025. Graphicl: Unlocking graph learning potential in llms through structured prompt design. arXiv preprint arXiv:2501.15755. [find](https://scholar.google.com/scholar?q=Yuanfu+Sun%2C+Zhengnan+Ma%2C+Yi+Fang%2C+Jing+Ma%2C+and+Qiaoyu+Tan%2E+2025%2E+Graphicl%3A+Unlocking+graph+learning+potential+in+llms+through+structured+prompt+design%2E+arXiv+preprint+arXiv%3A2501%2E15755%2E)
70. Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, and Neel Nanda. 2023. Linear representations of sentiment in large language models. arXiv preprint arXiv:2310.15154. [find](https://scholar.google.com/scholar?q=Curt+Tigges%2C+Oskar+John+Hollinsworth%2C+Atticus+Geiger%2C+and+Neel+Nanda%2E+2023%2E+Linear+representations+of+sentiment+in+large+language+models%2E+arXiv+preprint+arXiv%3A2310%2E15154%2E)
71. Kiran Tomlinson and Austin R Benson. 2024. Graph-based methods for discrete choice. Network Science, 12(1):21–40. [find](https://scholar.google.com/scholar?q=Kiran+Tomlinson+and+Austin+R+Benson%2E+2024%2E+Graph%2Dbased+methods+for+discrete+choice%2E+Network+Science%2C+12%281%29%3A21%E2%80%9340%2E)
72. Olivier Toubia, George Z Gui, Tianyi Peng, Daniel J Merlau, Ang Li, and Haozhe Chen. 2025. Twin-2k-500: A data set for building digital twins of over 2,000 people based on their answers to over 500 questions. Marketing Science. [find](https://scholar.google.com/scholar?q=Olivier+Toubia%2C+George+Z+Gui%2C+Tianyi+Peng%2C+Daniel+J+Merlau%2C+Ang+Li%2C+and+Haozhe+Chen%2E+2025%2E+Twin%2D2k%2D500%3A+A+data+set+for+building+digital+twins+of+over+2%2C000+people+based+on+their+answers+to+over+500+qu)
73. Yutong Xie, Zhuoheng Li, Xiyuan Wang, Yijun Pan, Qijia Liu, Xingzhi Cui, Kuang-Yu Lo, Ruoyi Gao, Xingjian Zhang, Jin Huang, et al. 2025. Be. fm: Open foundation models for human behavior. arXiv preprint arXiv:2505.23058. — [arXiv:2505.23058](https://arxiv.org/abs/2505.23058) [find](https://scholar.google.com/scholar?q=Yutong+Xie%2C+Zhuoheng+Li%2C+Xiyuan+Wang%2C+Yijun+Pan%2C+Qijia+Liu%2C+Xingzhi+Cui%2C+Kuang%2DYu+Lo%2C+Ruoyi+Gao%2C+Xingjian+Zhang%2C+Jin+Huang%2C+et+al%2E+2025%2E+Be%2E+fm%3A+Open+foundation+models+for+human+behavior%2E+arXiv+prepri)
74. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
75. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
76. Kenneth E Train. 2009. Discrete choice methods with simulation. Cambridge university press. [find](https://scholar.google.com/scholar?q=Kenneth+E+Train%2E+2009%2E+Discrete+choice+methods+with+simulation%2E+Cambridge+university+press%2E)
77. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Petar+Velic%CC%8Ckovic%CC%81%2C+Guillem+Cucurull%2C+Arantxa+Casanova%2C+Adriana+Romero%2C+Pietro+Li%C3%B2%2C+and+Yoshua+Bengio%2E+2018%2E+Graph+attention+networks%2E+In+International+Conference+on+Learning+Representations%2E)
78. Leah von der Heyde, Anna-Carolina Haensch, and Alexander Wenz. 2025. Vox populi, vox ai? using large language models to estimate german vote choice. Social Science Computer Review, page 08944393251337014. [find](https://scholar.google.com/scholar?q=Leah+von+der+Heyde%2C+Anna%2DCarolina+Haensch%2C+and+Alexander+Wenz%2E+2025%2E+Vox+populi%2C+vox+ai%3F+using+large+language+models+to+estimate+german+vote+choice%2E+Social+Science+Computer+Review%2C+page+08944393251337)
79. Jimmy Wang, Thomas Zollo, Richard Zemel, and Hongseok Namkoong. 2025. Adaptive elicitation of latent information using natural language. arXiv preprint arXiv:2504.04204. [find](https://scholar.google.com/scholar?q=Jimmy+Wang%2C+Thomas+Zollo%2C+Richard+Zemel%2C+and+Hongseok+Namkoong%2E+2025%2E+Adaptive+elicitation+of+latent+information+using+natural+language%2E+arXiv+preprint+arXiv%3A2504%2E04204%2E)
80. Xiang Wang, Xiangnan He, Yixin Cao, Meng Liu, and Tat-Seng Chua. 2019a. Kgat: Knowledge graph attention network for recommendation. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 950–958. [find](https://scholar.google.com/scholar?q=Xiang+Wang%2C+Xiangnan+He%2C+Yixin+Cao%2C+Meng+Liu%2C+and+Tat%2DSeng+Chua%2E+2019a%2E+Kgat%3A+Knowledge+graph+attention+network+for+recommendation%2E+In+Proceedings+of+the+25th+ACM+SIGKDD+international+conference+on+kn)
81. Cheng Yang, Zhiyuan Liu, Deli Zhao, Maosong Sun, and Edward Y Chang. 2015. Network representation learning with rich text information. In IJCAI, volume 2015, pages 2111–2117. [find](https://scholar.google.com/scholar?q=Cheng+Yang%2C+Zhiyuan+Liu%2C+Deli+Zhao%2C+Maosong+Sun%2C+and+Edward+Y+Chang%2E+2015%2E+Network+representation+learning+with+rich+text+information%2E+In+IJCAI%2C+volume+2015%2C+pages+2111%E2%80%932117%2E)
82. Binwei Yao, Zefan Cai, Yun-Shiuan Chuang, Shanglin Yang, Ming Jiang, Diyi Yang, and Junjie Hu. 2025. No preference left behind: Group distributional preference optimization. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Binwei+Yao%2C+Zefan+Cai%2C+Yun%2DShiuan+Chuang%2C+Shanglin+Yang%2C+Ming+Jiang%2C+Diyi+Yang%2C+and+Junjie+Hu%2E+2025%2E+No+preference+left+behind%3A+Group+distributional+preference+optimization%2E+In+The+Thirteenth+Internat)
83. Liang Yao, Chengsheng Mao, and Yuan Luo. 2019. Graph convolutional networks for text classification. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 7370–7377. [find](https://scholar.google.com/scholar?q=Liang+Yao%2C+Chengsheng+Mao%2C+and+Yuan+Luo%2E+2019%2E+Graph+convolutional+networks+for+text+classification%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+volume+33%2C+pages+7370%E2%80%937377%2E)
84. Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L Hamilton, and Jure Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pages 974–983. [find](https://scholar.google.com/scholar?q=Rex+Ying%2C+Ruining+He%2C+Kaifeng+Chen%2C+Pong+Eksombatchai%2C+William+L+Hamilton%2C+and+Jure+Leskovec%2E+2018%2E+Graph+convolutional+neural+networks+for+web%2Dscale+recommender+systems%2E+In+Proceedings+of+the+24th+AC)
85. Chenxiao Yu, Zhaotian Weng, Yuangang Li, Zheng Li, Xiyang Hu, and Yue Zhao. 2024. A large-scale empirical study on large language models for election prediction. CoRR. [find](https://scholar.google.com/scholar?q=Chenxiao+Yu%2C+Zhaotian+Weng%2C+Yuangang+Li%2C+Zheng+Li%2C+Xiyang+Hu%2C+and+Yue+Zhao%2E+2024%2E+A+large%2Dscale+empirical+study+on+large+language+models+for+election+prediction%2E+CoRR%2E)
86. Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019b. Neural graph collaborative filtering. In Proceedings of the 42nd international ACM SIGIR conference on Research and development in Information Retrieval, pages 165–174. [find](https://scholar.google.com/scholar?q=Xiang+Wang%2C+Xiangnan+He%2C+Meng+Wang%2C+Fuli+Feng%2C+and+Tat%2DSeng+Chua%2E+2019b%2E+Neural+graph+collaborative+filtering%2E+In+Proceedings+of+the+42nd+international+ACM+SIGIR+conference+on+Research+and+development)
87. Junliang Yu, Xin Xia, Tong Chen, Lizhen Cui, Nguyen Quoc Viet Hung, and Hongzhi Yin. 2023. Xsimgcl: Towards extremely simple graph contrastive learning for recommendation. IEEE Transactions on Knowledge and Data Engineering, 36(2):913–926. [find](https://scholar.google.com/scholar?q=Junliang+Yu%2C+Xin+Xia%2C+Tong+Chen%2C+Lizhen+Cui%2C+Nguyen+Quoc+Viet+Hung%2C+and+Hongzhi+Yin%2E+2023%2E+Xsimgcl%3A+Towards+extremely+simple+graph+contrastive+learning+for+recommendation%2E+IEEE+Transactions+on+Knowled)
88. Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E Turner, Richard G Baraniuk, Craig Barton, Simon Peyton Jones, et al. 2020. Instructions and guide for diagnostic questions: The neurips 2020 education challenge. arXiv preprint arXiv:20… — [arXiv:2007.12061](https://arxiv.org/abs/2007.12061) [find](https://scholar.google.com/scholar?q=Zichao+Wang%2C+Angus+Lamb%2C+Evgeny+Saveliev%2C+Pashmina+Cameron%2C+Yordan+Zaykov%2C+Jos%C3%A9+Miguel+Hern%C3%A1ndez%2DLobato%2C+Richard+E+Turner%2C+Richard+G+Baraniuk%2C+Craig+Barton%2C+Simon+Peyton+Jones%2C+et+al%2E+2020%2E+Instructio)
89. Daokun Zhang, Jie Yin, Xingquan Zhu, and Chengqi Zhang. 2019. Attributed network embedding via subspace discovery. Data Mining and Knowledge Discovery, 33(6):1953–1980. [find](https://scholar.google.com/scholar?q=Daokun+Zhang%2C+Jie+Yin%2C+Xingquan+Zhu%2C+and+Chengqi+Zhang%2E+2019%2E+Attributed+network+embedding+via+subspace+discovery%2E+Data+Mining+and+Knowledge+Discovery%2C+33%286%29%3A1953%E2%80%931980%2E)
90. Jiancan Wu, Xiang Wang, Fuli Feng, Xiangnan He, Liang Chen, Jianxun Lian, and Xing Xie. 2021. Self-supervised graph learning for recommendation. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 726–735. [find](https://scholar.google.com/scholar?q=Jiancan+Wu%2C+Xiang+Wang%2C+Fuli+Feng%2C+Xiangnan+He%2C+Liang+Chen%2C+Jianxun+Lian%2C+and+Xing+Xie%2E+2021%2E+Self%2Dsupervised+graph+learning+for+recommendation%2E+In+Proceedings+of+the+44th+international+ACM+SIGIR+conf)
91. Shu Wu, Yuyuan Tang, Yanqiao Zhu, Liang Wang, Xing Xie, and Tieniu Tan. 2019. Session-based recommendation with graph neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 346–353. [find](https://scholar.google.com/scholar?q=Shu+Wu%2C+Yuyuan+Tang%2C+Yanqiao+Zhu%2C+Liang+Wang%2C+Xing+Xie%2C+and+Tieniu+Tan%2E+2019%2E+Session%2Dbased+recommendation+with+graph+neural+networks%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C)
92. Jianan Zhao, Meng Qu, Chaozhuo Li, Hao Yan, Qian Liu, Rui Li, Xing Xie, and Jian Tang. 2022. Learning on large-scale text-attributed graphs via variational inference. arXiv preprint arXiv:2210.14709. — [arXiv:2210.14709](https://arxiv.org/abs/2210.14709) [find](https://scholar.google.com/scholar?q=Jianan+Zhao%2C+Meng+Qu%2C+Chaozhuo+Li%2C+Hao+Yan%2C+Qian+Liu%2C+Rui+Li%2C+Xing+Xie%2C+and+Jian+Tang%2E+2022%2E+Learning+on+large%2Dscale+text%2Dattributed+graphs+via+variational+inference%2E+arXiv+preprint+arXiv%3A2210%2E14709%2E+)
93. Siyan Zhao, John Dang, and Aditya Grover. 2024. Group preference optimization: Few-shot alignment of large language models. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Siyan+Zhao%2C+John+Dang%2C+and+Aditya+Grover%2E+2024%2E+Group+preference+optimization%3A+Few%2Dshot+alignment+of+large+language+models%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2E)
94. Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, et al. 2024. [Sotopia: Interactive evaluation for social intelligence in language agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-sotopia-interactive-evaluation-social-intelligence/). In The Twelfth International Conference on Learning Representations.
95. Jason Zhu, Yanling Cui, Yuming Liu, Hao Sun, Xue Li, Markus Pelger, Tianqi Yang, Liangjie Zhang, Ruofei Zhang, and Huasha Zhao. 2021. Textgnn: Improving text encoder via graph neural network in sponsored search. In Proceedings of the Web Conference 2021, pages 2848–2857. [find](https://scholar.google.com/scholar?q=Jason+Zhu%2C+Yanling+Cui%2C+Yuming+Liu%2C+Hao+Sun%2C+Xue+Li%2C+Markus+Pelger%2C+Tianqi+Yang%2C+Liangjie+Zhang%2C+Ruofei+Zhang%2C+and+Huasha+Zhao%2E+2021%2E+Textgnn%3A+Improving+text+encoder+via+graph+neural+network+in+sponso)

*Updated 1 November 2026*