---
title: "PrefRAG — paper by Zhou and Liu (2026) — summary and ideas"
description: "The authors first build a taxonomy of semantic errors in Z3 Python programs. 31 references."
authors: ["Yuyin Zhou", "Yongmei Liu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.795/"
doi: "10.18653/v1/2026.findings-acl.795"
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/zhou-2026-prefrag-correcting-semantic-errors-auto/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhou-2026-prefrag-correcting-semantic-errors-auto/)

[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/45/) / PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG

# PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG

**Authors:** [Yuyin Zhou](https://md.research.elamur.ai/free/en/authors/yuyin-zhou/) and Yongmei Liu · **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.795/) · [PDF](https://aclanthology.org/2026.findings-acl.795.pdf) · [DOI 10.18653/v1/2026.findings-acl.795](https://doi.org/10.18653/v1/2026.findings-acl.795) · [OpenAlex](https://openalex.org/W7166810066)

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

## Summary

Neuro-symbolic logical reasoning works by having an LLM translate a problem into a symbolic program that a solver then executes. Existing refinement methods mostly catch syntactic errors through solver messages. Semantic mistakes, where a program runs but misrepresents the problem, go largely unchecked at the program level. The authors first build a taxonomy of semantic errors in Z3 Python programs. They then use regex-based rules and LLM augmentation to automatically synthesize SemanticPref, a dataset of preferred versus rejected program pairs built on AR-LSAT and FOLIO. This dataset serves as the knowledge base for PrefRAG, a retrieval-augmented self-refinement loop. In PrefRAG, the LLM itself decides whether a program needs fixing or the loop can stop, rather than reacting only to parse failures. PrefRAG beats strong baselines on in-distribution and out-of-distribution benchmarks, and its gains are largest on unseen data. This suggests that preference examples of typical errors improve how reliably and how widely formalization-based reasoning works.

## Key points

- The semantic error taxonomy has four domain-independent classes:
  - declaration errors
  - missing information (e.g., implicit constraints)
  - inconsistent constraints
  - mismatched predicates
- SemanticPref contains 2921 preference pairs for AR-LSAT and 3091 for FOLIO, all encoded with the Z3 Python API.
- Evaluation covered two kinds of benchmarks:
  - **In-distribution:** AR-LSAT and FOLIO, with an average accuracy gain of 2.39% over the best baselines.
  - **Out-of-distribution:** LogicalDeduction (BIG-bench) and ProverQA, with an average gain of 6.23%.
- On cost, PrefRAG retrieves only during the fix stage, with at most three rounds. On AR-LSAT, its retrieved examples average about 1,939 tokens, compared with about 1,089 for LTRAG, so overhead stays within a constant factor.
- The authors note several limitations:
  - The method is bounded by what Z3 can express and solve, so it cannot handle modal or non-monotonic reasoning.
  - Building the dataset requires a seed set of correct programs.
  - Fine-tuning smaller models with DPO on SemanticPref is proposed as future work.
  - Code is available at github.com/sysulic/PrefRAG.

*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

- [Sun Yat-sen University](https://md.research.elamur.ai/free/en/universities/sun-yat-sen-university/) — University, Guangzhou, China · 72 works · 9,502 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works

## Cite

Cite as: Yuyin Zhou and Yongmei Liu. 2026. PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG. 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{zhou2026prefrag,
  title = {{PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG}},
  author = {Yuyin Zhou and Yongmei Liu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.795},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.795}
}
```

- [← previous Prefix Parsing is Just Parsing](https://md.research.elamur.ai/free/en/papers/pasti-2026-prefix-parsing-is-just-parsing/)
- [next → PrePPER: A Preference Pattern-based Profiling Framework for Explainable Recommendation](https://md.research.elamur.ai/free/en/papers/usumi-2026-prepper-preference-pattern-based-profiling/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/45/)

## References

31 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Michał Podstawski, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. Graph of Thoughts: Solving Elaborate Problems with Large Language Models. In Proceedings of the AAAI Conferen… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Micha%C5%82+Podstawski%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+Torsten+Hoefler%2E+2024%2E+Graph+of+)
2. Leonardo Mendonça de Moura and Nikolaj S. Bjørner. 2008. Z3: an efficient SMT solver. In Proceedings of the 14th International Conference on Tools and Algorithms for the Construction and Analysis of Systems (TACAS). [find](https://scholar.google.com/scholar?q=Leonardo+Mendon%C3%A7a+de+Moura+and+Nikolaj+S%2E+Bj%C3%B8rner%2E+2008%2E+Z3%3A+an+efficient+SMT+solver%2E+In+Proceedings+of+the+14th+International+Conference+on+Tools+and+Algorithms+for+the+Construction+and+Analysis+of+S)
3. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. [DeepSeek-R1: Incentivizing reasoning capability in LL…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/)
4. DeepSeek-AI, Aixin Liu, Aoxue Mei, Bangcai Lin, Bing Xue, Bingxuan Wang, Bingzheng Xu, Bochao Wu, Bowei Zhang, Chaofan Lin, Chen Dong, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenhao Xu, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, and 245 others. 2025. [Deepseek-v3.2: Pushing the frontier of open…](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-v3-2-pushing/)
5. Jiazhan Feng, Ruochen Xu, Junheng Hao, Hiteshi Sharma, Yelong Shen, Dongyan Zhao, and Weizhu Chen. 2024. Language models can be deductive solvers. In Findings of the Association for Computational Linguistics: NAACL 2024. [find](https://scholar.google.com/scholar?q=Jiazhan+Feng%2C+Ruochen+Xu%2C+Junheng+Hao%2C+Hiteshi+Sharma%2C+Yelong+Shen%2C+Dongyan+Zhao%2C+and+Weizhu+Chen%2E+2024%2E+Language+models+can+be+deductive+solvers%2E+In+Findings+of+the+Association+for+Computational+Ling)
6. Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, and 16 others. 2024. [FOLIO:…](https://md.research.elamur.ai/free/en/papers/han-2022-folio-natural-language-reasoning-first/)
7. Shibo Hao, Yi Gu, Haodi Ma, Joshua Hong, Zhen Wang, Daisy Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Yi+Gu%2C+Haodi+Ma%2C+Joshua+Hong%2C+Zhen+Wang%2C+Daisy+Wang%2C+and+Zhiting+Hu%2E+2023%2E+Reasoning+with+language+model+is+planning+with+world+model%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Met)
8. Ruikang Hu, Shaoyu Lin, Yeliang Xiu, and Yongmei Liu. 2025. LTRAG: Enhancing autoformalization and self-refinement for logical reasoning with thought-guided RAG. In Findings of the Association for Computational Linguistics: ACL 2025. [find](https://scholar.google.com/scholar?q=Ruikang+Hu%2C+Shaoyu+Lin%2C+Yeliang+Xiu%2C+and+Yongmei+Liu%2E+2025%2E+LTRAG%3A+Enhancing+autoformalization+and+self%2Drefinement+for+logical+reasoning+with+thought%2Dguided+RAG%2E+In+Findings+of+the+Association+for+Com)
9. Fangkai Jiao, Zhiyang Teng, Bosheng Ding, Zhengyuan Liu, Nancy Chen, and Shafiq Joty. 2024. Exploring self-supervised logic-enhanced training for large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Languag… [find](https://scholar.google.com/scholar?q=Fangkai+Jiao%2C+Zhiyang+Teng%2C+Bosheng+Ding%2C+Zhengyuan+Liu%2C+Nancy+Chen%2C+and+Shafiq+Joty%2E+2024%2E+Exploring+self%2Dsupervised+logic%2Denhanced+training+for+large+language+models%2E+In+Proceedings+of+the+2024+Conf)
10. Tongxuan Liu, Wenjiang Xu, Weizhe Huang, Yuting Zeng, Jiaxing Wang, Xingyu Wang, Hailong Yang, and Jing Li. 2025. Logic-of-thought: Injecting logic into contexts for full reasoning in large language models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Associati… [find](https://scholar.google.com/scholar?q=Tongxuan+Liu%2C+Wenjiang+Xu%2C+Weizhe+Huang%2C+Yuting+Zeng%2C+Jiaxing+Wang%2C+Xingyu+Wang%2C+Hailong+Yang%2C+and+Jing+Li%2E+2025%2E+Logic%2Dof%2Dthought%3A+Injecting+logic+into+contexts+for+full+reasoning+in+large+language+m)
11. Wangyue Lu, Lun Du, Sirui Li, Ke Weng, Haozhe Sun, Hengyu Liu, Minghe Yu, Tiancheng Zhang, and Ge Yu. 2025. Automated formalization via conceptual retrieval-augmented llms. Computing Research Repository, arxiv:2508.06931. — [arXiv:2508.06931](https://arxiv.org/abs/2508.06931) [find](https://scholar.google.com/scholar?q=Wangyue+Lu%2C+Lun+Du%2C+Sirui+Li%2C+Ke+Weng%2C+Haozhe+Sun%2C+Hengyu+Liu%2C+Minghe+Yu%2C+Tiancheng+Zhang%2C+and+Ge+Yu%2E+2025%2E+Automated+formalization+via+conceptual+retrieval%2Daugmented+llms%2E+Computing+Research+Reposito)
12. Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, and Yasuhiro Sogawa. 2024. Enhancing reasoning capabilities of llms via principled synthetic logic corpus. In Advances in Neural Information Processing Systems (NeurIPS), pages 73572–73604. [find](https://scholar.google.com/scholar?q=Terufumi+Morishita%2C+Gaku+Morio%2C+Atsuki+Yamaguchi%2C+and+Yasuhiro+Sogawa%2E+2024%2E+Enhancing+reasoning+capabilities+of+llms+via+principled+synthetic+logic+corpus%2E+In+Advances+in+Neural+Information+Processin)
13. Theo Olausson, Alex Gu, Ben Lipkin, Cedegao Zhang, Armando Solar-Lezama, Joshua Tenenbaum, and Roger Levy. 2023. [LINC: A neurosymbolic approach for logical reasoning by combining language models with first-order logic provers](https://md.research.elamur.ai/free/en/papers/olausson-2023-linc-neurosymbolic-approach-logical-reasoning/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Lan…
14. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/)
15. OpenAI, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, and 400 others. 2024. [GPT-4o sys…](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/)
16. Liangming Pan, Alon Albalak, Xinyi Wang, and William Wang. 2023. [Logic-LM: Empowering large language models with symbolic solvers for faithful logical reasoning](https://md.research.elamur.ai/free/en/papers/pan-2023-logic-lm-empowering-large-language/). In Findings of the Association for Computational Linguistics: EMNLP 2023.
17. Chengwen Qi, Ren Ma, Bowen Li, He Du, Binyuan Hui, Jinwang Wu, Yuanjun Laili, and Conghui He. 2025. Large language models meet symbolic provers for logical reasoning evaluation. In The Thirteenth International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Chengwen+Qi%2C+Ren+Ma%2C+Bowen+Li%2C+He+Du%2C+Binyuan+Hui%2C+Jinwang+Wu%2C+Yuanjun+Laili%2C+and+Conghui+He%2E+2025%2E+Large+language+models+meet+symbolic+provers+for+logical+reasoning+evaluation%2E+In+The+Thirteenth+Inte)
18. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). In Advances in Neural Information Processing Systems (NeurIPS).
19. Mohammad Raza and Natasa Milic-Frayling. 2025. Instantiation-based formalization of logical reasoning tasks using language models and logical solvers. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence(IJCAI 2025). [find](https://scholar.google.com/scholar?q=Mohammad+Raza+and+Natasa+Milic%2DFrayling%2E+2025%2E+Instantiation%2Dbased+formalization+of+logical+reasoning+tasks+using+language+models+and+logical+solvers%2E+In+Proceedings+of+the+Thirty%2DFourth+International)
20. Hyun Ryu, Gyeongman Kim, Hyemin S. Lee, and Eunho Yang. 2025. Divide and translate: Compositional first-order logic translation and verification for complex logical reasoning. In The Thirteenth International Conference on Learning Representations (ICLR 2025). [find](https://scholar.google.com/scholar?q=Hyun+Ryu%2C+Gyeongman+Kim%2C+Hyemin+S%2E+Lee%2C+and+Eunho+Yang%2E+2025%2E+Divide+and+translate%3A+Compositional+first%2Dorder+logic+translation+and+verification+for+complex+logical+reasoning%2E+In+The+Thirteenth+Intern)
21. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W. Kocurek, Ali Safaya, Ali Tazarv, an… — [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://md.research.elamur.ai/free/en/papers/srivastava-2022-imitation-game-quantifying-extrapolating-capabilities/)
22. Koushik Viswanadha, Deepanway Ghosal, and Somak Aditya. 2025. LOGICPO: efficient translation of nl-based logical problems to FOL using llms and preference optimization. Computing Research Repository, arXiv:2506.18383. — [arXiv:2506.18383](https://arxiv.org/abs/2506.18383) [find](https://scholar.google.com/scholar?q=Koushik+Viswanadha%2C+Deepanway+Ghosal%2C+and+Somak+Aditya%2E+2025%2E+LOGICPO%3A+efficient+translation+of+nl%2Dbased+logical+problems+to+FOL+using+llms+and+preference+optimization%2E+Computing+Research+Repository%2C+)
23. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). In The Eleventh International Conference on Learning Representations, (ICLR 2023).
24. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems (NeurIPS).
25. Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, and Wynne Hsu. 2025. [Aristotle: Mastering logical reasoning with a logic-complete decompose-search-resolve framework](https://md.research.elamur.ai/free/en/papers/xu-2025-aristotle-mastering-logical-reasoning-logic/). In Proceedings of the 63rd Annual Meeting of the Association for Computational…
26. Jundong Xu, Hao Fei, Liangming Pan, Qian Liu, Mong-Li Lee, and Wynne Hsu. 2024. [Faithful logical reasoning via symbolic chain-of-thought](https://md.research.elamur.ai/free/en/papers/xu-2024-faithful-logical-reasoning-symbolic-chain/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).
27. Yuan Yang, Siheng Xiong, Ali Payani, Ehsan Shareghi, and Faramarz Fekri. 2024. Harnessing the power of large language models for natural language to first-order logic translation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024). [find](https://scholar.google.com/scholar?q=Yuan+Yang%2C+Siheng+Xiong%2C+Ali+Payani%2C+Ehsan+Shareghi%2C+and+Faramarz+Fekri%2E+2024%2E+Harnessing+the+power+of+large+language+models+for+natural+language+to+first%2Dorder+logic+translation%2E+In+Proceedings+of+th)
28. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+Thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+In+Advances+in+Neural+)
29. Xi Ye, Qiaochu Chen, Isil Dillig, and Greg Durrett. 2023. [SatLM: Satisfiability-aided language models using declarative prompting](https://md.research.elamur.ai/free/en/papers/ye-2023-satlm-satisfiability-aided-language-models/). In Advances in Neural Information Processing Systems (NeurIPS).
30. Meiru Zhang, Philipp Borchert, Milan Gritta, and Gerasimos Lampouras. 2025. DRIFT: decompose, retrieve, illustrate, then formalize theorems. In The Fourteenth International Conference on Learning Representations, (ICLR 2026). [find](https://scholar.google.com/scholar?q=Meiru+Zhang%2C+Philipp+Borchert%2C+Milan+Gritta%2C+and+Gerasimos+Lampouras%2E+2025%2E+DRIFT%3A+decompose%2C+retrieve%2C+illustrate%2C+then+formalize+theorems%2E+In+The+Fourteenth+International+Conference+on+Learning+Repr)
31. Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, and Nan Duan. 2022. Analytical reasoning of text. In Findings of the Association for Computational Linguistics: NAACL 2022. [find](https://scholar.google.com/scholar?q=Wanjun+Zhong%2C+Siyuan+Wang%2C+Duyu+Tang%2C+Zenan+Xu%2C+Daya+Guo%2C+Yining+Chen%2C+Jiahai+Wang%2C+Jian+Yin%2C+Ming+Zhou%2C+and+Nan+Duan%2E+2022%2E+Analytical+reasoning+of+text%2E+In+Findings+of+the+Association+for+Computatio)

*Updated 2 November 2026*