---
title: "P-QuASAR — paper by Song et al. (2026) — summary and ideas"
description: "The paper addresses automated quality control of patent specifications. 46 references. Among them: 0."
authors: ["Xinyuan Song", "Ziyi Ni", "Fred Yang", "Bo Zhang", "Yijin Wang", "Jane Zhang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.579/"
doi: "10.18653/v1/2026.findings-acl.579"
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/song-2026-p-quasar-unified-probabilistic-framework/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/song-2026-p-quasar-unified-probabilistic-framework/)

[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/38/) / P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement

# P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement

**Authors:** [Xinyuan Song](https://md.research.elamur.ai/free/en/authors/xinyuan-song/), [Ziyi Ni](https://md.research.elamur.ai/free/en/authors/ziyi-ni/), Fred Yang, [Bo Zhang](https://md.research.elamur.ai/free/en/authors/bo-zhang/), Yijin Wang and Jane Zhang · **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.579/) · [PDF](https://aclanthology.org/2026.findings-acl.579.pdf) · [DOI 10.18653/v1/2026.findings-acl.579](https://doi.org/10.18653/v1/2026.findings-acl.579) · [OpenAlex](https://openalex.org/W7166844233)

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

## Summary

The paper addresses automated quality control of patent specifications. Filings keep growing, and AI drafting tools produce documents with more defects than human-written ones. Existing approaches use citation-style proxies, generic text metrics or binary AI detectors. None of them diagnose specific defects across several quality dimensions at once.

P-QuASAR treats a patent as a Quality Graph. Each node is a quality dimension with a latent violation state, and edges carry dependency potentials learned from expert annotations. Three Quality Assessment Functions supply the evidence: QAF-R for regulatory compliance, QAF-T for technical coherence and QAF-F for figure–reference consistency. Each one reports its own uncertainty through Monte Carlo Dropout. Loopy belief propagation combines these signals into a joint posterior. Detected defects are then mapped to ranked sequences of atomic edits, which the authors call Optimal Intervention Paths.

On 500 Chinese patents from eight IPC domains, the framework beats seven baselines on all three dimensions. When its recommended edits are applied to AI-generated drafts, they end up with fewer defects than human-authored patents. This makes it a useful template for structured, explainable assessment of legal-technical documents.

## Key points

- **Accuracy:** Balanced accuracy is 99.86% for regulatory compliance, 88.91% for technical coherence and 94.70% for figure consistency. These are gains of +3.0, +9.0 and +7.1 points over the strongest baseline in each dimension. For figure consistency, that baseline is LayoutLMv3 at 87.65%.
- **Ablation:** Removing the joint graph reasoning lowers average performance by 3.66 points.
- **Regulatory scope:** QAF-R covers 12 violation types drawn from CNIPA examination guidelines as of 2024. Examples include claim dependency errors, abstracts over 300 characters and claims broader than the disclosure supports.
- **Refinement results:** The test set was 250 AI-generated patents from Eureka, MindFlowing and PatSnap.
  - Average defects per document fell from 9.04–12.15 to 3.21, against 7.13 for human-authored patents.
  - MindFlowing's figure–text inconsistencies dropped from 3.41 to 0.24 per document.
- **Limitations:**
  - Only Chinese patents were evaluated.
  - QAF-F depends on OCR for figure labels.
  - The suggested rewrites still require human or generative-model implementation.

*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 Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 147 works · 8,480 citations
- [Emory University](https://md.research.elamur.ai/free/en/universities/emory-university/) — University, Atlanta, United States · 36 works · 39,779 citations
- [Xidian University](https://md.research.elamur.ai/free/en/universities/xidian-university/) — University, Xi'an, China · 14 works · 1,357 citations

📚 Shelves (6): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 182 works · [💼 Business, Management and Accounting](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/) · 32 works · [💼 Management of Technology and Innovation](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/management-of-technology-and-innovation/) · 6 works

## Cite

Cite as: Xinyuan Song, Ziyi Ni, Fred Yang, Bo Zhang, Yijin Wang and Jane Zhang. 2026. P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement. 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{song2026p,
  title = {{P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement}},
  author = {Xinyuan Song, Ziyi Ni, Fred Yang, Bo Zhang, Yijin Wang and Jane Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.579},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.579}
}
```

- [← previous Overview of the UZH Shared Task 2026 on Reconstructing the Reasoning in United Nations Resolutions](https://md.research.elamur.ai/free/en/papers/shaitarova-2026-overview-uzh-shared-task-2026/)
- [next → PACE: Predictive Adaptive Context Extraction for Long-Horizon LLM Agents](https://md.research.elamur.ai/free/en/papers/wei-2026-pace-predictive-adaptive-context-extraction/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/)

## References

46 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, and R Manmatha. 2021. Docformer: End-to-end transformer for document understanding. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 993–1003. [find](https://scholar.google.com/scholar?q=Srikar+Appalaraju%2C+Bhavan+Jasani%2C+Bhargava+Urala+Kota%2C+Yusheng+Xie%2C+and+R+Manmatha%2E+2021%2E+Docformer%3A+End%2Dto%2Dend+transformer+for+document+understanding%2E+In+Proceedings+of+the+IEEE%2FCVF+International+Con)
2. Leonidas Aristodemou and Frank Tietze. 2018. The state-of-the-art on intellectual property analytics (ipa): A literature review on artificial intelligence, machine learning and deep learning methods for analysing intellectual property (ip) data. World Patent Information, 55:37–51. [find](https://scholar.google.com/scholar?q=Leonidas+Aristodemou+and+Frank+Tietze%2E+2018%2E+The+state%2Dof%2Dthe%2Dart+on+intellectual+property+analytics+%28ipa%29%3A+A+literature+review+on+artificial+intelligence%2C+machine+learning+and+deep+learning+methods+f)
3. Tom Brown, Benjamin Mann, Nick Ryder, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in Neural Information Processing Systems, 33:1877–1901.
4. Ilias Chalkidis, Manos Fergadiotis, Prodromos Malakasiotis, Nikolaos Aletras, and Ion Androutsopoulos. 2020. [Legal-bert: The muppets straight out of law school](https://md.research.elamur.ai/free/en/papers/chalkidis-2020-legal-bert-muppets-straight-out/). In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2898–2904.
5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805.
6. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, and 1 others. 2021. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). In International Conference on…
7. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin, 76(5):378–382. [find](https://scholar.google.com/scholar?q=Joseph+L+Fleiss%2E+1971%2E+Measuring+nominal+scale+agreement+among+many+raters%2E+Psychological+Bulletin%2C+76%285%29%3A378%E2%80%93382%2E)
8. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning, pages 1050–1059. PMLR. [find](https://scholar.google.com/scholar?q=Yarin+Gal+and+Zoubin+Ghahramani%2E+2016%2E+Dropout+as+a+bayesian+approximation%3A+Representing+model+uncertainty+in+deep+learning%2E+In+International+Conference+on+Machine+Learning%2C+pages+1050%E2%80%931059%2E+PMLR%2E)
9. Alfonso Gambardella, Dietmar Harhoff, and Bart Verspagen. 2017. The value of european patents: Evidence from a survey of european inventors. Research Policy, 46(7):1218–1231. [find](https://scholar.google.com/scholar?q=Alfonso+Gambardella%2C+Dietmar+Harhoff%2C+and+Bart+Verspagen%2E+2017%2E+The+value+of+european+patents%3A+Evidence+from+a+survey+of+european+inventors%2E+Research+Policy%2C+46%287%29%3A1218%E2%80%931231%2E)
10. Michele Grimaldi, Livio Cricelli, and Francesco Rogo. 2018. Auditing patent portfolio for strategic exploitation: A decision support framework for intellectual property managers. Journal of Intellectual Capital, 19(2):272–293. [find](https://scholar.google.com/scholar?q=Michele+Grimaldi%2C+Livio+Cricelli%2C+and+Francesco+Rogo%2E+2018%2E+Auditing+patent+portfolio+for+strategic+exploitation%3A+A+decision+support+framework+for+intellectual+property+managers%2E+Journal+of+Intellectu)
11. Bronwyn H Hall, Adam Jaffe, and Manuel Trajtenberg. 2005. Market value and patent citations. RAND Journal of Economics, 36(1):16–38. [find](https://scholar.google.com/scholar?q=Bronwyn+H+Hall%2C+Adam+Jaffe%2C+and+Manuel+Trajtenberg%2E+2005%2E+Market+value+and+patent+citations%2E+RAND+Journal+of+Economics%2C+36%281%29%3A16%E2%80%9338%2E)
12. Dietmar Harhoff, Francis Narin, Frederic M Scherer, and Katrin Vopel. 1999. Citation frequency and the value of patented inventions. Review of Economics and Statistics, 81(3):511–515. [find](https://scholar.google.com/scholar?q=Dietmar+Harhoff%2C+Francis+Narin%2C+Frederic+M+Scherer%2C+and+Katrin+Vopel%2E+1999%2E+Citation+frequency+and+the+value+of+patented+inventions%2E+Review+of+Economics+and+Statistics%2C+81%283%29%3A511%E2%80%93515%2E)
13. Dietmar Harhoff, Frederic M Scherer, and Katrin Vopel. 2003. Citations, family size, opposition and the value of patent rights. Research Policy, 32(8):1343–1363. [find](https://scholar.google.com/scholar?q=Dietmar+Harhoff%2C+Frederic+M+Scherer%2C+and+Katrin+Vopel%2E+2003%2E+Citations%2C+family+size%2C+opposition+and+the+value+of+patent+rights%2E+Research+Policy%2C+32%288%29%3A1343%E2%80%931363%2E)
14. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. [Deberta: Decoding-enhanced bert with disentangled attention](https://md.research.elamur.ai/free/en/papers/he-2020-deberta-decoding-enhanced-bert-disentangled/). In International Conference on Learning Representations.
15. Lena Helmers, Franziska Horn, Franziska Biegler, and 1 others. 2019. Automating the search for a patent’s prior art with a full text similarity search. PLoS One, 14(3):e0212103. [find](https://scholar.google.com/scholar?q=Lena+Helmers%2C+Franziska+Horn%2C+Franziska+Biegler%2C+and+1+others%2E+2019%2E+Automating+the+search+for+a+patent%E2%80%99s+prior+art+with+a+full+text+similarity+search%2E+PLoS+One%2C+14%283%29%3Ae0212103%2E)
16. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. 2022. [Layoutlmv3: Pre-training for document ai with unified text and image masking](https://md.research.elamur.ai/free/en/papers/huang-2022-layoutlmv3-pre-training-document-ai/). In Proceedings of the 30th ACM International Conference on Multimedia, pages 4083–4091.
17. Adam B Jaffe and Gaétan De Rassenfosse. 2017. Patent citation data in social science research: Overview and best practices. Journal of the Association for Information Science and Technology, 68(6):1360–1374. [find](https://scholar.google.com/scholar?q=Adam+B+Jaffe+and+Ga%C3%A9tan+De+Rassenfosse%2E+2017%2E+Patent+citation+data+in+social+science+research%3A+Overview+and+best+practices%2E+Journal+of+the+Association+for+Information+Science+and+Technology%2C+68%286%29%3A136)
18. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12):1–38.
19. Jaewoong Kim and 1 others. 2022. A text-embedding-based approach to measuring patent-to-patent technological similarity. Technological Forecasting and Social Change, 177:121559. [find](https://scholar.google.com/scholar?q=Jaewoong+Kim+and+1+others%2E+2022%2E+A+text%2Dembedding%2Dbased+approach+to+measuring+patent%2Dto%2Dpatent+technological+similarity%2E+Technological+Forecasting+and+Social+Change%2C+177%3A121559%2E)
20. John Kirchenbauer, Jonas Geiping, Yuxin Wen, Jonathan Katz, Ian Miers, and Tom Goldstein. 2023. [A watermark for large language models](https://md.research.elamur.ai/free/en/papers/kirchenbauer-2023-watermark-large-language-models/). In International Conference on Machine Learning, pages 17061–17084. PMLR.
21. Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT Press. [find](https://scholar.google.com/scholar?q=Daphne+Koller+and+Nir+Friedman%2E+2009%2E+Probabilistic+graphical+models%3A+principles+and+techniques%2E+MIT+Press%2E)
22. Frank R Kschischang, Brendan J Frey, and Hans-Andrea Loeliger. 2001. Factor graphs and the sum-product algorithm. IEEE Transactions on information theory, 47(2):498–519. [find](https://scholar.google.com/scholar?q=Frank+R+Kschischang%2C+Brendan+J+Frey%2C+and+Hans%2DAndrea+Loeliger%2E+2001%2E+Factor+graphs+and+the+sum%2Dproduct+algorithm%2E+IEEE+Transactions+on+information+theory%2C+47%282%29%3A498%E2%80%93519%2E)
23. J Richard Landis and Gary G Koch. 1977. The measurement of observer agreement for categorical data. Biometrics, 33(1):159–174. [find](https://scholar.google.com/scholar?q=J+Richard+Landis+and+Gary+G+Koch%2E+1977%2E+The+measurement+of+observer+agreement+for+categorical+data%2E+Biometrics%2C+33%281%29%3A159%E2%80%93174%2E)
24. Jean O Lanjouw and Mark Schankerman. 2004. Patent quality and research productivity: Measuring innovation with multiple indicators. The Economic Journal, 114(495):441–465. [find](https://scholar.google.com/scholar?q=Jean+O+Lanjouw+and+Mark+Schankerman%2E+2004%2E+Patent+quality+and+research+productivity%3A+Measuring+innovation+with+multiple+indicators%2E+The+Economic+Journal%2C+114%28495%29%3A441%E2%80%93465%2E)
25. Jieh-Sheng Lee and Jieh Hsiang. 2020. Patent claim generation by fine-tuning openai gpt-2. World Patent Information, 62:101983. [find](https://scholar.google.com/scholar?q=Jieh%2DSheng+Lee+and+Jieh+Hsiang%2E+2020%2E+Patent+claim+generation+by+fine%2Dtuning+openai+gpt%2D2%2E+World+Patent+Information%2C+62%3A101983%2E)
26. Zhe Li and 1 others. 2023. An explainable ai (xai) model for text-based patent novelty analysis. Expert Systems with Applications, 227:120281. [find](https://scholar.google.com/scholar?q=Zhe+Li+and+1+others%2E+2023%2E+An+explainable+ai+%28xai%29+model+for+text%2Dbased+patent+novelty+analysis%2E+Expert+Systems+with+Applications%2C+227%3A120281%2E)
27. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). In Advances in Neural Information Processing Systems, volume 36.
28. Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, and Daxiang Dong. 2025a. Tree-of-code: A self-growing tree framework for end-to-end code generation and execution in complex tasks. In Findings of the Association for Computational Linguistics: ACL 2025, pages 9804–9819. [find](https://scholar.google.com/scholar?q=Ziyi+Ni%2C+Yifan+Li%2C+Ning+Yang%2C+Dou+Shen%2C+Pin+Lyu%2C+and+Daxiang+Dong%2E+2025a%2E+Tree%2Dof%2Dcode%3A+A+self%2Dgrowing+tree+framework+for+end%2Dto%2Dend+code+generation+and+execution+in+complex+tasks%2E+In+Findings+of+the+)
29. Ziyi Ni, Hao Wang, and Huacan Wang. 2025b. Shieldlearner: A new paradigm for jailbreak attack defense in llms. arXiv preprint arXiv:2502.13162. — [arXiv:2502.13162](https://arxiv.org/abs/2502.13162) [find](https://scholar.google.com/scholar?q=Ziyi+Ni%2C+Hao+Wang%2C+and+Huacan+Wang%2E+2025b%2E+Shieldlearner%3A+A+new+paradigm+for+jailbreak+attack+defense+in+llms%2E+arXiv+preprint+arXiv%3A2502%2E13162%2E+%E2%80%94+%5BarXiv%3A2502%2E13162%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E13162%29)
30. Ziyi Ni, Huacan Wang, Shuo Zhang, Shuo Lu, Ziyang He, Zhenheng Tang, Sen Hu, Bo Li, Chen Hu, Binxing Jiao, and 1 others. 2026. Gittaskbench: A benchmark for code agents solving real-world tasks through code repository leveraging. In Proceedings of the AAAI Conference on Artificial Intelligence, volu… [find](https://scholar.google.com/scholar?q=Ziyi+Ni%2C+Huacan+Wang%2C+Shuo+Zhang%2C+Shuo+Lu%2C+Ziyang+He%2C+Zhenheng+Tang%2C+Sen+Hu%2C+Bo+Li%2C+Chen+Hu%2C+Binxing+Jiao%2C+and+1+others%2E+2026%2E+Gittaskbench%3A+A+benchmark+for+code+agents+solving+real%2Dworld+tasks+throug)
31. OpenAI. 2023. New ai classifier for indicating ai-written text. [https://openai.com/blog/new-ai-classifier-for-indicating-ai-written-text](https://openai.com/blog/new-ai-classifier-for-indicating-ai-written-text). OpenAI Blog. [↗](https://openai.com/blog/new-ai-classifier-for-indicating-ai-written-text)
32. Haowei Peng and 1 others. 2024. Can large language models generate high-quality patent claims? In arXiv preprint arXiv:2406.19465. [find](https://scholar.google.com/scholar?q=Haowei+Peng+and+1+others%2E+2024%2E+Can+large+language+models+generate+high%2Dquality+patent+claims%3F+In+arXiv+preprint+arXiv%3A2406%2E19465%2E)
33. Yun Ren, Xiao Yang, and 1 others. 2024. Sok: On the role and future of aigc watermarking in the era of gen-ai. In arXiv preprint arXiv:2411.11478. — [arXiv:2411.11478](https://arxiv.org/abs/2411.11478) [find](https://scholar.google.com/scholar?q=Yun+Ren%2C+Xiao+Yang%2C+and+1+others%2E+2024%2E+Sok%3A+On+the+role+and+future+of+aigc+watermarking+in+the+era+of+gen%2Dai%2E+In+arXiv+preprint+arXiv%3A2411%2E11478%2E+%E2%80%94+%5BarXiv%3A2411%2E11478%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2411%2E11478)
34. Julian Risch, Leonhard Alder, and Ralf Krestel. 2024. Natural language processing in the patent domain: A survey. Artificial Intelligence Review, 58:1–45. [find](https://scholar.google.com/scholar?q=Julian+Risch%2C+Leonhard+Alder%2C+and+Ralf+Krestel%2E+2024%2E+Natural+language+processing+in+the+patent+domain%3A+A+survey%2E+Artificial+Intelligence+Review%2C+58%3A1%E2%80%9345%2E)
35. Mariagrazia Squicciarini, Hélène Dernis, and Chiara Criscuolo. 2013. Measuring patent quality: Indicators of technological and economic value. OECD Science, Technology and Industry Working Papers, 2013(03). [find](https://scholar.google.com/scholar?q=Mariagrazia+Squicciarini%2C+H%C3%A9l%C3%A8ne+Dernis%2C+and+Chiara+Criscuolo%2E+2013%2E+Measuring+patent+quality%3A+Indicators+of+technological+and+economic+value%2E+OECD+Science%2C+Technology+and+Industry+Working+Papers%2C+201)
36. Yuchuan Tian and 1 others. 2024. Multiscale positive-unlabeled detection of ai-generated texts. In International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Yuchuan+Tian+and+1+others%2E+2024%2E+Multiscale+positive%2Dunlabeled+detection+of+ai%2Dgenerated+texts%2E+In+International+Conference+on+Learning+Representations+%28ICLR%29%2E)
37. Eric Mitchell, Yoonho Lee, Alexander Khazatsky, Christopher D Manning, and Chelsea Finn. 2023. [Detectgpt: Zero-shot machine-generated text detection using probability curvature](https://md.research.elamur.ai/free/en/papers/mitchell-2023-detectgpt-zero-shot-machine-generated/). In International Conference on Machine Learning, pages 24950–24962. PMLR.
38. Damiano Torre and 1 others. 2024. Nlp-based automated compliance checking of data processing agreements against gdpr. IEEE Software, 41(2):48–56. [find](https://scholar.google.com/scholar?q=Damiano+Torre+and+1+others%2E+2024%2E+Nlp%2Dbased+automated+compliance+checking+of+data+processing+agreements+against+gdpr%2E+IEEE+Software%2C+41%282%29%3A48%E2%80%9356%2E)
39. Kevin P Murphy, Yair Weiss, and Michael I Jordan. 1999. Loopy belief propagation for approximate inference: An empirical study. Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence, pages 467–475. [find](https://scholar.google.com/scholar?q=Kevin+P+Murphy%2C+Yair+Weiss%2C+and+Michael+I+Jordan%2E+1999%2E+Loopy+belief+propagation+for+approximate+inference%3A+An+empirical+study%2E+Proceedings+of+the+Fifteenth+conference+on+Uncertainty+in+artificial+int)
40. Qiyao Wang, Shiwen Ni, and 1 others. 2024. Autopatent: A multi-agent framework for automatic patent generation. In arXiv preprint arXiv:2412.09796. — [arXiv:2412.09796](https://arxiv.org/abs/2412.09796) [find](https://scholar.google.com/scholar?q=Qiyao+Wang%2C+Shiwen+Ni%2C+and+1+others%2E+2024%2E+Autopatent%3A+A+multi%2Dagent+framework+for+automatic+patent+generation%2E+In+arXiv+preprint+arXiv%3A2412%2E09796%2E+%E2%80%94+%5BarXiv%3A2412%2E09796%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E0979)
41. Ziyi Ni, Minglun Han, Feilong Chen, Linghui Meng, Jing Shi, Pin Lv, and Bo Xu. 2024. Vilas: Exploring the effects of vision and language context in automatic speech recognition. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 11366–11370.… [find](https://scholar.google.com/scholar?q=Ziyi+Ni%2C+Minglun+Han%2C+Feilong+Chen%2C+Linghui+Meng%2C+Jing+Shi%2C+Pin+Lv%2C+and+Bo+Xu%2E+2024%2E+Vilas%3A+Exploring+the+effects+of+vision+and+language+context+in+automatic+speech+recognition%2E+In+ICASSP+2024%2D2024+IE)
42. Manuel Trajtenberg. 1990. A penny for your quotes: patent citations and the value of innovations. RAND Journal of Economics, 21(1):172–187. [find](https://scholar.google.com/scholar?q=Manuel+Trajtenberg%2E+1990%2E+A+penny+for+your+quotes%3A+patent+citations+and+the+value+of+innovations%2E+RAND+Journal+of+Economics%2C+21%281%29%3A172%E2%80%93187%2E)
43. Wei Wang and 1 others. 2021. A survey on deep learning for patent analysis. World Patent Information, 65:102035. [find](https://scholar.google.com/scholar?q=Wei+Wang+and+1+others%2E+2021%2E+A+survey+on+deep+learning+for+patent+analysis%2E+World+Patent+Information%2C+65%3A102035%2E)
44. Zihong Wang and Yufei Liu. 2024. Sea-ps: Semantic embedding with attention to measuring patent similarity by leveraging various text fields. Journal of Information Science, 50(1):3–19. [find](https://scholar.google.com/scholar?q=Zihong+Wang+and+Yufei+Liu%2E+2024%2E+Sea%2Dps%3A+Semantic+embedding+with+attention+to+measuring+patent+similarity+by+leveraging+various+text+fields%2E+Journal+of+Information+Science%2C+50%281%29%3A3%E2%80%9319%2E)
45. Jonathan S Yedidia, William T Freeman, and Yair Weiss. 2003. Understanding belief propagation and its generalizations. Exploring artificial intelligence in the new millennium, 8:236–239. [find](https://scholar.google.com/scholar?q=Jonathan+S+Yedidia%2C+William+T+Freeman%2C+and+Yair+Weiss%2E+2003%2E+Understanding+belief+propagation+and+its+generalizations%2E+Exploring+artificial+intelligence+in+the+new+millennium%2C+8%3A236%E2%80%93239%2E)
46. Zhenyu Yu. 2025. Ai for science: A comprehensive review on innovations, challenges, and future directions. International Journal of Artificial Intelligence for Science (IJAI4S), 1(1). [find](https://scholar.google.com/scholar?q=Zhenyu+Yu%2E+2025%2E+Ai+for+science%3A+A+comprehensive+review+on+innovations%2C+challenges%2C+and+future+directions%2E+International+Journal+of+Artificial+Intelligence+for+Science+%28IJAI4S%29%2C+1%281%29%2E)

*Updated 1 November 2026*