---
title: "Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge"
description: "Knowledge bases behind RAG systems are costly assets that can be stolen and redeployed. 48 references."
authors: ["Ke Yang", "Shuguang Yuan", "Jing Yu", "Chi Chen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1066/"
doi: "10.18653/v1/2026.findings-acl.1066"
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/yang-2026-knowledge-infused-multi-bit-watermarking/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-knowledge-infused-multi-bit-watermarking/)

[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/) / Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge Bases

# Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge Bases

**Authors:** [Ke Yang](https://md.research.elamur.ai/free/en/authors/ke-yang/), [Shuguang Yuan](https://md.research.elamur.ai/free/en/authors/shuguang-yuan/), [Jing Yu](https://md.research.elamur.ai/free/en/authors/jing-yu/) and [Chi Chen](https://md.research.elamur.ai/free/en/authors/chi-chen/) · **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.1066/) · [PDF](https://aclanthology.org/2026.findings-acl.1066.pdf) · [DOI 10.18653/v1/2026.findings-acl.1066](https://doi.org/10.18653/v1/2026.findings-acl.1066) · [OpenAlex](https://openalex.org/W7166865431)

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

## Summary
Knowledge bases behind RAG systems are costly assets that can be stolen and redeployed. An owner can usually probe a suspect system only as a black box. Earlier RAG watermarks have two kinds of drawbacks. Some paraphrase the owner's documents, which hurts their accuracy. Others insert generated passages that may be implausible or false. All of them signal just one bit: watermarked or not.

KMW instead treats watermarking as knowledge-base completion. An LLM extracts knowledge graphs from sampled chunks, following the GraphRAG workflow, and predicts new plausible relations. Each relation becomes a prefix that steers generation of a context-consistent passage. During generation, a keyed hash splits the vocabulary at every token, so token choices encode bits of a shuffled, segmented message through proportional probability modulation. A Watermark Text Indexer uses an LLM and a RAG simulator to build queries that reliably retrieve these passages. Bits read from the responses are then combined by majority voting.

Across four datasets and several LLMs and RAG setups, KMW recovers the full watermark with little loss in task performance. This gives owners richer and more trustworthy ownership evidence.

## Key points
- KMW reaches a watermark recovery rate (WRR) of 1.00 across datasets and RAG configurations. It withstands knowledge selection, alteration and expansion attacks as well as RAG setting restrictions. Its secret key protects against ownership reclaiming and forgery.
- Watermarked texts lower main RAG task performance by only about 1.2%. Their filtering rate stays under 6.23%, outperforming baselines such as WARD and the injection methods of Lv et al. (2025) and Liu et al. (2025b).
- Watermark capacity and query quota drive performance far more than infusion volume. With high capacity and only 100 queries, WRR falls to 0.75.
- The authors acknowledge three limitations:
  - Multi-bit encoding needs more injected text and more queries, which raises computation and API costs.
  - Uneven word frequencies leave a slight statistical bias in generated text.
  - Style changes imposed by system prompts weaken the signal; currently this is handled by lowering capacity.
- The code is publicly released. The authors are affiliated with the Chinese Academy of Sciences through its information engineering institute, and the paper appears in Findings of ACL 2026.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🔌 Hardware and Architecture](https://md.research.elamur.ai/free/en/shelves/computer-science/hardware-and-architecture/) · 167 works

🧭 Topics (1): [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 211 works

## Cite

Cite as: Ke Yang, Shuguang Yuan, Jing Yu and Chi Chen. 2026. Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge Bases. 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{yang2026knowledge,
  title = {{Knowledge-Infused Multi-Bit Watermarking for RAG Knowledge Bases}},
  author = {Ke Yang, Shuguang Yuan, Jing Yu and Chi Chen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1066},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1066}
}
```

- [← previous Knowledge-Infused Hierarchy-Aware Emotion Recognition in Code-mixed Mental Health Counseling Conversations](https://md.research.elamur.ai/free/en/papers/srivastava-2026-knowledge-infused-hierarchy-aware-emotion/)
- [next → Knowledge-to-Verification: Exploring RLVR for LLMs in Knowledge-Intensive Domains](https://md.research.elamur.ai/free/en/papers/yuan-2026-knowledge-verification-exploring-rlvr-llms/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/)

## References

48 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Scott Aaronson. 2023. Watermarking of large language models. [https://simons.berkeley.edu/talks/](https://simons.berkeley.edu/talks/) scott-aaronson-ut-austin-openai-2023-08-17. Aloni Cohen, Alexander Hoover, and Gabe Schoenbach. Accessed: 2025-07-02. 2025. Watermarking language models for many adaptive users. In 2025 IEEE Symposium on… [↗](https://simons.berkeley.edu/talks/)
2. IEEE. Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. [Ms marco: A human generated machine reading comprehension dataset](https://md.research.elamur.ai/free/en/papers/bajaj-2016-ms-marco-human-generated/). Preprint, arXiv:1611.09268.
3. Vera Boteva, Demian Gholipour, Artem Sokolov, and Stefan Riezler. 2016. A full-text learning to rank dataset for medical information retrieval. In Proceedings of the 38th European Conference on Information Retrieval. [find](https://scholar.google.com/scholar?q=Vera+Boteva%2C+Demian+Gholipour%2C+Artem+Sokolov%2C+and+Stefan+Riezler%2E+2016%2E+A+full%2Dtext+learning+to+rank+dataset+for+medical+information+retrieval%2E+In+Proceedings+of+the+38th+European+Conference+on+Inform)
4. Brian J. Chan, Chao-Ting Chen, Jui-Hung Cheng, and Hen-Hsen Huang. 2025. Don’t do rag: When cache-augmented generation is all you need for knowledge tasks. In Companion Proceedings of the ACM on Sumanth Dathathri, Abigail See, Sumedh Ghaisas, Po-Sen Huang, Rob McAdam, Johannes Welbl, Vandana Bachani… [find](https://scholar.google.com/scholar?q=Brian+J%2E+Chan%2C+Chao%2DTing+Chen%2C+Jui%2DHung+Cheng%2C+and+Hen%2DHsen+Huang%2E+2025%2E+Don%E2%80%99t+do+rag%3A+When+cache%2Daugmented+generation+is+all+you+need+for+knowledge+tasks%2E+In+Companion+Proceedings+of+the+ACM+on+Suman)
5. Google DeepMind. 2025. Gemini 2.5 flash. [https://deepmind.google/models/gemini/flash/](https://deepmind.google/models/gemini/flash/). Accessed: 2025-07-15. [↗](https://deepmind.google/models/gemini/flash/)
6. Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. 2019. [DROP: A reading comprehension benchmark requiring discrete reasoning over paragraphs](https://md.research.elamur.ai/free/en/papers/dua-2019-drop-reading-comprehension-benchmark-requiring/). In Proc. of NAACL.
7. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+rag+app)
8. Jaiden Fairoze, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, and Mingyuan Wang. 2023. Publicly-detectable watermarking for language models. arXiv preprint arXiv:2310.18491. — [arXiv:2310.18491](https://arxiv.org/abs/2310.18491) [find](https://scholar.google.com/scholar?q=Jaiden+Fairoze%2C+Sanjam+Garg%2C+Somesh+Jha%2C+Saeed+Mahloujifar%2C+Mohammad+Mahmoody%2C+and+Mingyuan+Wang%2E+2023%2E+Publicly%2Ddetectable+watermarking+for+language+models%2E+arXiv+preprint+arXiv%3A2310%2E18491%2E+%E2%80%94+%5BarXiv%3A)
9. Xiaoyan Feng, He Zhang, Yanjun Zhang, Leo Yu Zhang, and Shirui Pan. 2025. Bimark: Unbiased multi-layer watermarking for large language models. arXiv preprint arXiv:2506.21602. — [arXiv:2506.21602](https://arxiv.org/abs/2506.21602) [find](https://scholar.google.com/scholar?q=Xiaoyan+Feng%2C+He+Zhang%2C+Yanjun+Zhang%2C+Leo+Yu+Zhang%2C+and+Shirui+Pan%2E+2025%2E+Bimark%3A+Unbiased+multi%2Dlayer+watermarking+for+large+language+models%2E+arXiv+preprint+arXiv%3A2506%2E21602%2E+%E2%80%94+%5BarXiv%3A2506%2E21602%5D%28htt)
10. Junfeng Guo, Yiming Li, Ruibo Chen, Yihan Wu, Chenxi Liu, Yanshuo Chen, and Heng Huang. 2025. Towards copyright protection for knowledge bases of retrieval-augmented language models via reasoning. Preprint, arXiv:2502.10440. — [arXiv:2502.10440](https://arxiv.org/abs/2502.10440) [find](https://scholar.google.com/scholar?q=Junfeng+Guo%2C+Yiming+Li%2C+Ruibo+Chen%2C+Yihan+Wu%2C+Chenxi+Liu%2C+Yanshuo+Chen%2C+and+Heng+Huang%2E+2025%2E+Towards+copyright+protection+for+knowledge+bases+of+retrieval%2Daugmented+language+models+via+reasoning%2E+Pre)
11. Md Toufique Hasan, Muhammad Waseem, Kai-Kristian Kemell, Ayman Asad Khan, Mika Saari, and Pekka Abrahamsson. 2025. Engineering rag systems for real-world applications: Design, development, and evaluation. Preprint, arXiv:2506.20869. — [arXiv:2506.20869](https://arxiv.org/abs/2506.20869) [find](https://scholar.google.com/scholar?q=Md+Toufique+Hasan%2C+Muhammad+Waseem%2C+Kai%2DKristian+Kemell%2C+Ayman+Asad+Khan%2C+Mika+Saari%2C+and+Pekka+Abrahamsson%2E+2025%2E+Engineering+rag+systems+for+real%2Dworld+applications%3A+Design%2C+development%2C+and+evaluat)
12. Zhiwei He, Binglin Zhou, Hongkun Hao, Aiwei Liu, Xing Wang, Zhaopeng Tu, Zhuosheng Zhang, and Rui Wang. 2024. Can watermarks survive translation? on the cross-lingual consistency of text watermark for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computation… [find](https://scholar.google.com/scholar?q=Zhiwei+He%2C+Binglin+Zhou%2C+Hongkun+Hao%2C+Aiwei+Liu%2C+Xing+Wang%2C+Zhaopeng+Tu%2C+Zhuosheng+Zhang%2C+and+Rui+Wang%2E+2024%2E+Can+watermarks+survive+translation%3F+on+the+cross%2Dlingual+consistency+of+text+watermark+for)
13. Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, and Liang Zhao. 2025. GRAG: Graph retrieval-augmented generation. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4145–4157. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yuntong+Hu%2C+Zhihan+Lei%2C+Zheng+Zhang%2C+Bo+Pan%2C+Chen+Ling%2C+and+Liang+Zhao%2E+2025%2E+GRAG%3A+Graph+retrieval%2Daugmented+generation%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+NAACL+2025%2C+page)
14. Zhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, and Heng Huang. 2023. Unbiased watermark for large language models. Preprint, arXiv:2310.10669. — [arXiv:2310.10669](https://arxiv.org/abs/2310.10669) [find](https://scholar.google.com/scholar?q=Zhengmian+Hu%2C+Lichang+Chen%2C+Xidong+Wu%2C+Yihan+Wu%2C+Hongyang+Zhang%2C+and+Heng+Huang%2E+2023%2E+Unbiased+watermark+for+large+language+models%2E+Preprint%2C+arXiv%3A2310%2E10669%2E+%E2%80%94+%5BarXiv%3A2310%2E10669%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
15. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/). Preprint, arXiv:2112.09118.
16. Nikola Jovanović, Robin Staab, Maximilian Baader, and Martin Vechev. 2025. Ward: Provable rag dataset inference via llm watermarks. Preprint, arXiv:2410.03537. — [arXiv:2410.03537](https://arxiv.org/abs/2410.03537) [find](https://scholar.google.com/scholar?q=Nikola+Jovanovic%CC%81%2C+Robin+Staab%2C+Maximilian+Baader%2C+and+Martin+Vechev%2E+2025%2E+Ward%3A+Provable+rag+dataset+inference+via+llm+watermarks%2E+Preprint%2C+arXiv%3A2410%2E03537%2E+%E2%80%94+%5BarXiv%3A2410%2E03537%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
17. 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.
18. John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, and Tom Goldstein. 2024. [On the reliability of watermarks for large language models](https://md.research.elamur.ai/free/en/papers/kirchenbauer-2023-reliability-watermarks-large-language-models/). Preprint, arXiv:2306.04634.
19. Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, and Percy Liang. 2024. [Robust distortion-free watermarks for language models](https://md.research.elamur.ai/free/en/papers/kuditipudi-2023-robust-distortion-free-watermarks-language/). Preprint, arXiv:2307.15593.
20. Abhijeet Kumar, Abhishek Pandey, Rohit Gadia, and Mridul Mishra. 2020. Building knowledge graph using pre-trained language model for learning entity-aware relationships. In 2020 IEEE international conference on computing, power and communication technologies (GUCON), pages 310–315. IEEE. [find](https://scholar.google.com/scholar?q=Abhijeet+Kumar%2C+Abhishek+Pandey%2C+Rohit+Gadia%2C+and+Mridul+Mishra%2E+2020%2E+Building+knowledge+graph+using+pre%2Dtrained+language+model+for+learning+entity%2Daware+relationships%2E+In+2020+IEEE+international+con)
21. Myeonghwa Lee, Seonho An, and Min-Soo Kim. 2024. Planrag: A plan-then-retrieval augmented generation for generative large language models as decision makers. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… [find](https://scholar.google.com/scholar?q=Myeonghwa+Lee%2C+Seonho+An%2C+and+Min%2DSoo+Kim%2E+2024%2E+Planrag%3A+A+plan%2Dthen%2Dretrieval+augmented+generation+for+generative+large+language+models+as+decision+makers%2E+In+Proceedings+of+the+2024+Conference+of+t)
22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
23. David Liben-Nowell and Jon Kleinberg. 2003. The link prediction problem for social networks. In Proceedings of the twelfth international conference on Information and knowledge management, pages 556– 559. [find](https://scholar.google.com/scholar?q=David+Liben%2DNowell+and+Jon+Kleinberg%2E+2003%2E+The+link+prediction+problem+for+social+networks%2E+In+Proceedings+of+the+twelfth+international+conference+on+Information+and+knowledge+management%2C+pages+556%E2%80%93+)
24. Peiyang Liu, Ziqiang Cui, Di Liang, and Wei Ye. 2025a. Who stole your data? a method for detecting unauthorized rag theft. Preprint, arXiv:2510.07728. — [arXiv:2510.07728](https://arxiv.org/abs/2510.07728) [find](https://scholar.google.com/scholar?q=Peiyang+Liu%2C+Ziqiang+Cui%2C+Di+Liang%2C+and+Wei+Ye%2E+2025a%2E+Who+stole+your+data%3F+a+method+for+detecting+unauthorized+rag+theft%2E+Preprint%2C+arXiv%3A2510%2E07728%2E+%E2%80%94+%5BarXiv%3A2510%2E07728%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510%2E0)
25. Yepeng Liu, Xuandong Zhao, Dawn Song, and Yuheng Bu. 2025b. Dataset protection via watermarked canaries in retrieval-augmented llms. Preprint, arXiv:2502.10673. [find](https://scholar.google.com/scholar?q=Yepeng+Liu%2C+Xuandong+Zhao%2C+Dawn+Song%2C+and+Yuheng+Bu%2E+2025b%2E+Dataset+protection+via+watermarked+canaries+in+retrieval%2Daugmented+llms%2E+Preprint%2C+arXiv%3A2502%2E10673%2E)
26. Peizhuo Lv, Mengjie Sun, Hao Wang, Xiaofeng Wang, Shengzhi Zhang, Yuxuan Chen, Kai Chen, and Limin Sun. 2025. Rag-wm: An efficient black-box watermarking approach for retrieval-augmented generation of large language models. Preprint, arXiv:2501.05249. — [arXiv:2501.05249](https://arxiv.org/abs/2501.05249) [find](https://scholar.google.com/scholar?q=Peizhuo+Lv%2C+Mengjie+Sun%2C+Hao+Wang%2C+Xiaofeng+Wang%2C+Shengzhi+Zhang%2C+Yuxuan+Chen%2C+Kai+Chen%2C+and+Limin+Sun%2E+2025%2E+Rag%2Dwm%3A+An+efficient+black%2Dbox+watermarking+approach+for+retrieval%2Daugmented+generation+of)
27. Karen Ka Yan Ng, Izuki Matsuba, and Peter Chengming Zhang. 2025. Rag in health care: a novel framework for improving communication and decision-making by addressing llm limitations. NEJM AI, 2(1):AIra2400380. [find](https://scholar.google.com/scholar?q=Karen+Ka+Yan+Ng%2C+Izuki+Matsuba%2C+and+Peter+Chengming+Zhang%2E+2025%2E+Rag+in+health+care%3A+a+novel+framework+for+improving+communication+and+decision%2Dmaking+by+addressing+llm+limitations%2E+NEJM+AI%2C+2%281%29%3AAIra)
28. OpenAI. 2025. Introducing gpt-4.1 in the api. [https://openai.com/index/gpt-4-1/](https://openai.com/index/gpt-4-1/). Accessed: 2025-07-15. [↗](https://openai.com/index/gpt-4-1/)
29. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. [Unifying large language models and knowledge graphs: A roadmap](https://md.research.elamur.ai/free/en/papers/pan-2023-unifying-large-language-models-knowledge/). IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
30. Hongjin Qian, Zheng Liu, Peitian Zhang, Kelong Mao, Defu Lian, Zhicheng Dou, and Tiejun Huang. 2025. Memorag: Boosting long context processing with global memory-enhanced retrieval augmentation. Preprint, arXiv:2409.05591. — [arXiv:2409.05591](https://arxiv.org/abs/2409.05591) [find](https://scholar.google.com/scholar?q=Hongjin+Qian%2C+Zheng+Liu%2C+Peitian+Zhang%2C+Kelong+Mao%2C+Defu+Lian%2C+Zhicheng+Dou%2C+and+Tiejun+Huang%2E+2025%2E+Memorag%3A+Boosting+long+context+processing+with+global+memory%2Denhanced+retrieval+augmentation%2E+Prepr)
31. Wenjie Qu, Wengrui Zheng, Tianyang Tao, Dong Yin, Yanze Jiang, Zhihua Tian, Wei Zou, Jinyuan Jia, and Jiaheng Zhang. 2025. Provably robust multi-bit watermarking for {AI-generated} text. In 34th USENIX Security Symposium (USENIX Security 25), pages 201–220. [find](https://scholar.google.com/scholar?q=Wenjie+Qu%2C+Wengrui+Zheng%2C+Tianyang+Tao%2C+Dong+Yin%2C+Yanze+Jiang%2C+Zhihua+Tian%2C+Wei+Zou%2C+Jinyuan+Jia%2C+and+Jiaheng+Zhang%2E+2025%2E+Provably+robust+multi%2Dbit+watermarking+for+%7BAI%2Dgenerated%7D+text%2E+In+34th+USENI)
32. Sapana Rani and Raju Halder. 2022. Comparative analysis of relational database watermarking techniques: An empirical study. IEEE Access, 10:27970–27989. [find](https://scholar.google.com/scholar?q=Sapana+Rani+and+Raju+Halder%2E+2022%2E+Comparative+analysis+of+relational+database+watermarking+techniques%3A+An+empirical+study%2E+IEEE+Access%2C+10%3A27970%E2%80%9327989%2E)
33. Mohammad Reza Rezaei, Maziar Hafezi, Amit Satpathy, Lovell Hodge, and Ebrahim Pourjafari. 2024. At-rag: An adaptive rag model enhancing query efficiency with topic filtering and iterative reasoning. Preprint, arXiv:2410.12886. [find](https://scholar.google.com/scholar?q=Mohammad+Reza+Rezaei%2C+Maziar+Hafezi%2C+Amit+Satpathy%2C+Lovell+Hodge%2C+and+Ebrahim+Pourjafari%2E+2024%2E+At%2Drag%3A+An+adaptive+rag+model+enhancing+query+efficiency+with+topic+filtering+and+iterative+reasoning%2E+P)
34. Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, and Aman Chadha. 2024. A comprehensive survey of hallucination in large language, image, video and audio foundation models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11709–11724. Associatio… [find](https://scholar.google.com/scholar?q=Pranab+Sahoo%2C+Prabhash+Meharia%2C+Akash+Ghosh%2C+Sriparna+Saha%2C+Vinija+Jain%2C+and+Aman+Chadha%2E+2024%2E+A+comprehensive+survey+of+hallucination+in+large+language%2C+image%2C+video+and+audio+foundation+models%2E+In+)
35. Aditya Kumar Sahu, Krishnan Umachandran, Vaishali D Biradar, Olebara Comfort, V Sri Vigna Hema, Frank Odimegwu, and MA Saifullah. 2023. A study on content tampering in multimedia watermarking. SN Computer Science, 4(3):222. [find](https://scholar.google.com/scholar?q=Aditya+Kumar+Sahu%2C+Krishnan+Umachandran%2C+Vaishali+D+Biradar%2C+Olebara+Comfort%2C+V+Sri+Vigna+Hema%2C+Frank+Odimegwu%2C+and+MA+Saifullah%2E+2023%2E+A+study+on+content+tampering+in+multimedia+watermarking%2E+SN+Comp)
36. Murugan Sankaradas, Ravi K. Rajendran, and Srimat T. Chakradhar. 2025. Streamingrag: Real-time contextual retrieval and generation framework. Preprint, arXiv:2501.14101. — [arXiv:2501.14101](https://arxiv.org/abs/2501.14101) [find](https://scholar.google.com/scholar?q=Murugan+Sankaradas%2C+Ravi+K%2E+Rajendran%2C+and+Srimat+T%2E+Chakradhar%2E+2025%2E+Streamingrag%3A+Real%2Dtime+contextual+retrieval+and+generation+framework%2E+Preprint%2C+arXiv%3A2501%2E14101%2E+%E2%80%94+%5BarXiv%3A2501%2E14101%5D%28https%3A%2F%2Fa)
37. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
38. Sourav Verma. 2024. Contextual compression in [retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2409.13385.
39. Ellen Voorhees, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, William R Hersh, Kyle Lo, Kirk Roberts, Ian Soboroff, and Lucy Lu Wang. 2021. Trec-covid: constructing a pandemic information retrieval test collection. In ACM SIGIR Forum. [find](https://scholar.google.com/scholar?q=Ellen+Voorhees%2C+Tasmeer+Alam%2C+Steven+Bedrick%2C+Dina+Demner%2DFushman%2C+William+R+Hersh%2C+Kyle+Lo%2C+Kirk+Roberts%2C+Ian+Soboroff%2C+and+Lucy+Lu+Wang%2E+2021%2E+Trec%2Dcovid%3A+constructing+a+pandemic+information+retriev)
40. Yuhao Wang, Wenjie Qu, Yanze Jiang, Zichen Liu, Yue Liu, Shengfang Zhai, Yinpeng Dong, and Jiaheng Zhang. 2025. Silent leaks: Implicit knowledge extraction attack on rag systems through benign queries. Preprint, arXiv:2505.15420. — [arXiv:2505.15420](https://arxiv.org/abs/2505.15420) [find](https://scholar.google.com/scholar?q=Yuhao+Wang%2C+Wenjie+Qu%2C+Yanze+Jiang%2C+Zichen+Liu%2C+Yue+Liu%2C+Shengfang+Zhai%2C+Yinpeng+Dong%2C+and+Jiaheng+Zhang%2E+2025%2E+Silent+leaks%3A+Implicit+knowledge+extraction+attack+on+rag+systems+through+benign+queries)
41. Xin Xie, Ningyu Zhang, Zhoubo Li, Shumin Deng, Hui Chen, Feiyu Xiong, Mosha Chen, and Huajun Chen. 2022. From discrimination to generation: Knowledge graph completion with generative transformer. In Companion Proceedings of the Web Conference 2022, pages 162–165. [find](https://scholar.google.com/scholar?q=Xin+Xie%2C+Ningyu+Zhang%2C+Zhoubo+Li%2C+Shumin+Deng%2C+Hui+Chen%2C+Feiyu+Xiong%2C+Mosha+Chen%2C+and+Huajun+Chen%2E+2022%2E+From+discrimination+to+generation%3A+Knowledge+graph+completion+with+generative+transformer%2E+In+C)
42. Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. [Approximate nearest neighbor negative contrastive learning for dense text retrieval](https://md.research.elamur.ai/free/en/papers/xiong-2020-approximate-nearest-neighbor-negative-contrastive/). Preprint, arXiv:2007.00808.
43. KiYoon Yoo, Wonhyuk Ahn, and Nojun Kwak. 2024. Advancing beyond identification: Multi-bit watermark for large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pa… [find](https://scholar.google.com/scholar?q=KiYoon+Yoo%2C+Wonhyuk+Ahn%2C+and+Nojun+Kwak%2E+2024%2E+Advancing+beyond+identification%3A+Multi%2Dbit+watermark+for+large+language+models%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+th)
44. Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. Preprint, arXiv:2410.10594. — [arXiv:2410.10594](https://arxiv.org/abs/2410.10594) [find](https://scholar.google.com/scholar?q=Shi+Yu%2C+Chaoyue+Tang%2C+Bokai+Xu%2C+Junbo+Cui%2C+Junhao+Ran%2C+Yukun+Yan%2C+Zhenghao+Liu%2C+Shuo+Wang%2C+Xu+Han%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2025%2E+Visrag%3A+Vision%2Dbased+retrieval%2Daugmented+generation+on+multi%2Dmoda)
45. Shuguang Yuan, Chi Chen, Ke Yang, Tengfei Yang, and Jing Yu. 2022. An attribute-attack-proof watermarking technique for relational database. In 2022 IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), pages 1136–1143. IEEE. [find](https://scholar.google.com/scholar?q=Shuguang+Yuan%2C+Chi+Chen%2C+Ke+Yang%2C+Tengfei+Yang%2C+and+Jing+Yu%2E+2022%2E+An+attribute%2Dattack%2Dproof+watermarking+technique+for+relational+database%2E+In+2022+IEEE+International+Conference+on+Trust%2C+Security+an)
46. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. [Opt: Open pre-trai…](https://md.research.elamur.ai/free/en/papers/zhang-2022-opt-open-pre-trained-transformer/)
47. Xuandong Zhao, Prabhanjan Ananth, Lei Li, and Yu-Xiang Wang. 2023. [Provable robust watermarking for ai-generated text](https://md.research.elamur.ai/free/en/papers/zhao-2023-provable-robust-watermarking-ai-generated/). Preprint, arXiv:2306.17439.
48. Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andres Fabrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramer, and 1 others. 2025. Sok: Watermarking for ai-generated content. In 2025 IEEE Symposium on Security and Privacy (SP), pages 2621–2639. IEEE. [find](https://scholar.google.com/scholar?q=Xuandong+Zhao%2C+Sam+Gunn%2C+Miranda+Christ%2C+Jaiden+Fairoze%2C+Andres+Fabrega%2C+Nicholas+Carlini%2C+Sanjam+Garg%2C+Sanghyun+Hong%2C+Milad+Nasr%2C+Florian+Tramer%2C+and+1+others%2E+2025%2E+Sok%3A+Watermarking+for+ai%2Dgenerate)

*Updated 2 November 2026*