Journal article · 2026 · Open access

1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning

Wenkai Li, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, Maarten Sap

Proceedings of IASEAI Conference, 2(1), 382–394 · Published 15 July 2026 · DOI 10.1609/iaseai.v2i1.43039

Open PDFView at the publisherCite this paper

In brief

“1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning” is a 2026 journal article by Wenkai Li and 4 co-authors, published in Proceedings of IASEAI Conference. OpenAlex counts 6 citations as of 19 November 2026, which puts it in the top 7% of works published in 2026 by citations. It is open access: the full text is free to read at AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)).

Citations
6
Most cited in
2026 (4)
Field-weighted impact
3.92
References
40
Authors
5

Abstract

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks (extraction, classification), reducing the information load on any single agent while enabling iterative validation and more reliable adherence to contextual privacy norms. To understand how privacy errors emerge and propagate, we conduct a systematic ablation study over information-flow topologies, revealing when and why upstream detection mistakes cascade into downstream leakage. The experiments on the ConfAIde and PrivacyLens benchmark with several open-source and closed-sourced LLMs demonstrate that our best multi-agent configuration substantially reduces private information leakage 18% on ConfAIde and 19% on PrivacyLens using GPT-4o) while preserving the fidelity of public content, outperforming single-agent baselines. These results highlight the promise of principled, visibility-aware information-flow design in multi-agent systems for contextual privacy with LLMs.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, W., Sun, L., Guan, Z., Zhou, X., & Sap, M. (2026). 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning. Proceedings of IASEAI Conference, 2(1), 382–394. https://doi.org/10.1609/iaseai.v2i1.43039

MLA 9

Li, Wenkai, et al. “1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning.” Proceedings of IASEAI Conference, vol. 2, no. 1, 2026, pp. 382–394. https://doi.org/10.1609/iaseai.v2i1.43039.

Chicago

Li, Wenkai, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, and Maarten Sap. 2026. “1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning.” Proceedings of IASEAI Conference 2 (1): 382–394. https://doi.org/10.1609/iaseai.v2i1.43039.

Harvard

Li, W. et al. (2026) ‘1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning’, Proceedings of IASEAI Conference, 2(1), pp. 382–394. doi:10.1609/iaseai.v2i1.43039.

IEEE

W. Li, L. Sun, Z. Guan, X. Zhou, and M. Sap, “1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning,” Proceedings of IASEAI Conference, vol. 2, no. 1, pp. 382–394, 2026, doi: 10.1609/iaseai.v2i1.43039.

BibTeX

@article{li2026check,
  title     = {{1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning}},
  author    = {Li, Wenkai and Sun, Liwen and Guan, Zhenxiang and Zhou, Xuhui and Sap, Maarten},
  journal   = {Proceedings of IASEAI Conference},
  year      = {2026},
  volume    = {2},
  number    = {1},
  pages     = {382--394},
  doi       = {10.1609/iaseai.v2i1.43039},
  url       = {https://doi.org/10.1609/iaseai.v2i1.43039}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • contextual privacy
  • large language models
  • multi-agent systems
  • information flow topology
  • meeting summarization

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, W., Sun, L., Guan, Z., Zhou, X., & Sap, M. (2026). 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning. Proceedings of IASEAI Conference, 2(1), 382–394. https://doi.org/10.1609/iaseai.v2i1.43039

How many times has this paper been cited?

6 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)): sign in and open the PDF from this page.

Who wrote this paper?

Wenkai Li, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, Maarten Sap.

What is the DOI of this paper?

10.1609/iaseai.v2i1.43039, permanently at https://doi.org/10.1609/iaseai.v2i1.43039. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.