Conference paper · 2026 · Open access
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
Proceedings of the conference - Association for Computational Linguistics. Meeting, 5979–5996 · Published 1 January 2026 · DOI 10.18653/v1/2026.acl-long.270
In brief
“Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage” is a 2026 conference paper by Jinwei Hu and 4 co-authors, published in Proceedings of the conference - Association for Computational Linguistics. Meeting. OpenAlex counts 24 citations as of 19 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Proceedings of the conference - Association for Computational Linguistics. Meeting.
- Citations
- 24
- Most cited in
- 2026 (24)
- Field-weighted impact
- 21.23
- References
- 60
- Authors
- 5
Abstract
As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an unexpected attack surface. This paper introduces a novel threat where colluding agents steer victim beliefs using only truthful evidence fragments distributed through public channels, without relying on covert communications, backdoors, or falsified documents. By exploiting LLMs' overthinking tendency, we formalize the first cognitive collusion attack and propose Generative Montage: a Writer-Editor-Director framework that constructs deceptive narratives through adversarial debate and coordinated posting of evidence fragments, causing victims to internalize and propagate fabricated conclusions. To study this risk, we develop CoPHEME, a dataset derived from real-world rumor events, and simulate attacks across diverse LLM families. Our results show pervasive vulnerability across 14 LLM families: attack success rates reach 74.4% for proprietary models and 70.6% for open-weights models. Counterintuitively, stronger reasoning capabilities increase susceptibility, with reasoning-specialized models showing higher attack success than base models or prompts. Furthermore, these false beliefs then cascade to downstream judges, achieving over 60% deception rates, highlighting a socio-technical vulnerability in how LLM-based agents interact with dynamic information environments. Our implementation and data are available at: https://github.com/CharlesJW222/Lying_with_Truth/tree/main.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hu, J., Huang, X., Sun, Y., Dong, Y., & Huang, X. (2026). Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage. Proceedings of the conference - Association for Computational Linguistics. Meeting, 5979–5996. https://doi.org/10.18653/v1/2026.acl-long.270
MLA 9
Hu, Jinwei, et al. “Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage.” Proceedings of the conference - Association for Computational Linguistics. Meeting, 2026, pp. 5979–5996. https://doi.org/10.18653/v1/2026.acl-long.270.
Chicago
Hu, Jinwei, Xinmiao Huang, Youcheng Sun, Yi Dong, and Xiaowei Huang. 2026. “Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage.” Proceedings of the conference - Association for Computational Linguistics. Meeting: 5979–5996. https://doi.org/10.18653/v1/2026.acl-long.270.
Harvard
Hu, J. et al. (2026) ‘Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage’, Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 5979–5996. doi:10.18653/v1/2026.acl-long.270.
IEEE
J. Hu, X. Huang, Y. Sun, Y. Dong, and X. Huang, “Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage,” Proceedings of the conference - Association for Computational Linguistics. Meeting, pp. 5979–5996, 2026, doi: 10.18653/v1/2026.acl-long.270.
BibTeX
@inproceedings{hu2026lying,
title = {{Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage}},
author = {Hu, Jinwei and Huang, Xinmiao and Sun, Youcheng and Dong, Yi and Huang, Xiaowei},
booktitle = {Proceedings of the conference - Association for Computational Linguistics. Meeting},
year = {2026},
pages = {5979--5996},
doi = {10.18653/v1/2026.acl-long.270},
url = {https://doi.org/10.18653/v1/2026.acl-long.270}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- LLM agents
- belief manipulation
- overthinking
- large language model security
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Hu, J., Huang, X., Sun, Y., Dong, Y., & Huang, X. (2026). Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage. Proceedings of the conference - Association for Computational Linguistics. Meeting, 5979–5996. https://doi.org/10.18653/v1/2026.acl-long.270
How many times has this paper been cited?
24 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 Proceedings of the conference - Association for Computational Linguistics. Meeting: sign in and open the full text from this page.
Who wrote this paper?
Jinwei Hu, Xinmiao Huang, Youcheng Sun, Yi Dong, Xiaowei Huang.
What is the DOI of this paper?
10.18653/v1/2026.acl-long.270, permanently at https://doi.org/10.18653/v1/2026.acl-long.270. 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.