# LLMs can hide text in other text of the same length

arXiv: https://arxiv.org/abs/2510.20075 · HTML: https://mlsanity.com/paper/2510.20075/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 52 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Impacts of floating-point non-associativity on reproducibility for HPC and deep learning applications](https://mlsanity.com/paper/2408.05148/) (2024)
- [Generative Text Steganography with Large Language Model](https://mlsanity.com/paper/2404.10229/) (2024)
- [Generative Steganography Network](https://mlsanity.com/paper/2207.13867/) (2022)
- [Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection](https://mlsanity.com/paper/2305.18726/) (2023)
- [A Theory of Unsupervised Translation Motivated by Understanding Animal Communication](https://mlsanity.com/paper/2211.11081/) (2022)
- [Generative Steganography by Sampling](https://mlsanity.com/paper/1804.10531/) (2018)
- [Explanatory Learning: Beyond Empiricism in Neural Networks](https://mlsanity.com/paper/2201.10222/) (2022)
- [Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography](https://mlsanity.com/paper/2409.04878/) (2024)
- [Artificial Scientific Discovery](https://mlsanity.com/paper/2411.11672/) (2024)

## Built on by (most cited first, 2 of 2)

- [Communicating Sound Through Natural Language](https://mlsanity.com/paper/2605.08750/) (2026)
- [CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding](https://mlsanity.com/paper/2609.10744/) (2026)

## Abstract (arXiv)

A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conceal a secret manuscript. This uncanny state of affairs is now possible thanks to Large Language Models, and in this paper we present Calgacus, a simple and efficient protocol to achieve it. We show that even modest 8-billion-parameter open-source LLMs are sufficient to obtain high-quality results, and a message as long as this abstract can be encoded and decoded locally on a laptop in seconds. The existence of such a protocol demonstrates a radical decoupling of text from authorial intent, further eroding trust in written communication, already shaken by the rise of LLM chatbots. We illustrate this with a concrete scenario: a company could covertly deploy an unfiltered LLM by encoding its answers within the compliant responses of a safe model. This possibility raises urgent questions for AI safety and challenges our understanding of what it means for a Large Language Model to know something.