# A Conditional No-Hair Theorem for Transformers: How Language Models Forget Their Prompt

**Published:** October 20, 2026
**Author:** Shuyang Xiang
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/a-conditional-no-hair-theorem-for-transformers-how-language-models-forge

arXiv:2610.24133v1 Announce Type: new Abstract: We ask how much an autoregressive transformer retains of its prompt after generating $t$ tokens. Consider two different prompts followed by the same continuation text, so that any difference in their hidden states comes from the…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2610.24133)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*