# Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models

arXiv: https://arxiv.org/abs/2609.15045 · HTML: https://mlsanity.com/paper/2609.15045/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale](https://mlsanity.com/paper/2212.09095/) (2022)
- [Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning](https://mlsanity.com/paper/2407.07011/) (2024)
- [Prompt Repetition Improves Non-Reasoning LLMs](https://mlsanity.com/paper/2512.14982/) (2025)
- [EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning](https://mlsanity.com/paper/2309.10687/) (2023)
- [Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning](https://mlsanity.com/paper/2602.06600/) (2026)

## Abstract (arXiv)

Prompt echoing is a recognized failure mode of instruct language models, in which a model instead of generating a response, mirrors the provided prompt, even though it did not receive a specific instruction to do so. Is this phenomenon a sign of the model leaking the content of its training dataset, or is it rather caused by a misaligned behavior of the internal induction/copying mechanisms? We investigate prompt echoing small language models from different families (Gemma, Llama, Qwen, SmolLM and OLMo) and show that echoing prompts are likely to have partial overlap with the training dataset but the phenomenon is primarily driven by the model's induction heads.