Skip to content
conftrace_
2026 EMNLP EMNLP 2026

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

AbstractPrompt 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.

More from EMNLP 2026

All EMNLP 2026 papers →