English(EN) Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models

小规模LLM中的提示回声与归纳头相关，而非仅仅数据泄露

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员调查了小规模指令遵循语言模型中提示回声的现象。他们分析了Gemma、Llama、Qwen、SmolLM和OLMo等多个系列的模型，以了解这种故障模式是表明训练数据泄露还是对齐不当的复制机制。研究发现，虽然回声提示可能与训练数据集部分重叠，但主要驱动因素似乎是模型的内部归纳头。 AI

影响这项研究阐明了小型语言模型中的一种故障模式，可能指导未来的开发和评估策略。

排序理由该集群包含一篇详细介绍语言模型行为研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍语言模型行为研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Inez Okulska, Bartosz Naskr\k{e}cki, Jan Piotrowski, Tomasz Steifer · 2026-09-15 04:00

魔镜魔镜挂墙上：小型指令语言模型中的提示回声

arXiv:2609.15045v1 Announce Type: cross Abstract: 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 pheno…