English(EN) To Copy or Not to Copy: Copying Is Easier to Induce Than Recall

新研究揭示语言模型如何在回忆和复制之间做出选择

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了一种方法来分析语言模型如何在利用其内部知识或使用提供的上下文信息之间进行决策。他们识别出了一个“仲裁向量”，可以通过操纵该向量来鼓励模型回忆其参数知识，或直接从提示中复制信息。在不同模型架构和问答基准上的实验表明，诱导复制比抑制复制和恢复回忆更容易，后者似乎对特定干预措施更敏感。 AI

影响为在检索增强设置中控制语言模型行为提供了见解，有可能提高准确性和流畅性。

排序理由研究论文发布在arXiv上，详细介绍了对语言模型行为的机制研究。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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: 24 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文发布在arXiv上，详细介绍了对语言模型行为的机制研究。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Mehrdad Farahani, Franziska Penzkofer, Richard Johansson · 2026-09-01 04:00

复制还是不复制：复制比回忆更容易诱发

arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information in the prompt. This work presents a mechanistic study of that choice by extracti…

本文如何被排名

报道来源 [1]

复制还是不复制：复制比回忆更容易诱发

相关实体

相关话题