English(EN) Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

上下文标签极大地改变了语言模型的行为

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-04 04:00

研究人员发现，用于向语言模型呈现上下文的标签对其行为有显著影响。在对 GPT-5.5 和 DeepSeek V4 Pro 等模型的测试中，使用“Instruction:”或“Reference:”等标签可以大大提高注入信息的采纳率，而“Example:”标签则会抑制它。这表明上下文的呈现方式会改变模型利用所提供信息的方式，基准测试应控制这些呈现选择。 AI

影响强调了在 RAG 基准测试中标准化上下文呈现的必要性，以确保可靠的模型性能评估。

排序理由学术论文，详细介绍了关于语言模型行为的新发现。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了关于语言模型行为的新发现。[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: 126 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Jianguo Zhu · 2026-06-04 04:00

Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

arXiv:2606.04109v1 Announce Type: new Abstract: Context-augmented language model systems often wrap supplied content with labels such as Reference:, Evidence:, Instruction:, Note:, or Example:, but the effect of these labels on reader-model behavior remains underexplored. We intr…

本文如何被排名

报道来源 [1]

Discourse-Role Labels as Presentation-Time Variables for Context Use in Language Models

相关实体

相关话题