PulseAugur
中
实时 08:54:44
English(EN) Context or Knowledge: How LLMs Attribute Their Own Answers

研究发现:大型语言模型(LLMs)的来源归因与其缓存状态存在因果关联

研究人员调查了大型语言模型(LLMs)如何将其答案归因于提供的上下文或其内部知识。通过干预模型键值(KV)缓存进行的实验显示,修改文档缓存对来源报告没有影响。然而,在运行之间移植问题与答案(Q+A)缓存会显著影响报告的来源,移植的Q+A缓存决定了答案报告的来源。这表明在答案生成过程中产生的缓存状态因果性地决定了这些模型的来源报告。 AI

影响 这项研究阐明了大型语言模型(LLMs)如何确定答案来源,可能影响其输出的可信度和审计方式。

排序理由 学术论文,详细介绍了关于大型语言模型(LLMs)行为的新研究发现。[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 →

研究发现:大型语言模型(LLMs)的来源归因与其缓存状态存在因果关联

本文如何被排名

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
学术论文,详细介绍了关于大型语言模型(LLMs)行为的新研究发现。[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
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]

  1. arXiv cs.CL TIER_1 English(EN) · Kirill Afendulev, Alexey Dontsov, Alla Chepurova, Elena Tutubalina, Anton Korznikov ·

    上下文或知识:大型语言模型如何归因其自身答案

    arXiv:2610.32109v1 Announce Type: new Abstract: Language models can answer a question from a supplied document or from their parametric knowledge. When later asked where the answer came from, what determines their source report? We study this by intervening on the model's key-val…