PulseAugur
中
实时 06:51:36
English(EN) The Presupposition Problem in Representation Genesis

新论文识别出大型语言模型生成中的“表征回归”

一篇新发表在arXiv上的论文探讨了人工智能,特别是大型语言模型(LLMs)中表征生成的“预设问题”。作者认为,当前的哲学框架,包括思想语言假说(Language of Thought hypothesis)和目的论(teleosemantics),未能充分解释系统如何从非表征状态过渡到内容敏感状态,因为它们预设了表征的存在。这造成了一个解释鸿沟,被称为“表征回归”(Representation Regress),阻碍了对LLMs如何在没有明确表征生成过程的情况下实现其认知能力的理解。该论文旨在诊断这一结构性问题,并为未来能够避免此问题的理论勾勒出条件。 AI

影响 强调了理解LLMs如何发展表征的理论挑战,可能影响未来的AI架构和可解释性研究。

排序理由 该条目是一篇发表在arXiv上的学术论文,讨论了AI表征生成中的理论问题。[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 →

新论文识别出大型语言模型生成中的“表征回归”

本文如何被排名

Signal score
38 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该条目是一篇发表在arXiv上的学术论文,讨论了AI表征生成中的理论问题。[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, other
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) · Yiling Wu (BridgeM, Inc.) ·

    表征生成中的预设问题

    arXiv:2603.21745v3 Announce Type: replace-cross Abstract: Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one whose states guide behavior…