EPISODE · Jun 8, 2025 · 7 MIN
90. 思考的幻象:推理模型的局限性
from 知为谁 · host 知为谁
本研究探讨了大型推理模型 (LRMs) 在不同复杂度问题上的推理能力,以可控的拼图环境作为测试平台。文章发现,LRMs 在处理低复杂度任务时有时不如标准的大型语言模型 (LLMs),但在中等复杂度任务中展现出优势。然而,对于高复杂度任务,LRMs 和 LLMs 的性能都完全崩溃,并且 LRM 的推理努力(思考代币使用)会反常地减少。此外,分析显示 LRMs 在精确计算和遵循给定算法方面存在局限性,并且随着问题复杂度的增加,正确解决方案在思维过程中的出现位置会向后偏移。内容来源:https://ml-site.cdn-apple.com/papers/the-illusion-of-thinking.pdf
Embed this episode
NOW PLAYING
90. 思考的幻象:推理模型的局限性
0:00
7:15
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.
Frequently Asked Questions
How long is this episode of 知为谁?
This episode is 7 minutes long.
When was this 知为谁 episode published?
This episode was published on June 8, 2025.
Can I download this 知为谁 episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!