Implicit Reasoning Steering via Concept Chaining
英文标题：Implicit Reasoning Steering via Concept Chaining
arXiv:2607.14242v1 Announce Type: new Abstract: Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how final decisions are formed. We study whether this fragility can be explo
打开原文相关 1.6 · 机会 0
2.1 KB
640 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.14242v1 Announce Type: new Abstract: Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how final decisions are formed. We study whether this fragility can be explo
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×