Newest papers

Present but Hard to Read: Probing Latent Reasoning with Minimal Pairs

Aur Shalev Merin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28498 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

我们用从同一个字符符号模型Ouro-1.4B和Qwen 2.5-1.5B的标准转换器中复制的数字来测试这个问题,比较只有在答案开始的模型状态,并采取一个失败的探测器作为证据,证明一个值不存在。我们用同一个字符号模型Ouro-1.4B和标准转换器Qwen 2.5-1.5B中复制的数字来测试这一点,比较只有在这个数字中有所不同的探测器显示它在最后一个提示符号上存在:在一个分布式的代码中(读取约0.9)的代码中共享的问题,而一个随机词在其位置移动状态更远,可读性更大。由于每一个变量符号留下了痕迹,一个成功的探测器太模糊了。我们在5249个培训问题

Machine translation (Meta M2M100); the English original follows.

Abstract

Probing studies of latent reasoning often read a model's state where the answer begins and take a failed probe as evidence that a value is absent. We test this with a digit copied from the question, in the looped model Ouro-1.4B and the standard transformer Qwen 2.5-1.5B. Comparing prompts that differ only in that digit shows it is present at the last prompt token, in a code shared across questions (readout about 0.9). A probe that sees one prompt at a time, the usual setting, barely reads it: 0.36 in Ouro and 0.19 in Qwen even after 5,249 training questions. The digit's change is small rather than crowded: random noise lands on equally busy directions, while a random word in its place moves the state far more and is readable. Since every varied token leaves a trace, a successful probe is ambiguous too. We give a protocol, including a synthetic null for generic mixing, for testing computed values against copies and mixtures of the inputs. In pre-registered studies of two-step problems it finds a small signal for the unwritten intermediate a+b just before Ouro writes the answer's last digit, and its sign follows the operation, though mixing alone produces much of that sign-following part. Holding that value at another problem's from the first loop on does not move the written digit toward the other problem's, while the same patch of the answer does: the value is readable but not used.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Security token, Computer science, Value (mathematics), Sign (mathematics), Arithmetic, State (computer science)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange