Computed Ahead, Copied Blind: Unchecked Handoffs in Chain-of-Thought Arithmetic
Abstract
When one position in a chain of thought hands a computed result to the next, does the receiver check it against the other input it can see? We study the final combination of two products in two models' own solutions to 749 linear systems, using sublayer readouts, attention cuts, and value substitutions. (1)Erroneous delivery passes unchecked on the copying route. The answer's first digit is computed at the equals position before it is written. A space receiver copies it through late attention, writing a donor's digit with probability near one with the correct operands in view. A minus receiver computes from the operands and shows no donor following. After operand damage, correct content at the equals position supports some answers, while most remain wrong. (2)The receiving state controls route selection and content influence. Changing the carrier changes input dependence. Cutting late equals reads makes copying fail; also cutting early equals reads restores operand support. Recovery reuses natural computation's operand-reading heads in both models. (3)Enabling operand computation and protecting its output are separate. With all operand reads at the equals position cut, cutting its remaining delivery restores further correct answers. On the computing route, delivered content shifts the output distribution while answers remain largely stable; after operand damage, it changes answers, mostly without donor following. Faithful transfer and effective verification are therefore different capabilities.
est. 32% chance this paper gets accepted at ICLR 2027.
What do you think this paper will get?
All positions stay anonymous.