program-aided-computation-moves-errors-to-translation
mechanismmechanism reasoning

Offloading the calculation to generated code removes the arithmetic as a source of error but does not remove error — what remains is the translation from problem to program, which is now the only thing the model is doing. Verification has to move there with it.

Capability: Digit-level arithmetic · Reasoning, Math

Sources

  • The paper frames its own design this way: "decomposing the natural language problem into runnable steps remains the only learning task for the LLM, while solving is delegated to the interpreter." A correct program run correctly still answers the wrong question if the decomposition was wrong.
Status: activeLast checked: 2026-09-04Evidence activityHow much the field cites the sources under this claimvery heavily cited in the last 12 months268 in 12mo · 824 total — PAL: Program-aided Language Models
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

Notes

Marked mechanism-reasoning rather than single-paper deliberately. The relocation follows from the decomposition the paper states; what I do not have is a source isolating how large the residual translation-error rate is, or whether it grows with problem complexity. Worth revisiting if a paper measures that directly.