← Thursday, October 8, 2026ResearchPaper

Lean verification cannot guarantee an AI-generated natural-language proof is sound

arxiv.org 3 min read Editor score 7/10

The paper argues that mechanically checking a Lean formalization does not establish that it faithfully represents the original natural-language proof. Engineers building AI verification workflows should treat translation fidelity as a separate problem from checking the formal result.

What: A paper argues that verifying an AI-generated Lean formalization does not establish that the original natural-language proof is correct.
Method: It describes semantic ambiguity as a barrier to faithful autoformalization and gives examples of mistranslations, including one involving a Navier–Stokes proof.
Why it matters: Engineers should treat formal verification as checking the translated statement, not the source text, unless their semantic correspondence is established.

Natural-language text is translated into Lean, where the formalized argument can be mechanically checked. Sketched from the article's own text.

Read on arxiv.org → Hacker News · 181 comments

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.