New paper: passing Lean checks doesn't mean the original proof was correct — faithful translation is undecidable
rohanpaul_ai · x · 2026-10-08
A new paper shows that when AI translates a math proof into Lean, passing the Lean check says nothing about whether the original proof is right. The authors demonstrate a chatbot turning a wrong proof into a valid Lean proof by silently fixing the error. Theoretically, deciding when a statement can be faithfully translated is provably harder than the Halting problem — so no AI translator can always do it. A key caveat for the current wave of Lean-certificated AI math results.
More from Research
- Are URM and Universal Transformers the forgotten architecture beating standard LLMs? — moschles · 2026-10-09
- Researcher: Use AI to Rewrite Machine-Generated Math Proofs Into Human-Readable Forms — jd_pressman · 2026-10-09
- AutoScientist's two-agent checklist loop auto-audits every training example — sarahookr · 2026-10-09
- NeurIPS GenAI4Health oral: retrieval-based medical fact-checking fails in ways bigger models can't fix — mdredze · 2026-10-09
- Bigger models, more reasoning, better sources won't fix medical fact-checking, researchers say — mdredze · 2026-10-09
- DEX best abstract: top LLMs catch many physician diagnostic errors, but big gaps remain — mdredze · 2026-10-09