Metraipolis › archive › dc_3c490bc6d192

DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving — arXiv:2610.41536

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41536
License (as archived)
CC0-1.0
Archived
2026-11-03T08:05:42.052Z
SHA-256 of the archived text
386c54f1870085d79054110f2e5ec94931f23e5a7f0580dfb391d5b596423b33
Stable URL of this page
https://metraipolis.com/documento/dc_3c490bc6d192

How to cite

DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving — arXiv:2610.41536 — arXiv (en), https://arxiv.org/abs/2610.41536 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c490bc6d192 (Metraipolis archive dc_3c490bc6d192, sha256 386c54f1870085d79054110f2e5ec94931f23e5a7f0580dfb391d5b596423b33)
BibTeX
@misc{dc3c490bc6d192,
  title = {DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving — arXiv:2610.41536},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41536},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c490bc6d192; sha256 386c54f1870085d79054110f2e5ec94931f23e5a7f0580dfb391d5b596423b33},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41536. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLM-based theorem proving in Lean 4 has advanced rapidly, but provers are difficult to leverage newly contributed lemmas, because retrieval skews toward popular foundational lemmas, leaving the right premises buried among hundreds of thousands of candidates. Existing neural selectors rank candidates by semantic similarity, with three intrinsic limitations: frequency-skewed retrieval, isolated pairwise ranking, and degradation on out-of-distribution queries such as competition problems and informal language. Given that mathematics is structured by dependencies rather than similarities, we restore this signal to both the training data and the model. We curate two underused dependency resources. We conduct the first systematic mining of 53 Lean Blueprint projects, a previously untapped corpus of 3,805 manually curated informal+formal nodes that capture rare, research-level premises absent from Mathlib4. We further pair it with the extraction of comprehensive, typed, multi-level Mathlib4 dependencies. We then introduce DAPS, a dependency-aware premise selector with a structural neighborhood encoder, a group-level contrastive objective, and a Mathlib-then-Blueprint adaptation procedure. DAPS reaches mean Recall@32 of 89.25 on Mathlib4-Heldout (+11.41 over the strong selector LeanHammer), and maintains this lead on two out-of-distribution benchmarks. Further experiments demonstrate that DAPS premises improve theorem proving on miniF2F and IMO-ProofBench. Project page: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Logic in Computer Science (cs.LO) ; Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.41536 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:59:53.622Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).