Metraipolis › archive › dc_fc289f46c803
Prompt Less, Infer More: Static Analysis-Guided LLM Type Annotation for Python — arXiv:2610.41617
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41617
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:42:19.461Z
- SHA-256 of the archived text
ab9daaabca31da2a06648ff05c4a67c6882a0efa8cb96a5c9325619210040f4e- Stable URL of this page
https://metraipolis.com/documento/dc_fc289f46c803
How to cite
Prompt Less, Infer More: Static Analysis-Guided LLM Type Annotation for Python — arXiv:2610.41617 — arXiv (en), https://arxiv.org/abs/2610.41617 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc289f46c803 (Metraipolis archive dc_fc289f46c803, sha256 ab9daaabca31da2a06648ff05c4a67c6882a0efa8cb96a5c9325619210040f4e)
BibTeX
@misc{dcfc289f46c803,
title = {Prompt Less, Infer More: Static Analysis-Guided LLM Type Annotation for Python — arXiv:2610.41617},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41617},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc289f46c803; sha256 ab9daaabca31da2a06648ff05c4a67c6882a0efa8cb96a5c9325619210040f4e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41617. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Type annotations improve the maintainability and reliability of Python programs, but many real-world projects remain under-annotated because manual annotation is time-consuming and error-prone. Recent neural and LLM-based type inference systems can recover missing annotations, yet they often trade accuracy for efficiency. Existing approaches often fail to exploit project-wide type evidence, or do so inefficiently through unnecessary model calls and noisy prompts. We present SALT, an LLM-based type inference system guided by static analysis. SALT integrates static analysis with LLM inference to resolve types statically, prioritize LLM queries, and construct concise type-aware context. To demonstrate the effectiveness of SALT, we evaluated it on 12 real-world Python projects. SALT achieves the best accuracy among the evaluated systems and reduces estimated LLM cost by up to 78.5% compared with a strong coding-assistant baseline. It also shows similar cost savings with the frontier model GPT-5.5, demonstrating that SALT remains effective with strong LLMs. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2610.41617 — 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 2026-11-03T05:26:33.105Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).