EUVIMEDEUVIMED entdecken
Crossref

ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries

Tom Yuviler, Dana Drachsler-Cohen

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 34557-34565

DOI: 10.1609/aaai.v40i41.40755 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Tom Yuviler und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite recent advances in LLMs, the task of code generation is still challenging. To cope, code selection algorithms select the best program from multiple programs generated by an LLM. However, existing algorithms can fail to identify the correct program, either because they fail to distinguish nonequivalent programs or because they rely on an LLM and assume it always correctly determines the output for every input. We present ExPairT-LLM, an exact learning algorithm for code selection that selects a program by posing two new types of queries to an LLM oracle: pairwise membership and pairwise equivalence. These queries are simpler for LLMs and enable ExPairT-LLM to identify the correct program through a tournament, which is robust to some LLM mistakes. We evaluate ExPairT-LLM on four popular code datasets. Its pass@1 (success rate) outperforms the state-of-the-art code selection algorithm on average by +13.0% and up to +27.1%. It also improves the pass@1 of LLMs performing complex reasoning by +24.0%.

Zitieren

APA

Yuviler, T., & Drachsler-Cohen, D. (2026). ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 34557-34565. https://doi.org/10.1609/aaai.v40i41.40755

Vancouver

Yuviler T, Drachsler-Cohen D. ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):34557-34565. doi:10.1609/aaai.v40i41.40755

BibTeX
@article{Yuviler2026,
  author = {Yuviler, Tom and Drachsler-Cohen, Dana},
  title = {ExPairT-LLM: Exact Learning for LLM Code Selection by Pairwise Queries},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {41},
  pages = {34557--34565},
  doi = {10.1609/aaai.v40i41.40755}
}
Kostenlos starten →