{"schema":"hottub-news/story/v1","story":"st_zimss4bakesa6o6o5ogq","title":"ORCA: Evaluating LLMs on Data Science Code Translation","title_en":null,"outlets":1,"brief":null,"page":"https://hottub.news/stories/orca-evaluating-llms-on-data-science-code-translation-zimss4bake","count":1,"items":[{"id":"n_zimss4bakesa6o6o5ogq","seq":340938,"kind":"article","title":"ORCA: Evaluating LLMs on Data Science Code Translation","url":"https://arxiv.org/abs/2609.30749","summary":"arXiv:2609.30749v1 Announce Type: new Abstract: Data Science Code Translation (DSCT) is the process of converting code between data science libraries while preserving functional equivalence and enabling interoperability across data science ecosystems. While Large Language Models (LLMs) have demonstrated considerable progress in Data Science Code Generation (DSCG), their performance in DSCT remains insufficiently studied. To address this gap, we introduce ORCA, a…","published":"2026-09-28T04:00:00Z","seen":"2026-09-28T04:38:16Z","lang":"en","source":{"id":"kite-export-arxiv-org-f680e9","name":"export.arxiv.org","domain":"export.arxiv.org"},"via":"kite-export-arxiv-org-f680e9","topics":["ai","cs.ai"],"authors":["Xiaolong Li, Jinyang Li, Bowen Qin, Ge Qu, Nan Huo, Xiaohan Xu, Shipei Lin…"],"entities":[{"id":"Q1024483","name":"Orca","type":"other"}],"story":"st_zimss4bakesa6o6o5ogq","category":"science-technology","category_p":0.7300000190734863,"sentiment":"neutral","tone":0.14000000059604645,"political":0.03999999910593033}]}