{"ID":2841446,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.10868","arxiv_id":"2511.10868","title":"Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go","abstract":"Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world developer workflows such as unit test generation. To address this gap, we introduce GO UT Bench, a benchmark dataset of 5264 pairs of code and unit tests, drawn from 10 permissively licensed Golang repositories spanning diverse domain. We evaluate its effectiveness as a fine tuning dataset across two LLM families i.e. mixture of experts and dense decoders. Our results show that finetuned models outperform their base counterparts on more than 75% of benchmark tasks.","short_abstract":"Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world devel...","url_abs":"https://arxiv.org/abs/2511.10868","url_pdf":"https://arxiv.org/pdf/2511.10868v2","authors":"[\"Yashshi Pipalani\",\"Hritik Raj\",\"Rajat Ghosh\",\"Vaishnavi Bhargava\",\"Debojyoti Dutta\"]","published":"2025-11-14T00:35:00Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Mixture of Experts\",\"Large Language Model\"]","has_code":false}