Researchers Ioana Grigore and Sergiu Nisioi have introduced a novel hybrid pipeline designed to mitigate gender bias in English-to-Romanian machine translation, addressing the challenge of translating from a gender-neutral language to a highly gendered one. The proposed architecture integrates a fine-tuned Large Language Model (LLM) with a neural machine translation (NMT) system. In the first stage, the LLM performs gender classification to detect the intended gender of target words within English sentences, subsequently inserting inline gender hint tags. These tagged inputs are then processed by a Transformer-based model specifically fine-tuned to generate morphologically accurate Romanian translations based on the provided hints. To facilitate this method, the authors developed three new datasets specifically for gender disambiguation and translation tasks. Experimental results demonstrate that this approach significantly outperforms baseline NMT systems, achieving an improvement in gender accuracy of over 40 percentage points on the WinoMT and WinoGender benchmarks. This research represents the first methodology to explicitly tackle and evaluate gender bias in English-Romanian translation through the combined use of LLM inference and tag-aware translation techniques.