{"ID":2866495,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.01250","arxiv_id":"2510.01250","title":"GemDetox at TextDetox CLEF 2025: Enhancing a Massively Multilingual Model for Text Detoxification on Low-resource Languages","abstract":"As social-media platforms emerge and evolve faster than the regulations meant to oversee them, automated detoxification might serve as a timely tool for moderators to enforce safe discourse at scale. We here describe our submission to the PAN 2025 Multilingual Text Detoxification Challenge, which rewrites toxic single-sentence inputs into neutral paraphrases across 15 typologically diverse languages. Building on a 12B-parameter Gemma-3 multilingual transformer, we apply parameter-efficient LoRA SFT fine-tuning and prompting techniques like few-shot and Chain-of-Thought. Our multilingual training corpus combines 3,600 human-authored parallel pairs, 21,600 machine-translated synthetic pairs, and model-generated pairs filtered by Jaccard thresholds. At inference, inputs are enriched with three LaBSE-retrieved neighbors and explicit toxic-span annotations. Evaluated via Style Transfer Accuracy, LaBSE-based semantic preservation, and xCOMET fluency, our system ranks first on high-resource and low-resource languages. Ablations show +0.081 joint score increase from few-shot examples and +0.088 from basic CoT prompting. ANOVA analysis identifies language resource status as the strongest predictor of performance ($η^2$ = 0.667, p \u003c 0.01).","short_abstract":"As social-media platforms emerge and evolve faster than the regulations meant to oversee them, automated detoxification might serve as a timely tool for moderators to enforce safe discourse at scale. We here describe our submission to the PAN 2025 Multilingual Text Detoxification Challenge, which rewrites toxic single-...","url_abs":"https://arxiv.org/abs/2510.01250","url_pdf":"https://arxiv.org/pdf/2510.01250v1","authors":"[\"Trung Duc Anh Dang\",\"Ferdinando Pio D'Elia\"]","published":"2025-09-24T10:06:40Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Transformer\",\"LoRA\"]","has_code":false}