论文概要
研究领域: NLP 作者: Srikar Kashyap Pulipaka 发布时间: 2026-05-06 arXiv: 2605.05159中文摘要
我们介绍了SemEval-2026任务9的系统：多语言极化检测，一个涵盖22种语言的二分类任务。我们的方法使用LoRA对每个语言单独微调Gemma 3模型（12B和27B参数），并用LLM生成的合成数据进行增强。我们采用三种合成数据策略（直接生成、改写和对比对创建），使用GPT-4o-mini，并配以多阶段质量过滤流水线，包括基于嵌入的去重。我们发现，在开发集上进行每语言阈值调优可在无需重新训练的情况下带来2至4%的F1改进。我们还使用12B和27B模型预测的加权集成，并进行每语言策略选择。我们的最终系统在所有22种语言上达到平均宏F1 0.811，在所有参赛队伍中排名第2，在3种语言中获得第1名，在8种语言中进入前3。我们还发现，在开发集上表现强劲的替代架构（XLM-RoBERTa、Qwen3）在测试集上遭受了30至50%的F1下降，凸显了泛化性的重要性。原文摘要
We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma 3 models (12B and 27B parameters) per language using Low-Rank Adaptation (LoRA), augmented with synthetic data generated by a large language model (LLM). We employ three synthetic data strategies (direct generation, paraphrasing, and contrastive pair creation) using GPT-4o-mini, with a multi-stage quality filtering pipeline including embedding-based deduplication. We find that per-language threshold tuning on the development set yields 2 to 4% F1 improvements without retraining. We also use weighted ensembles of 12B and 27B model predictions with per-language strategy selection. Our final system achieves a mean macro-F1 of 0.811 across all 22 languages, ranking 2nd overall of the participating teams, with 1st place finishes in 3 languages and top-3 in 8 languages. We also find that alternative architectures (XLM-RoBERTa, Qwen3) that showed strong development set performance suffered 30 to 50% F1 drops on the test set, highlighting the importance of generalization.--- *自动采集于 2026-05-08*
#论文 #arXiv #NLP #小凯