Abstract
We present Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis in SemEval-2026 Task 3 (Track A). SCSG enhances prediction reliability by executing a LoRA-adapted large language model multiple times per instance, retaining only tuples that achieve a majority consensus across runs. To mitigate the computational overhead of multiple forward passes, we leverage vLLM's PagedAttention mechanism for efficient key--value cache reuse. Evaluation across 6 languages and 8 language--domain combinations demonstrates that self-consistency with 15 executions yields statistically significant improvements over single-inference prompting, with our system (leveraging Gemma 3) ranking in the top seven across all settings, achieving second place on three out of four English subsets and first place on Tatar-Restaurant for DimASTE.
Abstract (translated)
我们提出了自洽结构化生成(Self-Consistent Structured Generation,SCSG)方法用于SemEval-2026任务3(Track A)中的维度方面情感分析。通过多次执行一个经过LoRA调整的大规模语言模型并仅保留多轮运行中达到多数共识的元组,SCSG增强了预测的可靠性。为了减少多次前向传递带来的计算开销,我们利用了vLLM的PagedAttention机制来高效地重复使用键值缓存。 跨6种语言和8种语言-领域组合进行的评估表明,自洽性通过15次执行可以显著提升统计学上优于单一推理提示的效果。我们的系统(利用Gemma 3)在所有设置中均排名前七,在四个英语子集中的三个获得第二名,并且在塔塔尔语餐厅数据集中于DimASTE任务中获得了第一名。
URL
https://arxiv.org/abs/2603.01788