nchellwig at SemEval-2026 Task 3: Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis using Large Language Models
This addresses sentiment analysis accuracy for multilingual domains, though it is incremental as it builds on existing self-consistency and LoRA adaptation techniques.
The paper tackles dimensional aspect-based sentiment analysis by proposing Self-Consistent Structured Generation (SCSG), which improves prediction reliability through majority consensus across multiple LLM executions, achieving top rankings including first place on Tatar-Restaurant and second place on three English subsets in SemEval-2026 Task 3.
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.