PALI at SemEval-2026 Task 3: LoRA Fine-Tuning with Validation for DimABSA

AbstractWe describe the PALI system submitted to SemEval-2026 Task~3 (Dimensional Aspect-Based Sentiment Analysis), which requires predicting valence–arousal (VA) scores and extracting structured sentiment tuples across multiple languages.Our final system centers on LoRA fine-tuning of Qwen3-32B using Llama-Factory, together with data conversion/cleaning, multilingual data-mixing strategies, and inference-time validation and repair.We additionally explored retrieval-based few-shot prompting with BGE-M3, but found it less effective for learning consistent VA scoring preferences.On Track~A, our final system uses per-language LoRA adapters that mix all subtasks per language for a better trade-off between performance and efficiency.On the official test set, we achieve average per-language scores of 1.2071 RMSE\VA for Subtask~1 and 0.5641/0.4905 cF1 for Subtask~2/3.On the development set, we find that per-language-per-task adapters further improve extraction cF1 but are less attractive in terms of training and deployment cost.For Track~B, we report results for VA prediction on five languages and two domains.