arXiv：cs.CL· Vihindi Kotalawala, Nevidu Jayatilleke·· 3 小时前
PlurVA-LLM 2026 Shared Task Track-1：用多语言微调与阈值校准实现 LLM 多元价值对齐
PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration
AI 导读
针对 PlurVA-LLM 2026 Shared Task Track-1 中国、印尼、斯里兰卡三地的多元价值对齐任务，该团队用 4-bit QLoRA 微调 Llama 3.1 8B Instruct，并分别采用选项排列增强、标注者投票扩展和二元重构加 SinhalaMMLU 增强处理三地数据，还对斯里兰卡数据做了条件阈值校准。
正文
Abstract:We present our system for the PlurVA-LLM 2026 Shared Task Track-1, which focuses on pluralistic value alignment in the contexts of China, Indonesia, and Sri Lanka. For this resource-constrained track, we fine-tuned Llama 3.1 8B Instruct using 4-bit QLoRA. Our approach combines option-permutation augmentation for Chinese data, annotator vote expansion for Indonesian data, and binary reformulation with SinhalaMMLU augmentation for Sri Lankan data. We further applied conditional threshold calibration to the predictions for the Sri Lankan data. The final system achieved accuracies of 0.785 for Chinese, 0.715 for Indonesian, and 0.916 for Sri Lankan, resulting in an overall macro-average accuracy of 0.805.
| Comments: | 11 pages, 6 figures, 6 tables, Accepted paper at the first workshop on Pluralistic Value Alignment of LLMs @ AACL-IJCNLP 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.32382 [cs.CL] |
| (or arXiv:2609.32382v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.32382 arXiv-issued DOI via DataCite |
Submission history
From: Nevidu Jayatilleke Mr. [view email]
[v1]
Sat, 26 Sep 2026 08:56:11 UTC (917 KB)
[v2]
Thu, 8 Oct 2026 11:56:29 UTC (950 KB)
来源：arXiv：cs.CL · arxiv.org