mlsanityData to 14 Oct 2026

PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration

arXiv 2609.32382 ↗First posted 26 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 26 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

20 of 26 references.

References · 20

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  2. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  3. 2024A Roadmap to Pluralistic Alignmentcited by 184
  4. 2024MaxMin-RLHF: Alignment with Diverse Human Preferencescited by 123
  5. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 113
  6. 2024WorldValuesBench: A Large-Scale Benchmark Dataset for Multi-Cultural Value Awareness of Language Modelscited by 60
  7. 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
  8. 2024PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferencescited by 54
  9. 2024Diverging Preferences: When do Annotators Disagree and do Models Know?cited by 47
  10. 2019Survey on Publicly Available Sinhala Natural Language Processing Tools and Researchcited by 46
  11. 2024Self-Pluralising Culture Alignment for Large Language Modelscited by 31
  12. 2023On Diversified Preferences of Large Language Model Alignmentcited by 26
8 more
  1. 2024Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?cited by 24
  2. 2024X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructionscited by 18
  3. 2025Cultural Learning-Based Culture Adaptation of Language Modelscited by 16
  4. 2025Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignmentcited by 9
  5. 2025SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhalacited by 6
  6. 2025SiDiaC: Sinhala Diachronic Corpuscited by 2
  7. 2026D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarioscited by 1
  8. 2026LKValues: Aligning Large Language Models with Sri Lankan Societal Valuescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
  2. 2025PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization
  3. 2025DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
  4. 2025A Comprehensive Evaluation framework of Alignment Techniques for LLMs
  5. 2025Aligning LLMs for Multilingual Consistency in Enterprise Applications
  6. 2026PLURAL: A Global Dataset for Value Alignment
  7. 2026VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
  8. 2025Benchmarking Multi-National Value Alignment for Large Language Models