3 papers
cs.CL2026
M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
Chunguang Zhao, Yilun Liu, Pufan Zeng +10
Multilingual instruction fine-tuning (IFT) empowers large language models to generalize across diverse linguistic and cultural contexts; however, high-quality, systematically curat…
cs.CL2026
C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment
Pufan Zeng, Yilun Liu, Mingchen Dai +12
Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initial step is seed curation; ho…
cs.CV2026
Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation
Minggui He, Mingchen Dai, Jian Zhang +5
Vision-Language Models (VLMs) have shown promise in generating plotting code from chart images, yet achieving structural fidelity remains challenging. Existing approaches largely r…