3 papers
cs.LG2026
Data Selection for LLM Alignment Using Fine-Grained Preferences
Jia Zhang, Yao Liu, Chen-Xi Zhang +4
Large language models (LLMs) alignment aims to ensure that the behavior of LLMs meets human preferences. While collecting data from multiple fine-grained, aspect-specific preferenc…
cs.CL2025
Towards Effective Model Editing for LLM Personalization
Baixiang Huang, Limeng Cui, Jiapeng Liu +7
Personalization is becoming indispensable for LLMs to align with individual user preferences and needs. Yet current approaches are often computationally expensive, data-intensive,…
cs.LG2025
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
Jia Zhang, Chen-Xi Zhang, Yao Liu +5
Recent advancements in instruction tuning for large language models (LLMs) suggest that a small, high-quality dataset can significantly equip LLMs with instruction-following capabi…