3 papers
cs.LG2026
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
Xian Qi Loye, Qinglin Su, Zhexin Zhang +5
The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text generation. Existing alignment…
cs.CL2025
ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs
Zige Wang, Qi Zhu, Fei Mi +3
Gradient-based data influence approximation has been leveraged to select useful data samples in the supervised fine-tuning of large language models. However, the computation of gra…
cs.CL2025
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Boyang Xue, Fei Mi, Qi Zhu +6
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where…