2 papers
cs.AI2026
Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints
Songping Peng, Zhiheng Zhang, Daojian Zeng +2
Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmfu…
cs.CL2023
KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
Zhanglin Wu, Min Zhang, Ming Zhu +5
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation. In this paper, we incorporate multilingual knowledge graph into BERTScore a…