作者位次 #2/3ACL 2026Findings· Findings of ACL
Preserving Fairness and Safety in Quantized LLM s Through Critical Weight Protection
Muhammad Alif Al Hakim · Alfan Farizki Wicaksono · Fajri Koto
摘要
Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety, particularly in dynamic quantization and multilingual contexts, remain underexplored. In this work, we conduct a systematic study of how static and d...