arXiv Computer Science @arxiv_cs@qoto.org

Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World https://arxiv.org/abs/2603.04408 #cs.CL

Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework https://arxiv.org/abs/2603.04409 #cs.CL #cs.AI #cs.HC

SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models https://arxiv.org/abs/2603.04410 #cs.CL #cs.AI

One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache https://arxiv.org/abs/2603.04411 #cs.CL #cs.AI #cs.LG