arXiv Computer Science @arxiv_cs@qoto.org

GhazalBench: Usage-Grounded Evaluation of LLMs on Persian Ghazals https://arxiv.org/abs/2603.09979 #cs.CL

Explainable LLM Unlearning Through Reasoning https://arxiv.org/abs/2603.09980 #cs.LG #cs.AI #cs.CL

Large Language Models and Book Summarization: Reading or Remembering, Which Is Better? https://arxiv.org/abs/2603.09981 #cs.CL

AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic https://arxiv.org/abs/2603.09982 #cs.CL #cs.AI

MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios https://arxiv.org/abs/2603.09983 #cs.LG #cs.AI #cs.CL

An Efficient Hybrid Deep Learning Approach for Detecting Online Abusive Language https://arxiv.org/abs/2603.09984 #cs.CL

The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration https://arxiv.org/abs/2603.09985 #cs.CL #cs.AI

Quantifying Hallucinations in Language Language Models on Medical Textbooks https://arxiv.org/abs/2603.09986 #cs.CL #cs.AI

Evolving Demonstration Optimization for Chain-of-Thought Feature Transformation https://arxiv.org/abs/2603.09987 #cs.CL #cs.AI #cs.LG

A Hybrid Residue Floating Numerical Architecture with Formal Error Bounds for High Throughput FPGA Computation https://arxiv.org/abs/2603.08712 #cs.AR

Unveiling the Potential of Quantization with MXFP4: Strategies for Quantization Error Reduction https://arxiv.org/abs/2603.08713 #cs.AR #cs.AI #cs.LG #cs.PF

On the Multi-Commodity Flow with convex objective function: Column-Generation approaches https://arxiv.org/abs/2603.08714 #math.OC #cs.NI #cs.DM

VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation https://arxiv.org/abs/2603.08715 #cs.AR #cs.CL

Design Conductor: An agent autonomously builds a 1.5 GHz Linux-capable RISC-V CPU https://arxiv.org/abs/2603.08716 #cs.AR #cs.AI

Equitable Multi-Task Learning for AI-RANs https://arxiv.org/abs/2603.08717 #cs.LG #cs.NI

CktEvo: Repository-Level RTL Code Benchmark for Design Evolution https://arxiv.org/abs/2603.08718 #cs.AR #cs.AI

SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation https://arxiv.org/abs/2603.08719 #cs.AR #cs.AI #cs.SE

AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding https://arxiv.org/abs/2603.08720 #cs.AR #cs.ET

KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware https://arxiv.org/abs/2603.08721 #cs.AR #cs.LG #cs.SE

Rethinking Personalization in Large Language Models at the Token Level https://arxiv.org/abs/2603.06595 #cs.CL