arXiv AI By Renwei Meng, Bowen Zhang, Jian Wang, Xican Wang, Haoyi Wu, Xuanyan Qiu, Shengan Yang

Know2Guess: A Contamination-Aware Multi-Zone Benchmark for Knowledge-Boundary Evaluation in Large Language Models

Read the original on arXiv AI →

arXiv:2606. 26101v1 Announce Type: cross Abstract: Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.