Guo, H., Dennis, S., Patil, R., & Shabahang, K. (2026). When Mean CE Fails: Median CE Can Better Track Language Model Quality.
Chicago Style (17th ed.) CitationGuo, Hao, Simon Dennis, Rivaan Patil, and Kevin Shabahang. When Mean CE Fails: Median CE Can Better Track Language Model Quality. 2026.
MLA (9th ed.) CitationGuo, Hao, et al. When Mean CE Fails: Median CE Can Better Track Language Model Quality. 2026.
Warning: These citations may not always be 100% accurate.