arXivLingfei Qian, Yan Wang, Xueqing Peng, Yupeng Cao, Yuechen Jiang, Zhuohan Xie, Anke Xu, Wenbo Cao, Jiarui Chen, Zehan Li, Jimin Huang, Alejandro Lopez-Lira, Yuehua Tang, Sophia Ananiadou, Jian-Yun NieWed, Nov 4, 2026, 9:24 AM PST
score 17.0
AI models can't reliably tell what they know about the past
Original: LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting
Source: arxiv.org ↗
Writing ELI5 summary…