Mitigating memorization in LLMs

• inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.

Benchmarks built on historical outcomes can reward memorized answers. This shows how to detect that and use inference-time divergence decoding to reduce it.

• articleMemorization Diagnostics for Code LLMs Should be Scale-AwarePrateek Kumar Rajput, Abdoul Aziz Bonkoungou, Alberick Euraste Djir\'e, Xunzhu Tang, Yewei Song, Iyiola Emmanuel Olatunji, El Hacen Diallo, Jacques Klein, Tegawend\'e F. Bissyand\'e
• articleAre the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon StatementsXinke Tong, Xuanming Zhang, Tianyi Tang, An Yang, Jiatu Hu, Guojie Lin, Zhenzhen Shi, Lingfeng Zeng, Boyu Yang, Bing Zhao, Hu Wei, Lin Qu, Dayiheng Liu
• articleWhen Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM AgentsShweta Mishra, Shashank Mishra

Checking sign-in…

Loading comments…