2025.emnlp-main.235@ACL

Total: 1

#1 Recall with Reasoning: Chain-of-Thought Distillation for Mamba’s Long-Context Memory and Extrapolation [PDF] [Copy] [Kimi1] [REL]

Authors: Jun-Yu Ma, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu

Mamba’s theoretical infinite-context potential is limited in practice when sequences far exceed training lengths. This work explores unlocking Mamba’s long-context memory ability by a simple-yet-effective method, Recall with Reasoning (RwR), by distilling chain-of-thought (CoT) summarization from a teacher model. Specifically, RwR prepends these summarization as CoT prompts during fine-tuning, teaching Mamba to actively recall and reason over long contexts. Experiments on LONGMEMEVAL and HELMET show that RwR outperforms existing long-term memory methods on the Mamba model. Furthermore, under similar pre-training conditions, RwR improves the long-context performance of Mamba relative to comparable Transformer/hybrid baselines while preserving short-context capabilities, all without changing the architecture.

Subject: EMNLP.2025 - Main