5 papers · 1 filter
System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
Xiaoqiang Wang, Suyuchen Wang, Yun Zhu +1
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative System-2 reasoning. However, this comes at t…
RMem: Bridging Memory Retention and Retrieval via Reversible Compression
Xiaoqiang Wang, Suyuchen Wang, Yun Zhu +1
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external stora…
FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval
Jinlin Wang, Suyuchen Wang, Ziwen Xia +4
Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts,…
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Zhiyuan Hu, Yuliang Liu, Jinman Zhao +8
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts t…
Resonance RoPE: Improving Context Length Generalization of Large Language Models
Suyuchen Wang, Ivan Kobyzev, Peng Lu +2
This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-traine…