Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
Large language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT) reasoning. However, the internal mechanisms underlying this improvement remain unclear. We investigate these mechanisms through a needle-in-a-haystack (NIAH) counting task, where an LLM is asked to count th...
Liang Twist Shan, Tian-Yu Hu, Hao Yan et al.
· 0 citations