English

Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps

Computation and Language 2025-08-27 v9

Abstract

Long-context language models (LCLMs), characterized by their extensive context window, are becoming popular. However, despite the fact that they are nearly perfect at standard long-context retrieval tasks, our evaluations demonstrate they fail in some basic cases. Later, we find they can be well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts. This result emphasizes the potential necessity of solving specific long-context tasks using long-CoT methods, while previous long-context benchmarks always ignore the necessity of long reasoning for long-context tasks and treat them as direct QA tasks.

Keywords

Cite

@article{arxiv.2410.04422,
  title  = {Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps},
  author = {Yijiong Yu and Yongfeng Huang and Zhixiao Qi and Wei Wang and Weifeng Liu and Ran Chen and Ji Pei},
  journal= {arXiv preprint arXiv:2410.04422},
  year   = {2025}
}

Comments

Our code is publicly available at https://github.com/yuyijiong/hard_retrieval_for_llm and the datasets is at https://huggingface.co/datasets/yuyijiong/difficult_retrieval

R2 v1 2026-06-28T19:10:10.758Z