AI RESEARCH
END: Early Noise Dropping for Efficient and Effective Context Denoising
arXiv CS.CL
•
ArXi:2502.18915v3 Announce Type: replace Large Language Models (LLMs) have nstrated remarkable performance across a wide range of natural language processing tasks. However, they are often distracted by irrelevant or noisy context in input sequences that degrades output quality. This problem affects both long- and short-context scenarios, such as retrieval-augmented generation, table question-answering, and in-context learning. We reveal that LLMs can implicitly identify whether input sequences contain useful information at early layers, prior to token generation. Leveraging this insight, we