4 papers
Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio
Yijiong Yu, Shuai Yuan, Jie Zheng +2
Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing f…
SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
Yijiong Yu, Jiale Liu, Qingyun Wu +2
The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest spar…
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps
Yijiong Yu, Yongfeng Huang, Zhixiao Qi +4
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…
OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training
Yijiong Yu, Ziyun Dai, Zekun Wang +3
Large language models (LLMs) have demonstrated remarkable capabilities, but their success heavily relies on the quality of pretraining corpora. For Chinese LLMs, the scarcity of hi…