13 papers
PolicyLong: Towards On-Policy Context Extension
Junlong Jia, Ziyang Chen, Xing Wu +4
Extending LLM context windows is hindered by scarce high-quality long-context data. Recent methods synthesize data with genuine long-range dependencies via information-theoretic ve…
LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference
Guangyuan Ma, Yongliang Ma, Xuanrui Gou +3
Large Language Models (LLMs)-based text retrieval retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arri…
MiLe Loss: a New Entropy-Weighed Loss for Mitigating the Bias of Learning Difficulties in Large Language Models
Zhenpeng Su, Xing Wu, Xue Bai +5
Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonst…
LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark
Ziyang Chen, Xing Wu, Junlong Jia +4
The rapid expansion of context length in large language models (LLMs) has outpaced existing evaluation benchmarks. Current long-context benchmarks often trade off scalability and r…
EntropyLong: Effective Long-Context Training via Predictive Uncertainty
Junlong Jia, Ziyang Chen, Xing Wu +5
Training long-context language models to capture long-range dependencies requires specialized data construction. Current approaches, such as generic text concatenation or heuristic…
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
Minxuan Lv, Zhenpeng Su, Leiyu Pan +10
As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning…