3 papers
cs.CL2026
Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
Julia Belikova, Danila Rozhevskii, Dennis Svirin +2
Efficient long-context processing remains a crucial challenge for contemporary large language models (LLMs), especially in resource-constrained environments. Soft compression archi…
cs.CL2024
xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics
Daniil Larionov, Mikhail Seleznyov, Vasiliy Viskov +2
State-of-the-art trainable machine translation evaluation metrics like xCOMET achieve high correlation with human judgment but rely on large encoders (up to 10.7B parameters), maki…
cs.CL2024
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers
Viktoriia Chekalina, Anna Rudenko, Gleb Mezentsev +3
The performance of Transformer models has been enhanced by increasing the number of parameters and the length of the processed text. Consequently, fine-tuning the entire model beco…