Adding an inter-class cosine similarity loss and Z-score outlier scores to LLMLingua-2's BERT compressor improves long-context compression quality and on-device speed.
In Proceedings of the 61st An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16409– 16423, Toronto, Canada
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores
Adding an inter-class cosine similarity loss and Z-score outlier scores to LLMLingua-2's BERT compressor improves long-context compression quality and on-device speed.