PruneRec prunes attention heads, embedding dimensions, MLP units, and layers from a recommendation-tuned LLM, retaining 88% of accuracy with under 5% of non-embedding parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning
PruneRec prunes attention heads, embedding dimensions, MLP units, and layers from a recommendation-tuned LLM, retaining 88% of accuracy with under 5% of non-embedding parameters.