LLM pruning damages the internal features used to detect false statements; the proposed TPLO method reallocates sparsity to protect them, though the measured improvements are modest and potentially confounded by leakage from the evaluation data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
LLM pruning damages the internal features used to detect false statements; the proposed TPLO method reallocates sparsity to protect them, though the measured improvements are modest and potentially confounded by leakage from the evaluation data.