LFQ improves generation accuracy of low-bit quantized LLMs by applying cross-entropy logit alignment specifically to the final block, addressing misalignment from omitted unembedding layers and MSE objectives in standard block-wise PTQ.
URL https: //aclanthology.org/2025.acl-long.498/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
LFQ improves generation accuracy of low-bit quantized LLMs by applying cross-entropy logit alignment specifically to the final block, addressing misalignment from omitted unembedding layers and MSE objectives in standard block-wise PTQ.