Quantized LLMs diverge from their base models at the decision level even when accuracy is preserved, with query and key attention projections showing the greatest structural distortion under low-bit compression.
5th International Conference on Learning Representations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Hidden layer distillation yields systematic perplexity gains over logit KD in LLM pre-training but does not consistently improve downstream performance.
Empirical evaluation of quantization effects on eight LLMs across bit widths, showing performance generally declines at lower precision but with model-size-dependent resilience and acceptable accuracy at 2 bits for many cases.
citing papers explorer
-
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Quantized LLMs diverge from their base models at the decision level even when accuracy is preserved, with query and key attention projections showing the greatest structural distortion under low-bit compression.
-
A Study on Hidden Layer Distillation for Large Language Model Pre-Training
Hidden layer distillation yields systematic perplexity gains over logit KD in LLM pre-training but does not consistently improve downstream performance.
-
K-Quantization and its Impact on Output Performance
Empirical evaluation of quantization effects on eight LLMs across bit widths, showing performance generally declines at lower precision but with model-size-dependent resilience and acceptable accuracy at 2 bits for many cases.