Pruning attention layers in five LLMs across eight datasets maintains accuracy but degrades faithfulness and calibration.
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression
3 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
3
Pith papers citing it
2
external citations · OpenAlex
years
2026 3representative citing papers
Across 51 quantized checkpoints, quality metrics fail to predict safety drops in 36 pairings and 10 hidden-danger cases, while a new RTSI screen routes all 10 dangerous rows to testing at matched bucket size.
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
-
Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration
Pruning attention layers in five LLMs across eight datasets maintains accuracy but degrades faithfulness and calibration.
-
Quality Is Not a Safety Proxy Under Quantization
Across 51 quantized checkpoints, quality metrics fail to predict safety drops in 36 pairings and 10 hidden-danger cases, while a new RTSI screen routes all 10 dangerous rows to testing at matched bucket size.
-
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.