arXiv Computation and Language By Yuan Wu, Mairui Li, Lesia Semenova, Chudi Zhong

The Asymmetric Harms of LLM Compression

Read the original on arXiv Computation and Language →

arXiv:2608. 19670v1 Announce Type: new Abstract: Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers
6d ago

The Asymmetric Harms of LLM Compression

Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In this work, we systematically evaluate 3 LLMs across 11 compression methods to investigate the effects of compression on knowledge retention, model confidence, and social bias.