Hugging Face Trending Papers August 20, 2026

The Asymmetric Harms of LLM Compression

Read the original on Hugging Face Trending Papers →

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.

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 Hugging Face Trending Papers.

arXiv Computation and Language

5d ago

The Asymmetric Harms of LLM Compression

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.

By Yuan Wu, Mairui Li, Lesia Semenova, Chudi Zhong

llms safety

arXiv AI

Jul 22

Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles

arXiv:2607. 18269v1 Announce Type: new Abstract: The wisdom of crowds -- the finding that aggregating judgments across individuals often outperforms the best individual -- has been extensively studied with human forecasters.

By Igor Douven

llms

Hugging Face Trending Papers

Jun 23

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

As Large Language Models are increasingly deployed in critical applications, robustly evaluating their social biases is paramount. However, the current literature suffers from widespread methodological fragmentation, which yields contradictory conclusions.

llms benchmarks safety

arXiv AI

Jun 24

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

arXiv:2606. 24083v1 Announce Type: cross Abstract: "Talk short.

By Morayo Danielle Adeyemi, Ryan A. Rossi, Franck Dernoncourt

llms benchmarks

Hugging Face Trending Papers

Jul 23

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs

Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.

llms efficiency benchmarks safety

arXiv AI

Jun 2

Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning

arXiv:2606. 00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely attributed to the advent of Large Language Models and their misalignment with natural language usage.

By Xiaoyang Ming, Jose Hernandez, Thomas Stephan Juzek

llms reinforcement-learning safety

One email a morning, machine-written

Related stories

The Asymmetric Harms of LLM Compression

Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles

To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs

Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning