AI ethics evidence index Search
Source-linked daily record
Evidence record 5085 · automatically gathered

Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three instruction-tuned models (Gemma-2-9b-it, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct) across three pruning methods (Random, Magnitude, Wanda) at four sparsity levels (10-70%) on 12,148 BBQ bias benchmark items with 5 random seeds, totaling 2,368,860 inference records. O

Record details

Published: 2 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Also mentions Mistral · Shared topic: Bias & fairness

EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage

arXiv · 5 May 2026

Also mentions Mistral · Shared topic: Bias & fairness

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science

arXiv · 12 May 2026

Also mentions Mistral · Shared topic: Bias & fairness

Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context

arXiv · 8 March 2026

Same publisher byline · Shared topic: Bias & fairness

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels

arXiv · 2 May 2026

Also mentions Mistral

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

arXiv · 1 May 2026

Also mentions Mistral

Generative AI in Academic Writing: A Comparison of DeepSeek, Qwen, ChatGPT, Gemini, Llama, Mistral, and Gemma

OpenAlex · 30 April 2026

How to cite this record

ethics.ai (2 May 2026), “Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI,” evidence record 5085, https://ethics.ai/record/5085 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.