AI ethics evidence index Search
Source-linked daily record
Evidence record 13482 · automatically gathered

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. We find its principal side effect is increased bias that standard safety evaluation misses. Holding the model, its training, and the prompts fixed, a quantized model still refuses harmful requests, still avoids over-refusing benign prompts, and still selects the unbiased multiple-choice answer.

Record details

Published: 23 July 2026
Source: arXiv cs.HC
Category: Research
Topics: Bias & fairness
Retrieved: 25 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.

Same publisher byline · Shared topic: Bias & fairness

Fairness and Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, and Mitigation Strategies

OpenAlex · 26 December 2023

Same publisher byline

Defeat Devices in AI Systems

arXiv · 27 June 2026

Same publisher byline

Cultural Targets, Structural Frames, Binding Morals: A Cross-Lingual Audit of Online Hate in Multicultural Singapore

arXiv · 20 June 2026

Same publisher byline

GenAI against humanity: nefarious applications of generative artificial intelligence and large language models

OpenAlex · 22 February 2024

Shared topic: Bias & fairness

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

arXiv · 23 July 2026

Shared topic: Bias & fairness

Examining User Behavior and Cognitive Biases in Personal Password Security

arXiv cs.CY · 23 July 2026

How to cite this record

ethics.ai (23 July 2026), “QuantiBias: Benchmarking Quantization-Induced Bias in LLMs,” evidence record 13482, https://ethics.ai/record/13482 (originally published by arXiv cs.HC).

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.