QuantiBias: Quantization Can Increase Undetected Bias in LLMs
A new arXiv preprint reports that quantizing large language models—a common step to make them more efficient—can introduce measurable bias in open-ended text generation, even when standard safety checks show no change. The study finds that quantized models are more likely to produce stereotyped responses across eight languages, a phenomenon not detected by typical refusal rate or multiple-choice fairness metrics. The authors introduce QuantiBias, a benchmark designed to reveal this hidden bias.
Why it matters: This work highlights a previously overlooked risk in LLM deployment, showing that quantization can silently increase bias without triggering standard safety evaluations.
Full story at: arXiv Computers and Society ↗