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

• URL: http://arxiv.org/abs/2605.15208v1
• Date: Sat, 02 May 2026 05:41:47 GMT
• Title: Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
• Abstract summary: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deployment.<n>Existing studies typically compare only two conditions, rely on aggregate bias metrics, and evaluate a single model family.<n>We conduct a controlled empirical study of three instruction-tuned models at five precision levels (BF16 through 3-bit) on 12,148 BBQ bias benchmark items.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deployment, yet the impact of this compression on model quality remains poorly understood. Existing studies typically compare only two conditions (full-precision vs. a single quantized variant), rely on aggregate bias metrics, and evaluate a single model family, making it impossible to distinguish gradual degradation from threshold-dependent safety failures. We conduct a controlled empirical study of three instruction-tuned models (Qwen2.5-7B, Mistral-7B, Phi-3.5-mini) at five precision levels (BF16 through 3-bit) on 12,148 BBQ bias benchmark items across 5 random seeds, totaling 911,100 inference records. Our results reveal that 3-bit quantization causes 6-21% of previously unbiased items to develop new stereotypical behaviors, following a clear dose-response pattern confirmed via logistic regression, while models' willingness to select "unknown" answers declines by 17.4%. Crucially, these item-level changes are invisible to standard quality metrics: perplexity increases by less than 0.5% at 8-bit and under 3% at 4-bit across all three models, yet 2.5-5.6% of items already develop new biases at 4-bit. These findings demonstrate that aggregate evaluation metrics systematically miss fairness-critical degradation, underscoring the need for quality-aware compression protocols that explicitly test for bias emergence before deployment.

Related papers

• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• Small Foundation Models of Human Cognition and Behaviour [45.88028371034407]
  We train 14 models from 135M to 14B parameters across four architecture families on Psych-101.<n>Psych-101 is a dataset of 10.7 million trial-level choices from 160 experiments.<n>We show that small cognitively fine-tuned models show promise as noise ceiling estimators for psychological experiments.
  arXiv  Detail & Related papers  (2026-08-05T11:34:20Z)
• Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts [0.0]
  We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.<n>We classify 30,000 chain-of-thought outputs from five instruction-tuned LLMs across three quantization precisions.<n>We find that while accuracy is robust across precisions, Hollow Convergence shows a significant size-dependent shift under NF4.
  arXiv  Detail & Related papers  (2026-07-10T21:55:05Z)
• Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI [0.0]
  We show that activation-aware pruning (Wanda) preserves perplexity nearly perfectly (just 3.5% increase at 50% sparsity for Mistral-7B) yet produces the highest bias amplification.<n>Random pruning destroys language capability entirely (perplexity exceeding $104$ and reaching $108$) but produces only random-chance bias.<n>We further show that unstructured pruning provides zero storage savings and zero inference latency reduction on real edge hardware.
  arXiv  Detail & Related papers  (2026-05-02T05:27:40Z)
• MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models [0.0]
  MIRROR is a benchmark that evaluates whether large language models can use self-knowledge to make better decisions.<n>We evaluate 16 models from 8 labs across approximately 250,000 evaluation instances.
  arXiv  Detail & Related papers  (2026-04-15T08:41:12Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• Brevity Constraints Reverse Performance Hierarchies in Language Models [0.0]
  On 7.7% of benchmark problems, larger language models underperform smaller ones by 28.4 percentage points despite 10-100x more parameters.<n>We identify the mechanism as spontaneous scale-dependent verbosity that introduces errors through overelaboration.<n>Our results establish that maximizing large model performance requires scale-aware prompt engineering.
  arXiv  Detail & Related papers  (2026-03-11T06:47:41Z)
• Uncertainty Drives Social Bias Changes in Quantized Large Language Models [3.921671869527028]
  Post-training quantization reduces the computational cost of large language models.<n>We present the first large-scale study of 50 quantized models evaluated on PostTrainingBiasBench.
  arXiv  Detail & Related papers  (2026-02-05T20:37:26Z)
• The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs [0.0]
  We evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family.<n>We replicate the effect across nine modern open-weights models.
  arXiv  Detail & Related papers  (2025-11-25T09:25:33Z)
• Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning [70.56067503630486]
  We argue that sixth-generation (6G) intelligence is not fluent token prediction but calibrated the capacity to imagine and choose.<n>We show that WM-MS3M cuts mean absolute error (MAE) by 1.69% versus MS3M with 32% fewer parameters and similar latency, and achieves 35-80% lower root mean squared error (RMSE) than attention/hybrid baselines with 2.3-4.1x faster inference.
  arXiv  Detail & Related papers  (2025-11-04T17:22:22Z)
• Reasoning Models Are More Easily Gaslighted Than You Think [85.84943447589511]
  We evaluate three state-of-the-art reasoning models, including OpenAI's o4-mini, Claude-3.7-Sonnet and Gemini-2.5-Flash.<n>Our evaluation reveals significant accuracy drops following gaslighting negation prompts.<n>We introduce GaslightingBench-R, a new diagnostic benchmark designed to evaluate reasoning models' susceptibility to defend their belief.
  arXiv  Detail & Related papers  (2025-06-11T12:52:25Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization [73.60493264901359]
  We present a unified framework for rigorous comparisons across 1-bit, 1.58-bit, 2-bit, 3-bit, and 4-bit quantization settings.<n>We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off.<n>Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• Sharpness-aware Quantization for Deep Neural Networks [45.150346855368]
  Sharpness-Aware Quantization (SAQ) is a novel method to explore the effect of Sharpness-Aware Minimization (SAM) on model compression. We show that SAQ improves the generalization performance of the quantized models, yielding the SOTA results in uniform quantization.
  arXiv  Detail & Related papers  (2021-11-24T05:16:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.