Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
Summary
This paper demonstrates that post-training quantization can silently alter how large language models reason, even when task accuracy is preserved, through a taxonomy-based analysis of 30,000 chain-of-thought outputs across multiple models and benchmarks.
View Cached Full Text
Cached at: 07/14/26, 04:21 AM
# Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts Source: [https://arxiv.org/abs/2607.09999](https://arxiv.org/abs/2607.09999) [View PDF](https://arxiv.org/pdf/2607.09999) > Abstract:We show that post\-training quantization can silently alter how large language models reason even when task accuracy is preserved\. Using a six\-category failure taxonomy validated by two independent human annotators \(Cohen's $\\kappa$ = 0\.906\), we classify 30,000 chain\-of\-thought outputs from five instruction\-tuned LLMs \(3B\-\-14B parameters\) across three quantization precisions \(FP32, FP16, NF4\) and four reasoning benchmarks\. We find that while accuracy is robust across precisions \(maximum 3\.1 pp drop\), Hollow Convergence \(correct answers reached through incomplete or unverifiable reasoning\) shows a significant size\-dependent shift under NF4, dropping sharply for the two smallest models tested but remaining invariant for models at 12B parameters and above\. This effect is also benchmark\-specific: GSM8K is categorically immune while LogiQA and ARC\-Challenge show the largest shifts\. Furthermore, under NF4, Shortcut Collapse rises from 44% to 78% of wrong\-answer failures in LLaMA 3\.2\-3B while Confidence Snowballing collapses from 15\.8% to near zero, a qualitative shift invisible to accuracy metrics\. Finally, we show Hollow Convergence cannot be reliably detected from surface\-level text features \(best F1 = 0\.53\), establishing it as a deployment\-relevant failure mode that standard evaluation pipelines cannot catch\. ## Submission history From: Renuka Oladri \[[view email](https://arxiv.org/show-email/8aee97f3/2607.09999)\] **\[v1\]**Fri, 10 Jul 2026 21:55:05 UTC \(467 KB\)
Similar Articles
From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization
Researchers identify two distinct failure modes in aggressive LLM quantization—Signal Degradation and Computation Collapse—and show that training-free fixes only remedy the former, indicating structural reconstruction is needed for ultra-low-bit models.
Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels
This paper studies how post-training quantization introduces new biases in instruction-tuned LLMs, finding that 3-bit precision causes 6–21% of previously unbiased items to develop stereotypes, while standard metrics like perplexity fail to detect this degradation.
How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures
This paper characterizes two distinct processes by which language models fail in reasoning—committed failure and persistent uncertainty—using token-level uncertainty signals, and demonstrates implications for self-consistency and failure detection strategies.
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
This paper reveals that aggressive post-training quantization of reasoning models leads to increased overthinking errors, where models reach correct intermediate answers but fail to finalize them. A simple logit penalty on overthinking markers reduces chain-of-thought length by 12-23% while improving accuracy, especially for quantized models.
Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations
This paper presents a comprehensive empirical evaluation of how large language models handle corruptions in chain-of-thought reasoning steps, testing 13 models across 5 perturbation types (MathError, UnitConversion, Sycophancy, SkippedSteps, ExtraSteps) on mathematical reasoning tasks. The findings reveal heterogeneous vulnerability patterns with implications for deploying LLMs in multi-stage reasoning pipelines.