REVIEW 13 cited by
Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning
read the original abstract
Large language models have achieved significant advancements in complex mathematical reasoning benchmarks, such as MATH. However, their substantial computational requirements present challenges for practical deployment. Model quantization has emerged as an effective strategy to reduce memory usage and computational costs by employing lower precision and bit-width representations. In this study, we systematically evaluate the impact of quantization on mathematical reasoning tasks. Our results demonstrate that aggressive quantization methods like AWQ and GPTQ introduce up to 32.39% accuracy degradation (average 11.31%) on Llama-3 models, particularly in numerical computation and reasoning planning. To address this, we introduce a multidimensional evaluation framework combining qualitative capability analysis and quantitative error assessment. We further develop targeted recovery strategies, showing that fine-tuning quantized models on only 545 task-specific examples for 3 minutes on 4 GPUs effectively restores reasoning capabilities to near full-precision levels. Additionally, our error assessment pipeline achieves 98.9% accuracy in diagnosing and localizing errors across 3,366 failure cases, providing actionable insights for mitigating quantization-induced degradation.
Forward citations
Cited by 13 Pith papers
-
Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization
TASA improves task-aware mixed-precision LLM quantization by searching calibration data mixtures via gradient-trace alignment and aggregating perplexity plus reasoning sensitivity signals, enabling 3.5-bit models to m...
-
Quantizing Recursive Reasoning Models
Per-tensor 4-bit quantization of weight-tied recursive reasoners induces accumulating activation bias that kills accuracy; per-block scaling (MXInt4) restores it.
-
BitNet Text Embeddings
BITEMBED trains 1.58-bit ternary-weight LLM embedders with contrastive pre-training, supervised distillation, and multi-precision output training, matching FP16 teachers within ~0.6 MMTEB points at ~2x CPU speed.
-
BitNet Text Embeddings
BITEMBED converts LLM backbones to ternary BitNet-style encoders, adapts them with contrastive pre-training and teacher distillation, and produces text embeddings at multiple precisions that perform comparably to full...
-
Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
Post-training quantization increases overthinking errors in reasoning models; a logit penalty on curated overthinking markers reduces CoT length 12-23% without accuracy loss.
-
LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
LAQuant improves long-decoding accuracy on quantized reasoning models like Qwen3-4B by 15pp on AIME25 via layer-wise lookahead loss, achieving 3.42x speedup over FP16.
-
Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression
PARSE trains a prompt-aware linear router on dense-model outputs to select dynamic SVD ranks, improving accuracy up to 10% at 0.6 compression ratio on LLaMA-7B while delivering 2.5x prefill and 2.4x decode speedups.
-
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
FluxMoE decouples MoE expert weights from persistent GPU residency via on-demand paging, achieving up to 3x throughput gains over vLLM in memory-constrained inference without accuracy loss.
-
The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning
Reducing precision from 16-bit to 8/4-bit in multi-hop reasoning creates a quantization trap that raises net energy consumption and degrades accuracy, breaking linear scaling laws.
-
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Quantized LLMs diverge from their base models at the decision level even when accuracy is preserved, with query and key attention projections showing the greatest structural distortion under low-bit compression.
-
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
Mix-Quant quantizes prefilling to NVFP4 and keeps BF16 for decoding in agentic LLMs, achieving up to 3x prefilling speedup while largely preserving task performance on long-context and agentic benchmarks.
-
Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation
Quantizing LLMs to 4 or 8 bits cuts GPU memory by up to 75% with generally small performance changes across eight biomedical NLP benchmarks.
-
Towards EnergyGPT: A Large Language Model Specialized for the Energy Sector
Fine-tuned LLaMA 3.1-8B variants for the energy sector outperform the base model on domain QA benchmarks, with LoRA delivering similar gains at lower training cost.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.