How Divergence Becomes Decision Flips in Compressed Language Models

arXiv:2610.00694 · cs.CL, cs.AI, cs.LG, stat.ML · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI, cs.LG, stat.ML

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Quantization — 36× in this paper · explained in 12 episodes
• Speculative Decoding — 19× in this paper · explained in 2 episodes
• Accuracy — 14× in this paper · explained in 1 episode
• Pruning — 12× in this paper · explained in 4 episodes
• Calibration — 10× in this paper · explained in 7 episodes
• In International Conference on Learning Representations — 7× in this paper
• Transformer — 6× in this paper · explained in 2 episodes
• Elias — 5× in this paper · explained in 2 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• In International Conference on Machine Learning — 5× in this paper
• KV cache — 5× in this paper · explained in 3 episodes
• Quantization-Aware Training — 4× in this paper · explained in 3 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Anisotropy — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Mixture of Experts — 2× in this paper · explained in 2 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
• SliceGPT: Compress Large Language Models by Deleting Rows and Columns
• QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
• Program Synthesis with Large Language Models
• On the Reproducibility of Neural Network Predictions
• Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
• QuIP: 2-Bit Quantization of Large Language Models With Guarantees
• Accelerating Large Language Model Decoding with Speculative Sampling
• Training Verifiers to Solve Math Word Problems
• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
• SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
• The case for 4-bit precision: k-bit Inference Scaling Laws
• HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
• Accuracy is Not All You Need
• Extreme Compression of Large Language Models via Additive Quantization
• SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
• GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
• Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning
• Gemma 3 Technical Report
• A Survey of Quantization Methods for Efficient Neural Network Inference

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering