FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization

arXiv:2610.14934 · cs.CL · Submitted 2026-10-10 · Read on arXiv

cs.CL

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/AI-Efficiency/FidelityQ

Terminology

• Fidelity — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• The Llama 3 Herd of Models
• Distilling the Knowledge in a Neural Network
• Qift: Shift-Friendly No-Zero W2 Post-Training Quantization for Rotated W2A4/KV4 LLM Inference
• Qwen3 Technical Report
• Code Llama: Open Foundation Models for Code
• LLaMA: Open and Efficient Foundation Language Models
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• GPTVQ: The Blessing of Dimensionality for LLM Quantization
• RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
• Using large language models for embodied planning introduces systematic safety risks

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