Image de couverture de livre

Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Paglieri, Davide, Dash, Saurabh, Rocktäschel, Tim, Parker-Holder, Jack
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Multi-Agent Diagnostics for Robustness via Illuminated Diversity
par: Samvelyan, Mikayel, et autres
Publié: (2024)

Preference-Based Alignment of Discrete Diffusion Models
par: Borso, Umberto, et autres
Publié: (2025)

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
par: Samvelyan, Mikayel, et autres
Publié: (2024)

Investigating Non-Transitivity in LLM-as-a-Judge
par: Xu, Yi, et autres
Publié: (2025)

Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
par: Cook, Jonathan, et autres
Publié: (2025)

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
par: Huang, Xijie, et autres
Publié: (2024)

Interpreting the Effects of Quantization on LLMs
par: Singh, Manpreet, et autres
Publié: (2025)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
par: Su, Zunhai, et autres
Publié: (2025)

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
par: Park, Jungwoo, et autres
Publié: (2025)

TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation
par: Cook, Jonathan, et autres
Publié: (2024)

OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
par: Gadhikar, Advait, et autres
Publié: (2025)

Open-Endedness is Essential for Artificial Superhuman Intelligence
par: Hughes, Edward, et autres
Publié: (2024)

Calibration Across Layers: Understanding Calibration Evolution in LLMs
par: Joshi, Abhinav, et autres
Publié: (2025)

The Diminishing Returns of Early-Exit Decoding in Modern LLMs
par: Wei, Rui, et autres
Publié: (2026)

Imagined Autocurricula
par: Güzel, Ahmet H., et autres
Publié: (2025)

Low-Rank Quantization-Aware Training for LLMs
par: Bondarenko, Yelysei, et autres
Publié: (2024)

Continuous Approximations for Improving Quantization Aware Training of LLMs
par: Li, He, et autres
Publié: (2024)

Systematic Outliers in Large Language Models
par: An, Yongqi, et autres
Publié: (2025)

BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
par: Huang, Wei, et autres
Publié: (2024)

Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox
par: Liu, Yijun, et autres
Publié: (2024)

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
par: Cheng, Wenhua, et autres
Publié: (2023)

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
par: Shen, Xuan, et autres
Publié: (2023)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
par: Sung, Yi-Lin, et autres
Publié: (2025)

Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL
par: Pignatelli, Eduardo, et autres
Publié: (2024)

English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance
par: Borgersen, Karl Audun, et autres
Publié: (2025)

Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies
par: Liu, Terrance, et autres
Publié: (2025)

Outlier-weighed Layerwise Sampling for LLM Fine-tuning
par: Li, Pengxiang, et autres
Publié: (2024)

FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
par: Luo, Haozheng, et autres
Publié: (2026)

SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs
par: Czakó, Patrik, et autres
Publié: (2025)

Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization
par: Xiong, Boya, et autres
Publié: (2025)

Jailbreaking LLMs via Calibration
par: Lu, Yuxuan, et autres
Publié: (2026)

Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting
par: Dai, Hui, et autres
Publié: (2026)

How Does Quantization Affect Multilingual LLMs?
par: Marchisio, Kelly, et autres
Publié: (2024)

Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents
par: Paglieri, Davide, et autres
Publié: (2025)

Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction
par: Ye, Yuanchang, et autres
Publié: (2025)

What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
par: Lv, Keyu, et autres
Publié: (2026)

GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
par: Zhou, Sifan, et autres
Publié: (2025)

Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data
par: Güzel, Ahmet H., et autres
Publié: (2025)

Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs
par: Sahoo, Subramanyam
Publié: (2026)

Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs
par: Loo, Chiyan
Publié: (2025)