Cover Image

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Li, Xiaoyi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

What Do Latent Action Models Actually Learn?
by: Zhang, Chuheng, et al.
Published: (2025)

Uncovering Gradient Inversion Risks in Practical Language Model Training
by: Feng, Xinguo, et al.
Published: (2025)

LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices
by: Lee, Jung Hyun, et al.
Published: (2024)

CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
by: Chen, Yutong, et al.
Published: (2026)

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
by: Tan, Zelin, et al.
Published: (2025)

Mapping Post-Training Forgetting in Language Models at Scale
by: Harmon, Jackson, et al.
Published: (2025)

How Do Electrocardiogram Models Scale?
by: Li, Jiawei, et al.
Published: (2026)

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
by: Lade, Ankit Hemant, et al.
Published: (2026)

Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages
by: Cui, Brandon, et al.
Published: (2026)

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
by: Kim, Junhan, et al.
Published: (2024)

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
by: Xu, Yongzhong
Published: (2026)

P$^2$ Law: Scaling Law for Post-Training After Model Pruning
by: Chen, Xiaodong, et al.
Published: (2024)

Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
by: Zhou, Chenxi, et al.
Published: (2025)

Are Language Models Actually Useful for Time Series Forecasting?
by: Tan, Mingtian, et al.
Published: (2024)

Scale Dependent Data Duplication
by: Kazdan, Joshua, et al.
Published: (2026)

Scaling Algorithm Distillation for Continuous Control with Mamba
by: Beaussant, Samuel, et al.
Published: (2025)

GaLore 2: Large-Scale LLM Pre-Training by Gradient Low-Rank Projection
by: Su, DiJia, et al.
Published: (2025)

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast
by: Wu, Wenhao, et al.
Published: (2026)

Zenith: Scaling up Ranking Models for Billion-scale Livestreaming Recommendation
by: Zhang, Ruifeng, et al.
Published: (2026)

On the Optimizer Dependence of Neural Scaling Laws
by: Ramani, Vansh, et al.
Published: (2026)

Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations
by: Tan, Zhen, et al.
Published: (2025)

Uncovering Scaling Laws for Large Language Models via Inverse Problems
by: Verma, Arun, et al.
Published: (2025)

Scaling and Transferability of Annealing Strategies in Large Language Model Training
by: Wang, Siqi, et al.
Published: (2025)

ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting
by: Wu, Binqing, et al.
Published: (2025)

Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
by: Wang, Siqi, et al.
Published: (2024)

BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models
by: Coscia, Dario, et al.
Published: (2026)

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
by: Viakhirev, Ivan, et al.
Published: (2026)

Interactions Across Blocks in Post-Training Quantization of Large Language Models
by: Shabanovi, Khasmamad, et al.
Published: (2024)

Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches
by: Chen, Yifang, et al.
Published: (2025)

Beyond Self-Consistency: Loss-Balanced Perturbation-Based Regularization Improves Industrial-Scale Ads Ranking
by: Ramazanli, Ilqar, et al.
Published: (2025)

Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
by: Xu, Yangshuang, et al.
Published: (2026)

Preference Learning Algorithms Do Not Learn Preference Rankings
by: Chen, Angelica, et al.
Published: (2024)

Ranking Across Different Content Types: The Robust Beauty of Multinomial Blending
by: Lichtenberg, Jan Malte, et al.
Published: (2024)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
by: Ren, Richard, et al.
Published: (2024)

CalArena: A Large-Scale Post-Hoc Calibration Benchmark
by: Berta, Eugène, et al.
Published: (2026)

VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study
by: Zhang, Zhicheng, et al.
Published: (2026)

On the Effects of Data Scale on UI Control Agents
by: Li, Wei, et al.
Published: (2024)

RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
by: Yang, Yongyi, et al.
Published: (2025)

When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
by: Wu, Boqian, et al.
Published: (2026)

Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
by: Zhang, Chengqian, et al.
Published: (2026)