Cover Image

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Matsutani, Kohsei, Minegishi, Gouki, Kojima, Takeshi, Iwasawa, Yusuke, Matsuo, Yutaka
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
by: Matsutani, Kohsei, et al.
Published: (2025)

Understanding Emergent Misalignment via Feature Superposition Geometry
by: Minegishi, Gouki, et al.
Published: (2026)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
by: Feng, Jingyuan, et al.
Published: (2026)

Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
by: Furuta, Hiroki, et al.
Published: (2024)

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
by: Minegishi, Gouki, et al.
Published: (2025)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
by: Minegishi, Gouki, et al.
Published: (2025)

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
by: Minegishi, Gouki, et al.
Published: (2023)

Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar
by: Gambardella, Andrew, et al.
Published: (2025)

Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models
by: Cao, Qi, et al.
Published: (2026)

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
by: Minegishi, Gouki, et al.
Published: (2025)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
by: Gambardella, Andrew, et al.
Published: (2024)

Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability
by: Kim, Bum Jun, et al.
Published: (2026)

Mechanism of Task-oriented Information Removal in In-context Learning
by: Cho, Hakaze, et al.
Published: (2025)

Thinking While Listening: Fast-Slow Recurrence for Long-Horizon Sequential Modeling
by: Takashiro, Shota, et al.
Published: (2026)

C-voting: Confidence-Based Test-Time Voting without Explicit Energy Functions
by: Kubo, Kenji, et al.
Published: (2026)

A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics
by: Kojima, Takeshi, et al.
Published: (2025)

ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making
by: Watanabe, Yusuke, et al.
Published: (2026)

$\infty$-MoE: Generalizing Mixture of Experts to Infinite Experts
by: Takashiro, Shota, et al.
Published: (2026)

Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
by: Wang, Ru, et al.
Published: (2025)

NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks
by: Hao, Yongchang, et al.
Published: (2024)

Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?
by: Uchiyama, Fumiya, et al.
Published: (2024)

ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate
by: Taniguchi, Shohei, et al.
Published: (2024)

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
by: Gu, Xiaojie, et al.
Published: (2026)

How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
by: Dionisopoulos, Lucas, et al.
Published: (2026)

DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
by: Yu, Xiaoming, et al.
Published: (2026)

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
by: Hu, Pingbang, et al.
Published: (2026)

GeneZip: Region-Aware Compression for Long Context DNA Modeling
by: Zhao, Jianan, et al.
Published: (2026)

GenORM: Generalizable One-shot Rope Manipulation with Parameter-Aware Policy
by: Kuroki, So, et al.
Published: (2023)

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
by: Guo, Yipin, et al.
Published: (2026)

AlphaZip: Neural Network-Enhanced Lossless Text Compression
by: Narashiman, Swathi Shree, et al.
Published: (2024)

When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
by: Zhang, Nan, et al.
Published: (2025)

KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
by: Kumaresan, Ramchand
Published: (2026)

Enhancing Unimodal Latent Representations in Multimodal VAEs through Iterative Amortized Inference
by: Oshima, Yuta, et al.
Published: (2024)

Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
by: Akter, Syeda Nahida, et al.
Published: (2025)

How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
by: Zhu, Rui, 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)

Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
by: Chandra, Abhranil, et al.
Published: (2025)

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
by: Pengmei, Zihan, et al.
Published: (2025)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
by: Li, Ming, et al.
Published: (2025)

Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Training
by: Odonchimed, Sodtavilan, et al.
Published: (2025)