Cover Image

Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Park, Jaesung R., Kim, Junsu, Kim, Gyeongman, Jo, Jinyoung, Choi, Sean, Cho, Jaewoong, Ryu, Ernest K.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Simple Drop-in LoRA Conditioning on Attention Layers Will Improve Your Diffusion Model
by: Choi, Joo Young, et al.
Published: (2024)

LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)
by: Kim, Junsu, et al.
Published: (2025)

Pruning and Distilling Mixture-of-Experts into Dense Language Models
by: Kim, Junhyuck, et al.
Published: (2026)

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
by: Su, Zhenpeng, et al.
Published: (2025)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
by: Marshall, Noah, et al.
Published: (2024)

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
by: Su, Zhenpeng, et al.
Published: (2025)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
by: Zhang, Bonan, et al.
Published: (2025)

ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval
by: Kim, Ji-Hyeon, et al.
Published: (2026)

Jailbreaking Multimodal Large Language Models using Multi-Clip Video
by: Kang, Choongwon, et al.
Published: (2026)

Image Clustering Conditioned on Text Criteria
by: Kwon, Sehyun, et al.
Published: (2023)

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
by: Chen, Peter, et al.
Published: (2025)

Unsupervised-to-Online Reinforcement Learning
by: Kim, Junsu, et al.
Published: (2024)

Clipping-Free Policy Optimization for Large Language Models
by: Çağatan, Ömer Veysel, et al.
Published: (2026)

Weight Clipping for Deep Continual and Reinforcement Learning
by: Elsayed, Mohamed, et al.
Published: (2024)

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level
by: Khah, Saleh Vatan, et al.
Published: (2025)

Task Diversity Shortens the ICL Plateau
by: Kim, Jaeyeon, et al.
Published: (2024)

Clipped Differences
Published: (2020)

GeoClip: Geometry-Aware Clipping for Differentially Private SGD
by: Gilani, Atefeh, et al.
Published: (2025)

SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training
by: Soleymani, Dorsa, et al.
Published: (2025)

Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models
by: Kim, Gyeongman, et al.
Published: (2025)

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping
by: Huang, Nai-Chieh, et al.
Published: (2023)

PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
by: Kim, Gyeongman, et al.
Published: (2024)

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
by: Ryu, Hyun, et al.
Published: (2024)

Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models
by: Park, Jaesung R., et al.
Published: (2024)

Learning Foreign Languages with ClipFlair: Using Captioning and Revoicing Activities to Increase Students' Motivation and Engagement
by: Baños, Rocío, et al.
Published: (2015)

Computing Clipped Products
by: Norman, Arthur C., et al.
Published: (2024)

Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Clipping Bias and Remedies
by: Li, Qiang, et al.
Published: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
by: Xu, Zihao, et al.
Published: (2024)

AGGC: Adaptive Group Gradient Clipping for Stabilizing Large Language Model Training
by: Li, Zhiyuan, et al.
Published: (2026)

MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
by: Ko, Dohwan, et al.
Published: (2026)

ClipFormer: Key-Value Clipping of Transformers on Memristive Crossbars for Write Noise Mitigation
by: Bhattacharjee, Abhiroop, et al.
Published: (2024)

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification
by: Zhou, Duo, et al.
Published: (2025)

Enhanced Phase Coherence in Series‐Fed Patch Array Antenna: A Design Method for Uniform Element Spacing With Low Sidelobe Levels
by: Jaewoong Jung, et al.
Published: (2024)

Adversarial Reinforcement Learning Framework for ESP Cheater Simulation
by: Park, Inkyu, et al.
Published: (2025)

Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains
by: Bae, Jaesung, et al.
Published: (2026)

DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
by: Park, Jinyoung, et al.
Published: (2025)

Adaptive Gradient Clipping for Robust Federated Learning
by: Allouah, Youssef, et al.
Published: (2024)

Optimized Gradient Clipping for Noisy Label Learning
by: Ye, Xichen, et al.
Published: (2024)

Emotional Movie Clip Dataset
by: Vijaykrishnan, Anirudhan
Published: (2026)

Feature Clipping for Uncertainty Calibration
by: Tao, Linwei, et al.
Published: (2024)