Imagen de Portada

Rethinking GSPO: The Perplexity-Entropy Equivalence

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Liu, Chi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking Entropy Regularization in Large Reasoning Models
por: Jiang, Yuxian, et al.
Publicado: (2025)

Momentum Point-Perplexity Mechanics in Large Language Models
por: Tomaz, Lorenzo, et al.
Publicado: (2025)

Perplexity Cannot Always Tell Right from Wrong
por: Veličković, Petar, et al.
Publicado: (2026)

SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction
por: Dai, Lu, et al.
Publicado: (2025)

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

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
por: Cui, Yingqian, et al.
Publicado: (2025)

Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
por: Xiao, Yao, et al.
Publicado: (2025)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
por: Shivagunde, Namrata, et al.
Publicado: (2026)

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

Rethinking Perplexity: Revealing the Impact of Input Length on Perplexity Evaluation in LLMs
por: Cheng, Letian, et al.
Publicado: (2026)

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
por: Boreiko, Valentyn, et al.
Publicado: (2024)

Reparameterized LLM Training via Orthogonal Equivalence Transformation
por: Qiu, Zeju, et al.
Publicado: (2025)

Equivalent Linear Mappings of Large Language Models
por: Golden, James R.
Publicado: (2025)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
por: Fan, Chongyu, et al.
Publicado: (2024)

FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs
por: Bhattacharya, Debarpan, et al.
Publicado: (2025)

What Scales in Cross-Entropy Scaling Law?
por: Yan, Junxi, et al.
Publicado: (2025)

REFRAG: Rethinking RAG based Decoding
por: Lin, Xiaoqiang, et al.
Publicado: (2025)

PanGu-$π$ Pro:Rethinking Optimization and Architecture for Tiny Language Models
por: Tang, Yehui, et al.
Publicado: (2024)

Rethinking Data Mixing from the Perspective of Large Language Models
por: Xu, Yuanjian, et al.
Publicado: (2026)

Adaptive-Boundary-Clipping GRPO: Ensuring Bounded Ratios for Stable and Generalizable Training
por: Liu, Chi, et al.
Publicado: (2026)

Revisiting Entropy in Reinforcement Learning for Large Reasoning Models
por: Jin, Renren, et al.
Publicado: (2025)

On the Entropy Calibration of Language Models
por: Cao, Steven, et al.
Publicado: (2025)

Rethinking Interpretability in the Era of Large Language Models
por: Singh, Chandan, et al.
Publicado: (2024)

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
por: Li, Yaxuan, et al.
Publicado: (2026)

Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models
por: Pan, Bowen, et al.
Publicado: (2024)

Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective
por: Chen, Kun, et al.
Publicado: (2026)

Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
por: Choi, Minsik, et al.
Publicado: (2025)

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
por: Liu, Yexiang, et al.
Publicado: (2025)

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
por: Hua, Andong, et al.
Publicado: (2025)

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
por: Cui, Ganqu, et al.
Publicado: (2025)

Rethinking the Role of Proxy Rewards in Language Model Alignment
por: Kim, Sungdong, et al.
Publicado: (2024)

Entropy Controllable Direct Preference Optimization
por: Omura, Motoki, et al.
Publicado: (2024)

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems
por: Hao, Yuren, et al.
Publicado: (2025)

Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification
por: Barone, Antonio Valerio Miceli, et al.
Publicado: (2026)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
por: Zhu, Xudong, et al.
Publicado: (2025)

Rethinking Cross-lingual Gaps from a Statistical Viewpoint
por: Piratla, Vihari, et al.
Publicado: (2025)

MemMamba: Rethinking Memory Patterns in State Space Model
por: Wang, Youjin, et al.
Publicado: (2025)

Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
por: Kim, Sunghwan, et al.
Publicado: (2025)

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

Rethinking harmless refusals when fine-tuning foundation models
por: Pop, Florin, et al.
Publicado: (2024)