Imagen de Portada

Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Davoodi, Arash Gholami, Rezazadeh, Navid, Davoudi, Seyed Pouyan Mousavi, Pezeshkpour, Pouya
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLMs Are Not Intelligent Thinkers: Introducing Mathematical Topic Tree Benchmark for Comprehensive Evaluation of LLMs
por: Davoodi, Arash Gholami, et al.
Publicado: (2024)

Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
por: Rezazadeh, Navid, et al.
Publicado: (2026)

Multi-Conditional Ranking with Large Language Models
por: Pezeshkpour, Pouya, et al.
Publicado: (2024)

AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs
por: Pezeshkpour, Pouya, et al.
Publicado: (2026)

The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces
por: Rezazadeh, Navid, et al.
Publicado: (2026)

From Task Solving to Robust Real-World Adaptation in LLM Agents
por: Pezeshkpour, Pouya, et al.
Publicado: (2026)

Learning Beyond the Surface: How Far Can Continual Pre-Training with LoRA Enhance LLMs' Domain-Specific Insight Learning?
por: Pezeshkpour, Pouya, et al.
Publicado: (2025)

Insight-RAG: Enhancing LLMs with Insight-Driven Augmentation
por: Pezeshkpour, Pouya, et al.
Publicado: (2025)

Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models
por: Amiri-Margavi, Alireza, et al.
Publicado: (2024)

Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions
por: Pezeshkpour, Pouya, et al.
Publicado: (2024)

Equal Access, Unequal Interaction: A Counterfactual Audit of LLM Fairness
por: Amiri-Margavi, Alireza, et al.
Publicado: (2026)

Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth
por: Davoudi, Seyed Pouyan Mousavi, et al.
Publicado: (2025)

One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
por: Afzali, Amirabbas, et al.
Publicado: (2025)

SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression
por: Wang, Xin, et al.
Publicado: (2024)

TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
por: Iranmanesh, Reihaneh, et al.
Publicado: (2026)

Fewer Truncations Improve Language Modeling
por: Ding, Hantian, et al.
Publicado: (2024)

Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
por: Hashimoto, Wataru, et al.
Publicado: (2025)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
por: You, Zejia, et al.
Publicado: (2026)

From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models
por: Bayat, Farima Fatahi, et al.
Publicado: (2025)

AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis
por: Davoudi, Saeedeh, et al.
Publicado: (2026)

The Geometry of Tokens in Internal Representations of Large Language Models
por: Viswanathan, Karthik, et al.
Publicado: (2025)

FlashDecoding++: Faster Large Language Model Inference on GPUs
por: Hong, Ke, et al.
Publicado: (2023)

Recurrent Drafter for Fast Speculative Decoding in Large Language Models
por: Cheng, Yunfei, et al.
Publicado: (2024)

Decoding Rarity: Large Language Models in the Diagnosis of Rare Diseases
por: Carbonari, Valentina, et al.
Publicado: (2025)

The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
por: Arias, Esteban Garces, et al.
Publicado: (2026)

Private Language Models via Truncated Laplacian Mechanism
por: Huang, Tianhao, et al.
Publicado: (2024)

CharED: Character-wise Ensemble Decoding for Large Language Models
por: Gu, Kevin, et al.
Publicado: (2024)

On Speculative Decoding for Multimodal Large Language Models
por: Gagrani, Mukul, et al.
Publicado: (2024)

LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models
por: Xi, Haocheng, et al.
Publicado: (2026)

Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder
por: M., Abhinav P., et al.
Publicado: (2024)

PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars
por: Prabhu, Sumanth
Publicado: (2024)

From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
por: Welleck, Sean, et al.
Publicado: (2024)

Semantic Consistency Regularization with Large Language Models for Semi-supervised Sentiment Analysis
por: Li, Kunrong, et al.
Publicado: (2025)

Confidence-Modulated Speculative Decoding for Large Language Models
por: Sen, Jaydip, et al.
Publicado: (2025)

Residual-Mass Accounting for Partial-KV Decoding
por: Hoshi, Yasuto, et al.
Publicado: (2026)

Confidence Geometry Reveals Trace-Level Correctness in Large Language Model Reasoning
por: Liu, Shuo, et al.
Publicado: (2026)

The Geometry of Categorical and Hierarchical Concepts in Large Language Models
por: Park, Kiho, et al.
Publicado: (2024)

The Linear Representation Hypothesis and the Geometry of Large Language Models
por: Park, Kiho, et al.
Publicado: (2023)

TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
por: Chang, Shenxu, et al.
Publicado: (2025)

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
por: Kiruluta, Andrew
Publicado: (2026)