Conceptio
›
Archive
›
Arxiv All
Arxiv All
metadata only
LZ Penalty: An information-theoretic repetition penalty for autoregressive language models
Ginart, Antonio A. et al.
· 2025
Arxiv All · Other · 2025
Open Source ↗
Direct PDF ↓
artificialintelligence
machine learning, artificial intelligence, information theory
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory
#665895
AI Alignment and Fiduciary Obligation
#665899
Control Allocation in Neural Network Optimization: Joint Affine Control of Weight and Bias Updates
#665900
Sparse PPMI Graph Averaging for Random Indexing Embeddings
#665904
Record
· ID 629775
Retrieved via
Conceptio
— every document is proof-bundled with source, license, and retrieval metadata.