Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | Arias, Esteban Garces, Li, Meimingwei, Heumann, Christian, Aßenmacher, Matthias |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
por: Arias, Esteban Garces, et al.
Publicado: (2024)
por: Arias, Esteban Garces, et al.
Publicado: (2024)
Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
por: Arias, Esteban Garces, et al.
Publicado: (2024)
por: Arias, Esteban Garces, et al.
Publicado: (2024)
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
por: Ding, Yuanhao, et al.
Publicado: (2025)
por: Ding, Yuanhao, 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)
por: Arias, Esteban Garces, et al.
Publicado: (2026)
Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
por: Ding, Yuanhao, et al.
Publicado: (2026)
por: Ding, Yuanhao, et al.
Publicado: (2026)
Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages
por: Schöffel, Matthias, et al.
Publicado: (2025)
por: Schöffel, Matthias, et al.
Publicado: (2025)
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
por: Li, Meimingwei, et al.
Publicado: (2026)
por: Li, Meimingwei, et al.
Publicado: (2026)
Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation
por: Mayer, Luis, et al.
Publicado: (2024)
por: Mayer, Luis, et al.
Publicado: (2024)
Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan
por: Schöffel, Matthias, et al.
Publicado: (2025)
por: Schöffel, Matthias, et al.
Publicado: (2025)
How Prevalent is Gender Bias in ChatGPT? -- Exploring German and English ChatGPT Responses
por: Urchs, Stefanie, et al.
Publicado: (2023)
por: Urchs, Stefanie, et al.
Publicado: (2023)
A Bayesian approach to modeling topic-metadata relationships
por: Schulze, P., et al.
Publicado: (2021)
por: Schulze, P., et al.
Publicado: (2021)
Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation
por: Khan, Muneeb Ur Raheem
Publicado: (2026)
por: Khan, Muneeb Ur Raheem
Publicado: (2026)
Statistical Multicriteria Evaluation of LLM-Generated Text
por: Arias, Esteban Garces, et al.
Publicado: (2025)
por: Arias, Esteban Garces, et al.
Publicado: (2025)
Improving Open-Ended Text Generation via Adaptive Decoding
por: Zhu, Wenhong, et al.
Publicado: (2024)
por: Zhu, Wenhong, et al.
Publicado: (2024)
ETS: Open Vocabulary Electroencephalography-To-Text Decoding and Sentiment Classification
por: Masry, Mohamed, et al.
Publicado: (2025)
por: Masry, Mohamed, et al.
Publicado: (2025)
Reflection-Window Decoding: Text Generation with Selective Refinement
por: Tang, Zeyu, et al.
Publicado: (2025)
por: Tang, Zeyu, et al.
Publicado: (2025)
Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
por: Ren, Liliang, et al.
Publicado: (2025)
por: Ren, Liliang, et al.
Publicado: (2025)
Decoding Speculative Decoding
por: Yan, Minghao, et al.
Publicado: (2024)
por: Yan, Minghao, et al.
Publicado: (2024)
The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
por: Arias, Esteban Garces, et al.
Publicado: (2025)
por: Arias, Esteban Garces, et al.
Publicado: (2025)
Reinforcement Learning for Latent-Space Thinking in LLMs
por: Özeren, Enes, et al.
Publicado: (2025)
por: Özeren, Enes, et al.
Publicado: (2025)
Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora
por: Urchs, Stefanie, et al.
Publicado: (2025)
por: Urchs, Stefanie, et al.
Publicado: (2025)
Deep Representation Learning for Open Vocabulary Electroencephalography-to-Text Decoding
por: Amrani, Hamza, et al.
Publicado: (2023)
por: Amrani, Hamza, et al.
Publicado: (2023)
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
por: Li, Zongxia, et al.
Publicado: (2025)
por: Li, Zongxia, et al.
Publicado: (2025)
Scaling Open-Ended Reasoning to Predict the Future
por: Chandak, Nikhil, et al.
Publicado: (2025)
por: Chandak, Nikhil, et al.
Publicado: (2025)
DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers
por: Menon, Rakesh R., et al.
Publicado: (2024)
por: Menon, Rakesh R., et al.
Publicado: (2024)
Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
por: Abdali, Sara, et al.
Publicado: (2024)
por: Abdali, Sara, et al.
Publicado: (2024)
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
por: Chang, Haw-Shiuan, et al.
Publicado: (2024)
por: Chang, Haw-Shiuan, et al.
Publicado: (2024)
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
por: Samvelyan, Mikayel, et al.
Publicado: (2024)
por: Samvelyan, Mikayel, et al.
Publicado: (2024)
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
por: Potraghloo, Erfan Baghaei, et al.
Publicado: (2025)
por: Potraghloo, Erfan Baghaei, et al.
Publicado: (2025)
TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
por: Uludoğan, Gökçe, et al.
Publicado: (2024)
por: Uludoğan, Gökçe, et al.
Publicado: (2024)
CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad
por: Chen, Yongqiang, et al.
Publicado: (2026)
por: Chen, Yongqiang, et al.
Publicado: (2026)
Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
por: Luo, Wen, et al.
Publicado: (2025)
por: Luo, Wen, et al.
Publicado: (2025)
Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models
por: Hashimoto, Wataru, et al.
Publicado: (2025)
por: Hashimoto, Wataru, et al.
Publicado: (2025)
Decoding Linguistic Nuances in Mental Health Text Classification Using Expressive Narrative Stories
por: Tang, Jinwen, et al.
Publicado: (2024)
por: Tang, Jinwen, et al.
Publicado: (2024)
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
por: Lange, Robert Tjarko, et al.
Publicado: (2025)
por: Lange, Robert Tjarko, et al.
Publicado: (2025)
Decoding Partial Differential Equations: Cross-Modal Adaptation of Decoder-only Models to PDEs
por: García-de-Herreros, Paloma, et al.
Publicado: (2025)
por: García-de-Herreros, Paloma, et al.
Publicado: (2025)
Predictive Pipelined Decoding: A Compute-Latency Trade-off for Exact LLM Decoding
por: Yang, Seongjun, et al.
Publicado: (2023)
por: Yang, Seongjun, et al.
Publicado: (2023)
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion
por: Christopher, Jacob K, et al.
Publicado: (2024)
por: Christopher, Jacob K, et al.
Publicado: (2024)
ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding
por: Zhong, Shuzhang, et al.
Publicado: (2024)
por: Zhong, Shuzhang, et al.
Publicado: (2024)
Seq vs Seq: An Open Suite of Paired Encoders and Decoders
por: Weller, Orion, et al.
Publicado: (2025)
por: Weller, Orion, et al.
Publicado: (2025)
Ejemplares similares
-
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
por: Arias, Esteban Garces, et al.
Publicado: (2024) -
Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
por: Arias, Esteban Garces, et al.
Publicado: (2024) -
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
por: Ding, Yuanhao, 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) -
Min-$k$ Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
por: Ding, Yuanhao, et al.
Publicado: (2026)