Copertina

Auxiliary-Hyperparameter-Free Sampling: Entropy Equilibrium for Text Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cai, Xiaodong, Lin, Hai, Zhan, Shaoxiong, Luo, Weiqi, Kim, Hong-Gee, Hao, Hongyan, Yang, Yu, Zheng, Hai-Tao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
di: Wu, Shunlong, et al.
Pubblicazione: (2026)

QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
di: Tan, Hongming, et al.
Pubblicazione: (2024)

3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models
di: Zhan, Shaoxiong, et al.
Pubblicazione: (2026)

LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation
di: Zhan, Shaoxiong, et al.
Pubblicazione: (2025)

A Hierarchical Framework for Measuring Scientific Paper Innovation via Large Language Models
di: Tan, Hongming, et al.
Pubblicazione: (2025)

From Token to Line: Enhancing Code Generation with a Long-Term Perspective
di: Lu, Tingwei, et al.
Pubblicazione: (2025)

Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion
di: Wang, Hebin, et al.
Pubblicazione: (2024)

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios
di: Tang, Jiwei, et al.
Pubblicazione: (2024)

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
di: Tang, Jiwei, et al.
Pubblicazione: (2025)

Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation
di: Zhou, Mingyuan, et al.
Pubblicazione: (2024)

X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents
di: Wu, Weiqi, et al.
Pubblicazione: (2024)

Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation
di: Cai, Shizhan, et al.
Pubblicazione: (2025)

CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction
di: Qin, Shang, et al.
Pubblicazione: (2025)

OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama
di: Xu, Tianyang, et al.
Pubblicazione: (2025)

VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text
di: Nguyen, Trieu Hai, et al.
Pubblicazione: (2025)

When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
di: Li, Yinghui, et al.
Pubblicazione: (2024)

p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
di: Tan, Runyan, et al.
Pubblicazione: (2025)

IRSC: A Zero-shot Evaluation Benchmark for Information Retrieval through Semantic Comprehension in Retrieval-Augmented Generation Scenarios
di: Lin, Hai, et al.
Pubblicazione: (2024)

RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
di: Lv, Qingsong, et al.
Pubblicazione: (2025)

Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
di: Arias, Esteban Garces, et al.
Pubblicazione: (2024)

Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
di: Wu, Hongqiu, et al.
Pubblicazione: (2025)

Preference-Guided Reflective Sampling for Aligning Language Models
di: Ye, Hai, et al.
Pubblicazione: (2024)

From Role-Play to Drama-Interaction: An LLM Solution
di: Wu, Weiqi, et al.
Pubblicazione: (2024)

Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking
di: Nguyen, Hai Toan, et al.
Pubblicazione: (2025)

Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction
di: Deng, Zheye, et al.
Pubblicazione: (2024)

On the (In)Effectiveness of Large Language Models for Chinese Text Correction
di: Li, Yinghui, et al.
Pubblicazione: (2023)

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation
di: Qin, Chengwei, et al.
Pubblicazione: (2025)

Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration
di: Ye, Hai, et al.
Pubblicazione: (2024)

Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
di: Deng, Zheye, et al.
Pubblicazione: (2025)

From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training
di: Liu, Tianqiao, et al.
Pubblicazione: (2025)

From Retrieval to Generation: Efficient and Effective Entity Set Expansion
di: Huang, Shulin, et al.
Pubblicazione: (2023)

CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
di: Ye, Jingheng, et al.
Pubblicazione: (2024)

Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization
di: Wu, Weiqi, et al.
Pubblicazione: (2025)

Correct Like Humans: Progressive Learning Framework for Chinese Text Error Correction
di: Li, Yinghui, et al.
Pubblicazione: (2023)

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
di: Zhan, Shaoxiong, et al.
Pubblicazione: (2025)

Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction
di: Nguyen, Cam-Van Thi, et al.
Pubblicazione: (2023)

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding
di: Jinnai, Yuu, et al.
Pubblicazione: (2024)

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
di: Sun, Chenxi, et al.
Pubblicazione: (2023)

EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling
di: Zhang, Shimao, et al.
Pubblicazione: (2024)

CLASS: Enhancing Cross-Modal Text-Molecule Retrieval Performance and Training Efficiency
di: Wu, Hongyan, et al.
Pubblicazione: (2025)