ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | Shin, Seungmin, Kim, Dooyoung, Ko, Youngjoong |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
DAPI: Domain Adaptive Toxicity Probe Vector Intervention for Fine-Grained Detoxification
por: Hyeonsu, Cho, et al.
Publicado: (2025)
por: Hyeonsu, Cho, et al.
Publicado: (2025)
Dependency Parsing with the Structuralized Prompt Template
por: Kim, Keunha, et al.
Publicado: (2025)
por: Kim, Keunha, et al.
Publicado: (2025)
SS-MPC: A Sequence-Structured Multi-Party Conversation System
por: Jang, Yoonjin, et al.
Publicado: (2025)
por: Jang, Yoonjin, et al.
Publicado: (2025)
HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
por: Jang, Yoonjin, et al.
Publicado: (2026)
por: Jang, Yoonjin, et al.
Publicado: (2026)
Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History
por: Sung, Mingi, et al.
Publicado: (2024)
por: Sung, Mingi, et al.
Publicado: (2024)
Grammar Control in Dialogue Response Generation for Language Learning Chatbots
por: Glandorf, Dominik, et al.
Publicado: (2025)
por: Glandorf, Dominik, et al.
Publicado: (2025)
Controlling Language Difficulty in Dialogues with Linguistic Features
por: Xu, Shuyao, et al.
Publicado: (2025)
por: Xu, Shuyao, et al.
Publicado: (2025)
Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation
por: Lee, Seungmin, et al.
Publicado: (2025)
por: Lee, Seungmin, et al.
Publicado: (2025)
Controlling Language Confusion in Multilingual LLMs
por: Lee, Nahyun, et al.
Publicado: (2025)
por: Lee, Nahyun, et al.
Publicado: (2025)
A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers
por: Huang, Chenyang, et al.
Publicado: (2025)
por: Huang, Chenyang, et al.
Publicado: (2025)
Prompt-Based Length Controlled Generation with Multiple Control Types
por: Jie, Renlong, et al.
Publicado: (2024)
por: Jie, Renlong, et al.
Publicado: (2024)
ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following
por: Han, Seungmin, et al.
Publicado: (2025)
por: Han, Seungmin, et al.
Publicado: (2025)
Controllable and Diverse Data Augmentation with Large Language Model for Low-Resource Open-Domain Dialogue Generation
por: Liu, Zhenhua, et al.
Publicado: (2024)
por: Liu, Zhenhua, et al.
Publicado: (2024)
Selective Generation for Controllable Language Models
por: Lee, Minjae, et al.
Publicado: (2023)
por: Lee, Minjae, et al.
Publicado: (2023)
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
por: Deng, Haikang, et al.
Publicado: (2023)
por: Deng, Haikang, et al.
Publicado: (2023)
Personalized Dialogue Generation with Persona-Adaptive Attention
por: Huang, Qiushi, et al.
Publicado: (2022)
por: Huang, Qiushi, et al.
Publicado: (2022)
Controlled Decoding from Language Models
por: Mudgal, Sidharth, et al.
Publicado: (2023)
por: Mudgal, Sidharth, et al.
Publicado: (2023)
Entropy Controllable Direct Preference Optimization
por: Omura, Motoki, et al.
Publicado: (2024)
por: Omura, Motoki, et al.
Publicado: (2024)
DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation
por: Xu, Chen, et al.
Publicado: (2024)
por: Xu, Chen, et al.
Publicado: (2024)
Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration
por: Wei, Longxuan, et al.
Publicado: (2026)
por: Wei, Longxuan, et al.
Publicado: (2026)
ControlMed: Adding Reasoning Control to Medical Language Model
por: Lee, Sung-Min, et al.
Publicado: (2025)
por: Lee, Sung-Min, et al.
Publicado: (2025)
Hansel: Output Length Controlling Framework for Large Language Models
por: Song, Seoha, et al.
Publicado: (2024)
por: Song, Seoha, et al.
Publicado: (2024)
TiCo: Time-Controllable Spoken Dialogue Model
por: Chang, Kai-Wei, et al.
Publicado: (2026)
por: Chang, Kai-Wei, et al.
Publicado: (2026)
A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation
por: Yang, Chenxu, et al.
Publicado: (2024)
por: Yang, Chenxu, et al.
Publicado: (2024)
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
por: Li, Yiwei, et al.
Publicado: (2024)
por: Li, Yiwei, et al.
Publicado: (2024)
Revealing User Familiarity Bias in Task-Oriented Dialogue via Interactive Evaluation
por: Kim, Takyoung, et al.
Publicado: (2023)
por: Kim, Takyoung, et al.
Publicado: (2023)
Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
por: Park, Seongwan, et al.
Publicado: (2025)
por: Park, Seongwan, et al.
Publicado: (2025)
Automatic Inter-document Multi-hop Scientific QA Generation
por: Lee, Seungmin, et al.
Publicado: (2026)
por: Lee, Seungmin, et al.
Publicado: (2026)
RSD: A Local Triangulation Audit Primitive for Learned Vector Blocks
por: Jin, Seungmin
Publicado: (2026)
por: Jin, Seungmin
Publicado: (2026)
$\texttt{SEM-CTRL}$: Semantically Controlled Decoding
por: Albinhassan, Mohammad, et al.
Publicado: (2025)
por: Albinhassan, Mohammad, et al.
Publicado: (2025)
Entropy-Based Decoding for Retrieval-Augmented Large Language Models
por: Qiu, Zexuan, et al.
Publicado: (2024)
por: Qiu, Zexuan, et al.
Publicado: (2024)
Linguistically-Controlled Paraphrase Generation
por: Elgaar, Mohamed, et al.
Publicado: (2024)
por: Elgaar, Mohamed, et al.
Publicado: (2024)
Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
por: Yuan, Haidong, et al.
Publicado: (2026)
por: Yuan, Haidong, et al.
Publicado: (2026)
Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
por: Chiniya, Purva, et al.
Publicado: (2026)
por: Chiniya, Purva, et al.
Publicado: (2026)
Language Generation as Optimal Control: Closed-Loop Diffusion in Latent Control Space
por: Dong, ZiYi, et al.
Publicado: (2026)
por: Dong, ZiYi, et al.
Publicado: (2026)
LiFi: Lightweight Controlled Text Generation with Fine-Grained Control Codes
por: Shi, Chufan, et al.
Publicado: (2024)
por: Shi, Chufan, et al.
Publicado: (2024)
Controlled LLM Decoding via Discrete Auto-regressive Biasing
por: Pynadath, Patrick, et al.
Publicado: (2025)
por: Pynadath, Patrick, et al.
Publicado: (2025)
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
por: Chakraborty, Souradip, et al.
Publicado: (2025)
por: Chakraborty, Souradip, et al.
Publicado: (2025)
Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming
por: Pasini, Tommaso, et al.
Publicado: (2024)
por: Pasini, Tommaso, et al.
Publicado: (2024)
Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
por: Zhang, Jiazheng, et al.
Publicado: (2026)
por: Zhang, Jiazheng, et al.
Publicado: (2026)
Ejemplares similares
-
DAPI: Domain Adaptive Toxicity Probe Vector Intervention for Fine-Grained Detoxification
por: Hyeonsu, Cho, et al.
Publicado: (2025) -
Dependency Parsing with the Structuralized Prompt Template
por: Kim, Keunha, et al.
Publicado: (2025) -
SS-MPC: A Sequence-Structured Multi-Party Conversation System
por: Jang, Yoonjin, et al.
Publicado: (2025) -
HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment
por: Jang, Yoonjin, et al.
Publicado: (2026) -
Context-Aware LLM Translation System Using Conversation Summarization and Dialogue History
por: Sung, Mingi, et al.
Publicado: (2024)