Imagen de Portada

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yoon, Hee Suk, Yoon, Eunseop, Hasegawa-Johnson, Mark, Kim, Sungwoong, Yoo, Chang D.
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
por: Yoon, Eunseop, et al.
Publicado: (2025)

LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
por: Yoon, Eunseop, et al.
Publicado: (2024)

TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
por: Yoon, Eunseop, et al.
Publicado: (2024)

PACR: Progressively Ascending Confidence Reward for LLM Reasoning
por: Yoon, Eunseop, et al.
Publicado: (2025)

PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
por: Yoon, Hee Suk, et al.
Publicado: (2026)

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
por: Yoon, Hee Suk, et al.
Publicado: (2024)

HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
por: Yoon, Sunjae, et al.
Publicado: (2023)

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
por: Yoon, Hee Suk, et al.
Publicado: (2026)

AdaMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition
por: Eom, SooHwan, et al.
Publicado: (2024)

ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
por: Yoon, Hee Suk, et al.
Publicado: (2023)

SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
por: Ryu, Hyun, et al.
Publicado: (2023)

Selective Query-guided Debiasing for Video Corpus Moment Retrieval
por: Yoon, Sunjae, et al.
Publicado: (2022)

TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation
por: Fodeh, Samah, et al.
Publicado: (2026)

SGPO: Self-Generated Preference Optimization based on Self-Improver
por: Lee, Hyeonji, et al.
Publicado: (2025)

SteerConf: Steering LLMs for Confidence Elicitation
por: Zhou, Ziang, et al.
Publicado: (2025)

ConfRAG: Confidence-Guided Retrieval-Augmenting Generation
por: Huang, Yin, et al.
Publicado: (2025)

High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decoding
por: Hong, Ji Woo, et al.
Publicado: (2026)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
por: Li, Yibo, et al.
Publicado: (2025)

BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
por: Yoon, Hee Suk, et al.
Publicado: (2024)

Latent Preference Modeling for Cross-Session Personalized Tool Calling
por: Yoon, Yejin, et al.
Publicado: (2026)

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
por: Xue, Boyang, et al.
Publicado: (2024)

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
por: Xue, Boyang, et al.
Publicado: (2024)

M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction Following
por: Gao, Ruirui, et al.
Publicado: (2025)

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
por: Ou, Litu, et al.
Publicado: (2025)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
por: Zhang, Bonan, et al.
Publicado: (2025)

ConfLayers: Adaptive Confidence-based Layer Skipping for Self-Speculative Decoding
por: Amer, Walaa, et al.
Publicado: (2026)

Reasoning Models Better Express Their Confidence
por: Yoon, Dongkeun, et al.
Publicado: (2025)

LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
por: Jo, Daejin, et al.
Publicado: (2025)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
por: Kim, Eunji, et al.
Publicado: (2024)

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification
por: Liu, Siran, et al.
Publicado: (2026)

PrefPO: Pairwise Preference Prompt Optimization
por: Singhal, Rahul, et al.
Publicado: (2026)

Speculative Verification: Exploiting Information Gain to Refine Speculative Decoding
por: Kim, Sungkyun, et al.
Publicado: (2025)

Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
por: Zhou, Yue, et al.
Publicado: (2024)

KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models
por: Zhang, Ruizhe, et al.
Publicado: (2024)

Beyond Learning: A Training-Free Alternative to Model Adaptation
por: Yoon, Namkyung, et al.
Publicado: (2026)

Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences
por: Shrivastava, Vaishnavi, et al.
Publicado: (2025)

QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation
por: Yoo, Gahyun, et al.
Publicado: (2024)

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings
por: Liu, Tong, et al.
Publicado: (2025)

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
por: Yoon, Sangyeon, et al.
Publicado: (2026)

CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences
por: Pokharel, Rhitabrat, et al.
Publicado: (2025)