Imagen de Portada

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Yougen, Chen, Qin, Zhou, Ningning, Zhou, Jie, Wu, Xingjiao, He, Liang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DiaCBT: A Long-Periodic Dialogue Corpus Guided by Cognitive Conceptualization Diagram for CBT-based Psychological Counseling
por: Zhou, Yougen, et al.
Publicado: (2025)

Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Tracking
por: Gu, Yiyang, et al.
Publicado: (2024)

Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
por: Kang, Dongjin, et al.
Publicado: (2024)

PRMB: Benchmarking Reward Models in Long-Horizon CBT-based Counseling Dialogue
por: Zhou, Yougen, et al.
Publicado: (2026)

Emotional Supporters often Use Multiple Strategies in a Single Turn
por: Bai, Xin, et al.
Publicado: (2025)

Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
por: Yin, Jianghao, et al.
Publicado: (2026)

SocialSim: Towards Socialized Simulation of Emotional Support Conversation
por: Chen, Zhuang, et al.
Publicado: (2025)

Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations
por: Zhu, Jie, et al.
Publicado: (2026)

CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
por: Zhu, Jie, et al.
Publicado: (2025)

Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis
por: Cheng, Zhenxiao, et al.
Publicado: (2024)

Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
por: Wang, Jiashuo, et al.
Publicado: (2024)

Boosting Large Language Models with Socratic Method for Conversational Mathematics Teaching
por: Ding, Yuyang, et al.
Publicado: (2024)

Quantifying and Mitigating Self-Preference Bias of LLM Judges
por: Yang, Jinming, et al.
Publicado: (2026)

ESCoT: Towards Interpretable Emotional Support Dialogue Systems
por: Zhang, Tenggan, et al.
Publicado: (2024)

DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization
por: Zhang, Chao, et al.
Publicado: (2025)

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
por: Cai, Yuxuan, et al.
Publicado: (2026)

P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts
por: Dan, Yuhao, et al.
Publicado: (2024)

Identifying and Mitigating Social Bias Knowledge in Language Models
por: Chen, Ruizhe, et al.
Publicado: (2024)

SURE: Synergistic Uncertainty-aware Reasoning for Multimodal Emotion Recognition in Conversations
por: Cai, Yiqiang, et al.
Publicado: (2026)

BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization
por: Allam, Ahmed
Publicado: (2024)

DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models
por: Chen, Kedi, et al.
Publicado: (2024)

A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder
por: Chen, Kedi, et al.
Publicado: (2024)

FairMonitor: A Dual-framework for Detecting Stereotypes and Biases in Large Language Models
por: Bai, Yanhong, et al.
Publicado: (2024)

Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis
por: Ding, Xuanwen, et al.
Publicado: (2024)

Evaluating and Mitigating Bias in AI-Based Medical Text Generation
por: Chen, Xiuying, et al.
Publicado: (2025)

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
por: Huai, Tianyu, et al.
Publicado: (2025)

Enhancing Event Causality Identification with Rationale and Structure-Aware Causal Question Answering
por: Zhang, Baiyan, et al.
Publicado: (2024)

Effective Explanations Support Planning Under Uncertainty
por: Zhou, Hanqi, et al.
Publicado: (2026)

LLMs Capture Emotion Labels, Not Emotion Uncertainty: Distributional Analysis and Calibration of Human-LLM Judgment Gaps
por: Inoshita, Keito, et al.
Publicado: (2026)

ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models
por: Zhao, Haiquan, et al.
Publicado: (2024)

Robust Preference Optimization via Dynamic Target Margins
por: Sun, Jie, et al.
Publicado: (2025)

ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
por: Zhu, Jie, et al.
Publicado: (2026)

Steering Conversational Large Language Models for Long Emotional Support Conversations
por: Madani, Navid, et al.
Publicado: (2024)

Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission
por: He, Jianfeng, et al.
Publicado: (2023)

From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test
por: Dai, Xunlian, et al.
Publicado: (2025)

Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors
por: Wu, Wen, et al.
Publicado: (2022)

Mitigating the Bias of Large Language Model Evaluation
por: Zhou, Hongli, et al.
Publicado: (2024)

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
por: Zhao, Weixiang, et al.
Publicado: (2025)

Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge
por: Liu, Zhuo, et al.
Publicado: (2025)

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization
por: Li, Junyi, et al.
Publicado: (2026)