Buchumschlag

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhao, Weixiang, Sui, Xingyu, Han, Xinyang, Deng, Yang, Hu, Yulin, Guo, Jiahe, Qin, Libo, Du, Qianyun, Wang, Shijin, Zhao, Yanyan, Qin, Bing, Liu, Ting
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
von: Sui, Xingyu, et al.
Veröffentlicht: (2026)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

Lens: Rethinking Multilingual Enhancement for Large Language Models
von: Zhao, Weixiang, et al.
Veröffentlicht: (2024)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
von: Zhao, Weixiang, et al.
Veröffentlicht: (2024)

Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
von: Hu, Yulin, et al.
Veröffentlicht: (2026)

Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
von: Fu, Xing, et al.
Veröffentlicht: (2026)

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
von: Zhao, Weixiang, et al.
Veröffentlicht: (2024)

MPO: Multilingual Safety Alignment via Reward Gap Optimization
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
von: Guo, Jiahe, et al.
Veröffentlicht: (2026)

Learning to Learn from Multimodal Experience
von: Sui, Xingyu, et al.
Veröffentlicht: (2026)

Large Language Model Agents Are Not Always Faithful Self-Evolvers
von: Zhao, Weixiang, et al.
Veröffentlicht: (2026)

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation
von: Lu, Xin, et al.
Veröffentlicht: (2025)

SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
von: Zhao, Weixiang, et al.
Veröffentlicht: (2024)

ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains
von: Huang, Zhaopei, et al.
Veröffentlicht: (2024)

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
von: Guo, Jiahe, et al.
Veröffentlicht: (2026)

ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
von: Zhao, Weixiang, et al.
Veröffentlicht: (2026)

Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers
von: Lu, Xin, et al.
Veröffentlicht: (2024)

Rethinking Experience Utilization in Self-Evolving Language Model Agents
von: Zhao, Weixiang, et al.
Veröffentlicht: (2026)

On Safety Risks in Experience-Driven Self-Evolving Agents
von: Zhao, Weixiang, et al.
Veröffentlicht: (2026)

RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models
von: Wang, Bichen, et al.
Veröffentlicht: (2024)

Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering
von: Liu, Runxuan, et al.
Veröffentlicht: (2025)

Data Uncertainty-Aware Learning for Multimodal Aspect-based Sentiment Analysis
von: Yang, Hao, et al.
Veröffentlicht: (2024)

Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
von: Wu, Di, et al.
Veröffentlicht: (2024)

DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model
von: Yang, Hao, et al.
Veröffentlicht: (2026)

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning
von: Du, Yexing, et al.
Veröffentlicht: (2024)

CARE-Bench: A Benchmark of Diverse Client Simulations Guided by Expert Principles for Evaluating LLMs in Psychological Counseling
von: Wang, Bichen, et al.
Veröffentlicht: (2025)

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

Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought
von: Chen, Qiguang, et al.
Veröffentlicht: (2024)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
von: Wu, Di, et al.
Veröffentlicht: (2026)

Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
von: Wang, Haochun, et al.
Veröffentlicht: (2025)

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits
von: Li, Bohan, et al.
Veröffentlicht: (2024)

Mitigating Strategy Preference Bias in Emotional Support Conversation via Uncertainty Estimations
von: Zhou, Yougen, et al.
Veröffentlicht: (2025)

Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism
von: Wang, Libo
Veröffentlicht: (2024)

Eco‐Labels and Sales Mode Selection Strategies for E‐Commerce Platform Supply Chain
von: Fengmin Yao, et al.
Veröffentlicht: (2024)

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals
von: Zhao, Yangyang, et al.
Veröffentlicht: (2025)