39 citations · 46 across the 26 of their papers we have counts for
28 papers
ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
Xing Fu, Yulin Hu, Mengtong Ji +5
Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs…
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6
Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent…
Learning to Learn from Multimodal Experience
Xingyu Sui, Weixiang Zhao, Yongxin Tang +4
Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing past experience. However, ex…
Rethinking Experience Utilization in Self-Evolving Language Model Agents
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +6
Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and upd…
On Safety Risks in Experience-Driven Self-Evolving Agents
Weixiang Zhao, Yichen Zhang, Yingshuo Wang +8
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduc…
ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
Weixiang Zhao, Haozhen Li, Yanyan Zhao +5
As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safet…
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
Yige Li, Wei Zhao, Zhe Li +6
Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional act…
OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
Yulin Hu, Zimo Long, Jiahe Guo +5
Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchmarks primarily foc…
Large Language Model Agents Are Not Always Faithful Self-Evolvers
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +5
Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experie…
TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
Xingyu Sui, Yanyan Zhao, Yulin Hu +3
Emotional Support Conversation requires not only affective expression but also grounded instrumental support to provide trustworthy guidance. However, existing ESC systems and benc…
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Jiahe Guo, Xiangran Guo, Yulin Hu +8
Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and use…
Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
Weixiang Zhao, Jiahe Guo, Yang Deng +7
Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative think…
MPO: Multilingual Safety Alignment via Reward Gap Optimization
Weixiang Zhao, Yulin Hu, Yang Deng +8
Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across di…
Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
Weixiang Zhao, Xingyu Sui, Yulin Hu +6
Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization met…
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Weixiang Zhao, Jiahe Guo, Yang Deng +9
Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration f…
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
Weixiang Zhao, Jiahe Guo, Yulin Hu +8
Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but re…
Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
Weixiang Zhao, Xingyu Sui, Jiahe Guo +9
Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-…
Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter
Weixiang Zhao, Xingyu Sui, Xinyang Han +9
The growing emotional stress in modern society has increased the demand for Emotional Support Conversations (ESC). While Large Language Models (LLMs) show promise for ESC, they fac…
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
Weixiang Zhao, Yulin Hu, Yang Deng +8
Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fi…
Lens: Rethinking Multilingual Enhancement for Large Language Models
Weixiang Zhao, Yulin Hu, Jiahe Guo +7
As global demand for multilingual large language models (LLMs) grows, most LLMs still remain overly focused on English, leading to the limited access to advanced AI for non-English…
Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
Weixiang Zhao, Yulin Hu, Zhuojun Li +7
Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanism…
Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence
Weixiang Zhao, Zhuojun Li, Shilong Wang +5
Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the c…
SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models
Weixiang Zhao, Shilong Wang, Yulin Hu +6
The continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific k…
TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition
Weixiang Zhao, Yanyan Zhao, Shilong Wang +1
Emotion Support Conversation (ESC) is an emerging and challenging task with the goal of reducing the emotional distress of people. Previous attempts fail to maintain smooth transit…