5 citations · 27 across the 50 of their papers we have counts for
21 papers · 1 filter
Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update
Huanhuan Ma, Henry Peng Zou, Chengze Li +3
Large language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise from different causes. One po…
Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu +12
Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely the underlying medium in which…
Unveiling Language Routing Isolation in Multilingual MoE Models for Interpretable Subnetwork Adaptation
Kening Zheng, Wei-Chieh Huang, Jiahao Huo +9
Mixture-of-Experts (MoE) models exhibit striking performance disparities across languages, yet the internal mechanisms driving these gaps remain poorly understood. In this work, we…
When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang +16
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as addi…
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
Liancheng Fang, Aiwei Liu, Henry Peng Zou +7
Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregre…
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang +56
Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation. As the field enters the "…
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
Chunyu Miao, Henry Peng Zou, Yangning Li +28
Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing…
Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety
Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu +12
Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address co…
Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs
Yangning Li, Weizhi Zhang, Yuyao Yang +17
Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inf…
LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey
Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu +17
Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant…
Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
Zhengyao Gu, Henry Peng Zou, Yankai Chen +3
The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground…
TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistency
Henry Peng Zou, Zhengyao Gu, Yue Zhou +7
Test-time computing approaches, which leverage additional computational resources during inference, have been proven effective in enhancing large language model performance. This w…
GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback
Henry Peng Zou, Siffi Singh, Yi Nian +4
Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled d…
Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges
Vinay Samuel, Yue Zhou, Henry Peng Zou
As large language models achieve increasingly impressive results, questions arise about whether such performance is from generalizability or mere data memorization. Thus, numerous…
PersonaGym: Evaluating Persona Agents and LLMs
Vinay Samuel, Henry Peng Zou, Yue Zhou +6
Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and h…
Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks
Yue Zhou, Henry Peng Zou, Barbara Di Eugenio +1
We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterp…
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
Jiangshu Du, Yibo Wang, Wenting Zhao +37
This work is motivated by two key trends. On one hand, large language models (LLMs) have shown remarkable versatility in various generative tasks such as writing, drawing, and ques…
Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey
Chengyuan Deng, Yiqun Duan, Xin Jin +15
Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns…
CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification
Henry Peng Zou, Yue Zhou, Cornelia Caragea +1
The shared real-time information about natural disasters on social media platforms like Twitter and Facebook plays a critical role in informing volunteers, emergency managers, and…
JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text Classification
Henry Peng Zou, Cornelia Caragea
Semi-supervised text classification (SSTC) has gained increasing attention due to its ability to leverage unlabeled data. However, existing approaches based on pseudo-labeling suff…
DeCrisisMB: Debiased Semi-Supervised Learning for Crisis Tweet Classification via Memory Bank
Henry Peng Zou, Yue Zhou, Weizhi Zhang +1
During crisis events, people often use social media platforms such as Twitter to disseminate information about the situation, warnings, advice, and support. Emergency relief organi…