3 citations · 3 across the 15 of their papers we have counts for
15 papers
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Mengru Wang, Junfeng Fang, Shuofei Qiao +17
AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becom…
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Mengru Wang, Haozhe Luo, Zhenqian Xu +6
Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly ev…
MobileMem: Learning from a Year of Mobile Experiences
Xinle Deng, Yida Xue, Xiangyuan Ru +16
The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and conti…
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis
Kewei Xu, Xiaoben Lu, Shuofei Qiao +4
Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical…
When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
Haoming Xu, Weihong Xu, Zongrui Li +6
Long-horizon interactions require language models to manage accumulating information: when to update their state, when to preserve their state, and what to ignore. We study this ch…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling
Hao-Xiang Xu, Chong Deng, Jiaqing Liu +5
Large Language Models (LLMs) extend their capabilities through function-calling (FC), which relies on training data with high quality, diversity, and broad coverage of scenario. Ho…
Towards Policy-Adaptive Image Guardrail: Benchmark and Method
Caiyong Piao, Zhiyuan Yan, Haoming Xu +4
Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolvi…
Step-Level Sparse Autoencoder for Reasoning Process Interpretation
Xuan Yang, Jiayu Liu, Yuhang Lai +3
Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated…
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7
As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under…
LightMem: Lightweight and Efficient Memory-Augmented Generation
Jizhan Fang, Xinle Deng, Haoming Xu +9
Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory…
ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
Haoming Xu, Shuxun Wang, Yanqiu Zhao +6
This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models. This task aims to selectively erase sensitive kn…
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models
Ziwen Xu, Shuxun Wang, Kewei Xu +7
In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide ra…
ReLearn: Unlearning via Learning for Large Language Models
Haoming Xu, Ningyuan Zhao, Liming Yang +7
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent token…
MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
Chenxi Wang, Xiang Chen, Ningyu Zhang +4
Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood. In this paper, we present an empirical ana…