9 papers
Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents
Haoyang Chen, Yi Liu, Jianzhi Shao +3
Long-horizon tool-use agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an agent is biased toward submitti…
MLQENABLER: Enabling Secure Machine Learning Queries over Encrypted Database in Cloud Computing
Xu Zhou, Haoyang Chen, Xinyu Lei
In cloud computing, the public cloud service providers (CSPs) can provide cloud storage as the primary service while providing additional machine learning (ML)-based services by us…
Editable XAI: Toward Bidirectional Human-AI Alignment with Co-Editable Explanations of Interpretable Attributes
Haoyang Chen, Jingwen Bai, Fang Tian +1
While Explainable AI (XAI) helps users understand AI decisions, misalignment in domain knowledge can lead to disagreement. This inconsistency hinders understanding, and because exp…
An evaluation of LLMs for political bias in Western media: Israel-Hamas and Ukraine-Russia wars
Rohitash Chandra, Haoyan Chen, Yaqing Zhang +2
Political bias in media plays a critical role in shaping public opinion, voter behaviour, and broader democratic discourse. Subjective opinions and political bias can be found in m…
Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation Perspective
Haoyang Chen, Richong Zhang, Junfan Chen
Large language models (LLMs) perform in-context learning (ICL) with minimal supervised examples, which benefits various natural language processing (NLP) tasks. One of the critical…
Scale-free Characteristics of Multilingual Legal Texts and the Limitations of LLMs
Haoyang Chen, Kumiko Tanaka-Ishii
We present a comparative analysis of text complexity across domains using scale-free metrics. We quantify linguistic complexity via Heaps' exponent (vocabulary growth), Taylor'…
Understanding Benchmark Language Under Weakened Formal Semantics
Haoyang Chen, Kumiko Tanaka-Ishii
State-of-the-art NLP benchmarks require interpretation of natural language that specifies conditions, procedures, and exceptions, often relying on implicit assumptions and external…
Open Set Domain Adaptation with Vision-language models via Gradient-aware Separation
Haoyang Chen
Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Cur…
i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance
Haoyang Chen, Peiyan Sun, Qiyuan Song +5
Ride-hailing platforms have been facing the challenge of balancing demand and supply. Existing vehicle reposition techniques often treat drivers as homogeneous agents and relocate…