8 papers
Do Audio Representations Compose Additively?
Chenhao Xue, Zhijin Guo, Joyraj Chakraborty +2
Compositionality, the ability to represent complex acoustic scenes as combinations of simpler sound sources, is central to auditory perception and classical additive signal models.…
Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal
Chenhao Xue, Raslen Guesmi, Siwei Feng +5
Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.e., on te…
Would You Walk to the Car Wash? Salience Bias in LLM Commonsense Reasoning
Zheng Wu, Chenhao Xue, Shijie Zheng +3
Despite advances in complex reasoning, large language models (LLMs) can prioritize explicit input conditions over implicit task prerequisites. In everyday commonsense reasoning, th…
ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
Tingting Yang, Chenhao Xue, Jun Chen
Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithm…
OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents
Zheng Wu, Yi Hua, Zhaoyuan Huang +8
The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex G…
Constructing Composite Features for Interpretable Music-Tagging
Chenhao Xue, Weitao Hu, Joyraj Chakraborty +5
Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this p…
Quantifying Compositionality of Classic and State-of-the-Art Embeddings
Zhijin Guo, Chenhao Xue, Zhaozhen Xu +4
For language models to generalize correctly to novel expressions, it is critical that they exploit access compositional meanings when this is justified. Even if we don't know what…
AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification
Chenhao Xue, Yuanzhe Jin, Adrian Carrasco-Revilla +2
When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we addr…