6 papers
Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection
Zhen Yang, Mengqi Wang, Gengda Zhao +3
Large language models (LLMs) are trained on massive and largely undisclosed corpora that may contain copyrighted or privacy-sensitive content. Data contamination detection (DCD) th…
Interpretable Column Annotation with LLM-Symbolized Decision Process Materialization
Mengqi Wang, Jianwei Wang, Qing Liu +5
Column annotation (CA), including column type annotation (CTA) and column property annotation (CPA), aims to identify the meanings of table columns and the semantic relationships a…
Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection
Mengqi Wang, Jianwei Wang, Qing Liu +5
Error detection (ED), which aims to identify incorrect or inconsistent cell values in tabular data, is important for ensuring data quality. Recent state-of-the-art ED methods lever…
Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing
Mengqi Wang, Zhan Liu, Zengrui Jin +3
Diffusion-based large language models (DLLMs) have recently attracted growing interest as an alternative to autoregressive decoders. In this work, we present an empirical study on…
How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models?
Mengqi Wang, Tiantian Feng, Shrikanth Narayanan
Large language models (LLMs) have enabled a wide variety of real-world applications in various domains. However, creating a high-performing application with high accuracy remains c…
LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements
Jianwei Wang, Mengqi Wang, Yinsi Zhou +5
Health, Safety, and Environment (HSE) compliance assessment demands dynamic real-time decision-making under complicated regulations and complex human-machine-environment interactio…