3 papers
cs.CL2026
WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents
Yuqing Zhou, Zhuoer Wang, Jie Yuan +4
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substant…
cs.LG2024
Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
Yuqing Zhou, Ziwei Zhu
In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the…
cs.CL2024
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models
Yuqing Zhou, Ruixiang Tang, Ziyu Yao +1
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of…