Skip to content
conftrace_
2025 ICML ICML 2025

The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Zihao Wang, Yibo Jiang, Jiahao Yu, Heqing Huang

Topics

Machine Learning > Core Methods > Representation Learning Natural Language Processing > Resources & Methods > Large Language Models Artificial Intelligence > Core AI > Large Language Models

Keywords

data augmentation large language model position id shortcuts role separation token-wise cues
Download PDF