Publications by Zeping Yu

Papers by Zeping Yu at NaCTeM, newest first. All publications

2026 | 2025 | 2024

9 publications

2026

zhang, H., Zhang, Z., Nie, E., Wang, M., Yu, Z., Su, Z., Wang, Y., Wang, Q., Yuan, S., Duan, X., Xue, Q., Yu, Z., Shang, C., Liang, X., Xiong, J. R., Shen, H., Tao, C., Liu, Z., Jin, S., Xi, Z., Zhang, D., Ananiadou, S., Gui, T., Xie, R., So, H. K., Schuetze, H., Huang, X., Zhang, Q. and Wong, N., Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models, in: Findings of the Association for Computational Linguistics:, pages 10317–10362, 2026 [Pure]

2025

Yu, Z., Belinkov, Y. and Ananiadou, S., Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models, in: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 11257–11272, 2025 [DOI] [URL] [Pure]
Yu, Z. and Ananiadou, S., Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs, in: Findings of the Association for Computational Linguistics: EMNLP 2025, pages 7065–7078, 2025 [DOI] [URL] [Pure]
Yu, Z. and Ananiadou, S., Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing, in: arXiv, 2025 [URL]

2024

Liu, Z., Zhang, T., Yang, K., Thompson, P., Yu, Z. and Ananiadou, S., Emotion detection for misinformation: A review, in: Information Fusion, 2024 [DOI] [Pure]
Yu, Z. and Ananiadou, S., How do Large Language Models Learn In-Context?: Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3281–3292, 2024 [DOI] [URL] [Pure]
Yu, Z. and Ananiadou, S., Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3293–3306, 2024 [DOI] [URL] [Pure]
Yu, Z. and Ananiadou, S., Neuron-Level Knowledge Attribution in Large Language Models, in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3267–3280, 2024 [DOI] [URL] [Pure]
Yu, Z. and Ananiadou, S., Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering, in: arXiv, 2024 [URL]