I am a PhD student at University of Manchester, supervised by Prof. Sophia Ananiadou. Previously, I worked as a deep learning researcher at Tencent Technology, where I used deep learning models to improve the accuracy of binary code similarity detection and binary source code matching.

Currently, my research focuses on:

a) Understanding LLMs and MLLMs. Identifying important paramaters in LLMs and understanding how LLMs work. My research has investigated the underlying mechanisms of factual knowledge, arithmetic, latent multi-hop reasoning, in-context learning, and visual question answering.

b) LLM post-training. Analyzing LLMs and designing methods to enhance LLMs’ capabilities (knowledge, arithmetic, reasoning, multimodal) during post-training. I have developed the back attention module to improve the latent multi-hop reasoning ability of LLMs.

c) Model editing for LLM. Identifying and editing the important parameters to reduce hallucination, unfairness, toxicity, and bias in LLMs. I designed the neuron-level model editing technique to mitigate gender bias without hurting the LLM’s existing capabilities.

My email is zepingyu@foxmail.com.

🔥 News

2025.2: New preprint: Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models. This work investigates the mechanism of latent multi-hop reasoning and propose the back attention module to enhance the latent multi-hop reasoning ability in LLMs.
2025.1: New preprint: Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing. This work investigates the mechanism of gender bias and proposes a neuron-level model editing method to reduce gender bias in LLMs without hurting the existing abilities.
2024.12: I’ve compiled paper lists of SAE and neuron in LLMs.
2024.11: New preprint: Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering. This work explores the mechanism of Llava in visual question answering.
2024.09: Our work is accepted by EMNLP 2024 (main): Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis. This work explores the neuron-level information flow of arithmetic mechanism in LLMs and proposes a model pruning method for arithmetic tasks.
2024.09: Our work is accepted by EMNLP 2024 (main): Neuron-Level Knowledge Attribution in Large Language Models. This work introduces how to identify important neurons in LLMs, and explores the neuron-level information flow of factual knowledge mechanism.
2024.09: Our work is accepted by EMNLP 2024 (main): How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning. This work explores the mechanism of in-context learning in LLMs.
2024.04: I’ve compiled a paper list for those interested in exploring the mechanisms of LLMs.