Publications (10)
Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
Zeping Yu, Sophia Ananiadou
Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into t…
Sliced Recurrent Neural Networks
Zeping Yu, Gongshen Liu
Recurrent neural networks have achieved great success in many NLP tasks. However, they have difficulty in parallelization because of the recurrent structure, so it takes much time…
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
Zeping Yu, Sophia Ananiadou
We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations. To delve into the reason, we introduce the Compar…
Emotion Detection for Misinformation: A Review
Zhiwei Liu, Tianlin Zhang, Kailai Yang +3
With the advent of social media, an increasing number of netizens are sharing and reading posts and news online. However, the huge volumes of misinformation (e.g., fake news and ru…
Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
Zeping Yu, Sophia Ananiadou
Large language models (LLMs) often exhibit gender bias, posing challenges for their safe deployment. Existing methods to mitigate bias lack a comprehensive understanding of its mec…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Neuron-Level Knowledge Attribution in Large Language Models
Zeping Yu, Sophia Ananiadou
Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution te…
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
Zeping Yu, Sophia Ananiadou
Although multimodal large language models (MLLMs) have achieved impressive performance, the multimodal instruction tuning stage often causes catastrophic forgetting of the base LLM…
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
Zeping Yu, Yonatan Belinkov, Sophia Ananiadou
We investigate how large language models perform latent multi-hop reasoning in prompts like "Wolfgang Amadeus Mozart's mother's spouse is". To analyze this process, we introduce lo…
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
Zeping Yu, Sophia Ananiadou
We investigate the mechanism of in-context learning (ICL) on sentence classification tasks with semantically-unrelated labels ("foo"/"bar"). We find intervening in only 1\% heads (…