5 papers
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…
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…
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…
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…