74 citations · 136 across the 10 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
cs.CL2025
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…
cs.CL2025
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…
cs.CL2025
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…