Search Results for author:
Found 11 papers, 7 papers with code
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs
Although multimodal large language models (MLLMs) have achieved impressive performance, the multimodal instruction tuning stage often causes catastrophic forgetting of the base LLM's language ability, even in strong models like Llama3.
Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
We investigate how large language models perform latent multi-hop reasoning in prompts like "Wolfgang Amadeus Mozart's mother's spouse is".
Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
Existing methods to mitigate bias lack a comprehensive understanding of its mechanisms or compromise the model's core capabilities.
Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies.
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations.
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
We investigate the mechanism of in-context learning (ICL) on sentence classification tasks with semantically-unrelated labels ("foo"/"bar").
Neuron-Level Knowledge Attribution in Large Language Models
Additionally, since most static methods typically only identify "value neurons" directly contributing to the final prediction, we propose a method for identifying "query neurons" which activate these "value neurons".
Emotion Detection for Misinformation: A Review
The emotions and sentiments of netizens, as expressed in social media posts and news, constitute important factors that can help to distinguish fake news from genuine news and to understand the spread of rumors.
CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching
We adopt Deep Pyramid Convolutional Neural Network (DPCNN) for source code feature extraction and Graph Neural Network (GNN) for binary code feature extraction.
Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation
User modeling is an essential task for online rec- ommender systems.
Ranked #2 on
Recommendation Systems
on Amazon Product Data
Sliced Recurrent Neural Networks
In this paper, we introduce sliced recurrent neural networks (SRNNs), which could be parallelized by slicing the sequences into many subsequences.
Ranked #6 on
Sentiment Analysis
on Amazon Review Full
