Gongshen Liu

An Aspect Level Sentiment Analysis Based on Embedding Tuning & Attention Neural Network

2018

A novel framework based on neural network is proposed to predict sentiment polarity of aspects in a sentence. The proposed model finely tunes pre-trained word embedding in order to get more accurate embedding for aspect-based …

U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario

2025 · arXiv (Cornell University)

With the widespread use of social media, user-generated content has surged on online platforms. When such content includes hateful, abusive, offensive, or cyberbullying behavior, it is classified as toxic speech, posing a significant threat to …

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

2025 · arXiv (Cornell University)

Multi-Modal Large Language Models (MLLMs) have exhibited remarkable performance on various vision-language tasks such as Visual Question Answering (VQA). Despite accumulating evidence of privacy concerns associated with task-relevant content, it remains unclear whether MLLMs inadvertently …

Adaptive User Modeling with Long and Short-Term Preferences for Personalized Recommendation

2019

User modeling is an essential task for online recommender systems. In the past few decades, collaborative filtering (CF) techniques have been well studied to model users' long term preferences. Recently, recurrent neural networks (RNN) have …