Social AI Studio's Projects
Official repository of EMNLP'23 Findings "Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer"
Official repository for SocialNLP'24 paper "Contrastive Disentanglement for Authorship Attribution"
This repository contains the source code of Dragnet++
Code implement for "Unsupervised User Identity Linkage via Factoid Embedding" (ICDM'18)
Code implementation for the paper "Evaluating GPT-3 Generated Explanations for Hateful Content Moderation" (IJCAI'23).
Code implementation for "Discovering Hidden Topical Hubs and Authorities in Online Social Networks" (SDM'18)
Official repository for IEEE TCSS paper "Model-agnostic meta-learning for multilingual hate speech detection"
Dataset and code implementation for the paper "Decoding the Underlying Meaning of Multimodal Hateful Memes" (IJCAI'23).
Official repository for COLM'24 paper "InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification"
Code implementation for the paper "Keen2Act: Activity Recommendation in Online Social Collaborative Platforms" (UMAP'20).
Official repository for EMNLP'23 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Code implementation for the paper "Evaluating The Sociodemographic Biases Of Large Language Models In Offensive Content Detection Using Simulated Personas"
Official repository for ACM Multimedia'23 paper "MATK: The Meme Analytical Tool Kit"
Repo for Meme Stance Detection
Official repository for WWW'24 paper "MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation"
Official repository for IEEE BigData'23 paper "MERMAID: A Dataset and Framework for Multimodal Meme Semantic Understanding"
Official repository for WWW'24 paper "Modularized Networks for Few-shot Hateful Meme Detection"
Code implementation for "Discovering hidden topical hubs and authorities across multiple online social networks" (TKDE'19)