Social AI Studio
Welcome to the Gitlab repositories for Social AI Studio! We are a group of researchers based in the Singapore University of Technology and Design (SUTD).
Singapore
Pinned Repositories
GPT3-HateEval
Code implementation for the paper "Evaluating GPT-3 Generated Explanations for Hateful Content Moderation" (IJCAI'23).
HateMAML
Official repository for IEEE TCSS paper "Model-agnostic meta-learning for multilingual hate speech detection"
HatReD
Dataset and code implementation for the paper "Decoding the Underlying Meaning of Multimodal Hateful Memes" (IJCAI'23).
MATK
Official repository for ACM Multimedia'23 paper "MATK: The Meme Analytical Tool Kit"
MemeCraft
Official repository for WWW'24 paper "MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation"
Mod_HATE
Official repository for WWW'24 paper "Modularized Networks for Few-shot Hateful Meme Detection"
MultiHateClip
Official repository for ACM Multimedia'24 paper "MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili"
Pro-Cap
Official repository for ACM Multimedia'23 paper "Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection"
SGHateCheck
Official repository for WOAH'24 paper "SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore"
ToxiCloakCN
Official repository for EMNLP'24 paper "ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations"
Social AI Studio's Repositories
Social-AI-Studio/ToxiCloakCN
Official repository for EMNLP'24 paper "ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations"
Social-AI-Studio/HatReD
Dataset and code implementation for the paper "Decoding the Underlying Meaning of Multimodal Hateful Memes" (IJCAI'23).
Social-AI-Studio/MATK
Official repository for ACM Multimedia'23 paper "MATK: The Meme Analytical Tool Kit"
Social-AI-Studio/Pro-Cap
Official repository for ACM Multimedia'23 paper "Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection"
Social-AI-Studio/HateMAML
Official repository for IEEE TCSS paper "Model-agnostic meta-learning for multilingual hate speech detection"
Social-AI-Studio/Mod_HATE
Official repository for WWW'24 paper "Modularized Networks for Few-shot Hateful Meme Detection"
Social-AI-Studio/MemeCraft
Official repository for WWW'24 paper "MemeCraft: Contextual and Stance-Driven Multimodal Meme Generation"
Social-AI-Studio/SGHateCheck
Official repository for WOAH'24 paper "SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore"
Social-AI-Studio/GPT3-HateEval
Code implementation for the paper "Evaluating GPT-3 Generated Explanations for Hateful Content Moderation" (IJCAI'23).
Social-AI-Studio/MultiHateClip
Official repository for ACM Multimedia'24 paper "MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili"
Social-AI-Studio/Adapter-TST
Official repository of EMNLP'23 Findings "Adapter-TST: A Parameter Efficient Method for Multiple-Attribute Text Style Transfer"
Social-AI-Studio/InstructAV
Official repository for COLM'24 paper "InstructAV: Instruction Fine-tuning Large Language Models for Authorship Verification"
Social-AI-Studio/Bridging-Modalities
Social-AI-Studio/PromptAV
Official repository for EMNLP'23 Findings "Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification"
Social-AI-Studio/PromptMTopic
Official repository for ACM Multimedia'23 paper "PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models"
Social-AI-Studio/Snowman-Application-Tasks-AY22-23
Social-AI-Studio/Meme-Stance-Detection
Repo for Meme Stance Detection
Social-AI-Studio/MUSCAT
Social-AI-Studio/Bottleshop-Reading-Group-2022
Social-AI-Studio/ContrastiveAA
Official repository for SocialNLP'24 paper "Contrastive Disentanglement for Authorship Attribution"
Social-AI-Studio/DeepStyle
Social-AI-Studio/Explain_Rumor
Social-AI-Studio/LLM-Adapters
Official repository for EMNLP'23 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"
Social-AI-Studio/MaskedModX
Code implementation for the paper "Evaluating The Sociodemographic Biases Of Large Language Models In Offensive Content Detection Using Simulated Personas"
Social-AI-Studio/MERMAID
Official repository for IEEE BigData'23 paper "MERMAID: A Dataset and Framework for Multimodal Meme Semantic Understanding"
Social-AI-Studio/Plan-and-Solve-Prompting
Code for our ACL 2023 Paper "Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models".
Social-AI-Studio/Snowman-Application-Tasks-AY20-21
Social-AI-Studio/Snowman-Application-Tasks-AY21-22
Social-AI-Studio/system-demonstrations
Social-AI-Studio/WWW-24-Tutorial-Understanding-Dark-Humour