Responsible AI

MACE: Mass Concept Erasure in Diffusion Models CVPR 2024 Machine Unlearning of Pre-trained Large Language Models ACL 2024 MAGE: Machine-generated Text Detection in the Wild ACL 2024 Making Harmful Behaviors Unlearnable for Large Language Models ACL 2024 MarkLLM: An Open-Source Toolkit for LLM Watermarking EMNLP 2024 MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024 Mathematical Framework for Online Social Media Auditing JMLR 2024 MBIAS: Mitigating Bias in Large Language Models While Retaining Context ACL 2024 Measuring Political Bias in Large Language Models: What Is Said and How It Is Said ACL 2024 Media Bias Detection Across Families of Language Models NAACL 2024 MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models NeurIPS 2024 MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme Intervention ACL 2024 Merging AI Incidents Research with Political Misinformation Research: Introducing the Political Deepfakes Incidents Database AAAI 2024 MICo: Preventative Detoxification of Large Language Models through Inhibition Control NAACL 2024 MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents EMNLP 2024 MisgenderMender: A Community-Informed Approach to Interventions for Misgendering NAACL 2024 MisinfoEval: Generative AI in the Era of “Alternative Facts” EMNLP 2024 Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NeurIPS 2024 Mitigate Extrinsic Social Bias in Pre-trained Language Models via Continuous Prompts Adjustment EMNLP 2024 Mitigating Hallucination in Fictional Character Role-Play EMNLP 2024 Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting AAAI 2024 Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models NeurIPS 2024 Modeling the Sacred: Considerations when Using Religious Texts in Natural Language Processing NAACL 2024 Model Merging and Safety Alignment: One Bad Model Spoils the Bunch EMNLP 2024