Responsible AI

SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024 SelfIE: Self-Interpretation of Large Language Model Embeddings ICML 2024 Self-Recognition in Language Models EMNLP 2024 Selling Personal Information: Data Brokers and the Limits of US Regulation COLING 2024 Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment CVPR 2024 Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation AAAI 2024 Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NeurIPS 2024 SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation EMNLP 2024 Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs ACL 2024 SLM as Guardian: Pioneering AI Safety with Small Language Model EMNLP 2024 Small Language Model Can Self-Correct AAAI 2024 Smooth Lower Bounds for Differentially Private Algorithms via Padding-and-Permuting Fingerprinting Codes COLT 2024 SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples CVPR 2024 SocialGaze: Improving the Integration of Human Social Norms in Large Language Models EMNLP 2024 Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning AAAI 2024 SoFA: Shielded On-the-fly Alignment via Priority Rule Following ACL 2024 Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models ACL 2024 STAR: SocioTechnical Approach to Red Teaming Language Models EMNLP 2024 Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections NAACL 2024 Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks ACL 2024 Style-Specific Neurons for Steering LLMs in Text Style Transfer EMNLP 2024 Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models ACL 2024 Subtle Signatures, Strong Shields: Advancing Robust and Imperceptible Watermarking in Large Language Models ACL 2024 Supporting Upper Elementary Students in Learning AI Concepts with Story-Driven Game-Based Learning AAAI 2024 Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the US EMNLP 2024