Responsible AI

SPRI: Aligning Large Language Models with Context-Situated Principles ICML 2025 Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models ACL 2025 Spurious Forgetting in Continual Learning of Language Models ICLR 2025 Standard Quality Criteria Derived from Current NLP Evaluations for Guiding Evaluation Design and Grounding Comparability and AI Compliance Assessments ACL 2025 STAND-Guard: A Small Task-Adaptive Content Moderation Model COLING 2025 Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack ACL 2025 STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models EMNLP 2025 StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings EMNLP 2025 Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approach ACL 2025 Strong Preferences Affect the Robustness of Preference Models and Value Alignment ICLR 2025 Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking ICLR 2025 Style Over Substance: Evaluation Biases for Large Language Models COLING 2025 sudoLLM: On Multi-role Alignment of Language Models EMNLP 2025 SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models ICCV 2025 Summary the Savior: Harmful Keyword and Query-based Summarization for LLM Jailbreak Defense NAACL 2025 Supporting AI Literacy Teaching Through the Development of Assessments for Classroom Use AAAI 2025 SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Models EMNLP 2025 Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models ACL 2025 SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise Use NAACL 2025 Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data COLING 2025 SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains EMNLP 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation CVPR 2025 Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers AAAI 2025 Taxonomizing Representational Harms using Speech Act Theory ACL 2025