Responsible AI

Intersectional Bias in Japanese Large Language Models from a Contextualized Perspective ACL 2025 Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces ICML 2025 Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding ICCV 2025 Intrinsic Bias is Predicted by Pretraining Data and Correlates with Downstream Performance in Vision-Language Encoders NAACL 2025 Intrinsic Linguistic Bias in Formal vs. Informal Bengali Pragmatics with Progressive Context Inflation IJCNLP 2025 Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models NAACL 2025 Investigating and Mitigating Undesirable Biases in Large Language Models AAAI 2025 Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception COLING 2025 Investigating Gender Bias in Text-to-Audio Generation Models Interspeech 2025 Investigating Value-Reasoning Reliability in Small Large Language Models EMNLP 2025 InvisMark: Invisible and Robust Watermarking for AI-Generated Image Provenance WACV 2025 ISACL: Internal State Analyzer for Copyrighted Training Data Leakage EMNLP 2025 Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness ICLR 2025 iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss SemEval 2025 IslamicEval 2025: The First Shared Task of Capturing LLMs Hallucination in Islamic Content EMNLP 2025 Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs ICML 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 Iterative Multilingual Spectral Attribute Erasure EMNLP 2025 Iterative Prompt Refinement for Safer Text-to-Image Generation EMNLP 2025 It’s My Data Too: Private ML for Datasets with Multi-User Training Examples ICML 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025 Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025 JBBQ: Japanese Bias Benchmark for Analyzing Social Biases in Large Language Models ACL 2025 Joint Vision-Language Social Bias Removal for CLIP CVPR 2025 K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean ACL 2025