Responsible AI

Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks ICML 2024 FairRR: Pre-Processing for Group Fairness through Randomized Response AISTATS 2024 FBK@IWSLT Test Suites Task: Gender Bias evaluation with MuST-SHE ACL 2024 Finding ε and δ of Traditional Disclosure Control Systems AAAI 2024 FLAME : Factuality-Aware Alignment for Large Language Models NeurIPS 2024 Flames: Benchmarking Value Alignment of LLMs in Chinese NAACL 2024 “Flex Tape Can’t Fix That”: Bias and Misinformation in Edited Language Models EMNLP 2024 Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024 FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts COLING 2024 From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment EMNLP 2024 From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP EMNLP 2024 From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking EMNLP 2024 From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning ICML 2024 Fundamental Limitations of Alignment in Large Language Models ICML 2024 GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets EMNLP 2024 Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts EMNLP 2024 Gendered Grammar or Ingrained Bias? Exploring Gender Bias in Icelandic Language Models COLING 2024 Gender Identity in Pretrained Language Models: An Inclusive Approach to Data Creation and Probing EMNLP 2024 Generative Debunking of Climate Misinformation ACL 2024 Generative Judge for Evaluating Alignment ICLR 2024 Geo-Cultural Representation and Inclusion in Language Technologies COLING 2024 “Global is Good, Local is Bad?”: Understanding Brand Bias in LLMs EMNLP 2024 Glue pizza and eat rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models EMNLP 2024 GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory EMNLP 2024 GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation EMNLP 2024