Responsible AI

Just Because We Camp, Doesn't Mean We Should: The Ethics of Modelling Queer Voices. Interspeech 2024 KorNAT: LLM Alignment Benchmark for Korean Social Values and Common Knowledge ACL 2024 KorSmishing Explainer: A Korean-centric LLM-based Framework for Smishing Detection and Explanation Generation EMNLP 2024 Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024 Large Language Models Are Not Robust Multiple Choice Selectors ICLR 2024 Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark EMNLP 2024 Large Language Model Unlearning NeurIPS 2024 Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs EACL 2024 Learning to Unlearn: Instance-Wise Unlearning for Pre-trained Classifiers AAAI 2024 Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism EMNLP 2024 Legal and Ethical Considerations that Hinder the Use of LLMs in a Finnish Institution of Higher Education COLING 2024 Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information NAACL 2024 LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models NeurIPS 2024 Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination EMNLP 2024 LIRE: listwise reward enhancement for preference alignment ACL 2024 LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses ICLR 2024 LLM Evaluators Recognize and Favor Their Own Generations NeurIPS 2024 LLM generated responses to mitigate the impact of hate speech EMNLP 2024 LLMGuard: Guarding against Unsafe LLM Behavior AAAI 2024 LLM Tropes: Revealing Fine-Grained Values and Opinions in Large Language Models EMNLP 2024 Local Contrastive Editing of Gender Stereotypes EMNLP 2024 Localization and Manipulation of Immoral Visual Cues for Safe Text-to-Image Generation WACV 2024 LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models EMNLP 2024 M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection ACL 2024 M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection EACL 2024