AI Safety

Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis EMNLP 2024 Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level NeurIPS 2024 IPRemover: A Generative Model Inversion Attack against Deep Neural Network Fingerprinting and Watermarking AAAI 2024 Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment EMNLP 2024 IterAlign: Iterative Constitutional Alignment of Large Language Models NAACL 2024 JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NeurIPS 2024 Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters NeurIPS 2024 Jailbreaking LLMs with Arabic Transliteration and Arabizi EMNLP 2024 Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models ICLR 2024 Jailbreak Open-Sourced Large Language Models via Enforced Decoding ACL 2024 Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates NeurIPS 2024 KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models ACL 2024 KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions ACL 2024 Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method NAACL 2024 Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning ACL 2024 k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text ACL 2024 Language Agents: Foundations, Prospects, and Risks EMNLP 2024 Language-guided Manipulator Motion Planning with Bounded Task Space CoRL 2024 Language Model Detectors Are Easily Optimized Against ICLR 2024 Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain NAACL 2024 Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024 Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024 Large Language Models Must Be Taught to Know What They Don’t Know NeurIPS 2024 Large Language Models Relearn Removed Concepts ACL 2024 Large Language Model Unlearning via Embedding-Corrupted Prompts NeurIPS 2024