← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Bypassing LLM Watermarks with Color-Aware Substitutions ACL 2024
Do Clinicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation ACL 2024
A StrongREJECT for Empty Jailbreaks NIPS 2024
Robust Reinforcement Learning from Corrupted Human Feedback NIPS 2024
SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types NIPS 2024
Large Language Model Unlearning via Embedding-Corrupted Prompts NIPS 2024
Uncovering Safety Risks of Large Language Models through Concept Activation Vector NIPS 2024
Rule Based Rewards for Language Model Safety NIPS 2024
Risk-Averse Fine-tuning of Large Language Models NIPS 2024
RedCode: Risky Code Execution and Generation Benchmark for Code Agents NIPS 2024
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack NIPS 2024
Stepwise Alignment for Constrained Language Model Policy Optimization NIPS 2024
$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs NIPS 2024
Can Models Learn Skill Composition from Examples? NIPS 2024
Rapid Plug-in Defenders NIPS 2024
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices NIPS 2024
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection NAACL 2024
How Susceptible Are LLMs to Logical Fallacies? COLING 2024
Formalisation and Evaluation of Properties for Consequentialist Machine Ethics IJCAI 2024
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling NIPS 2024
Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models NIPS 2024
A Closer Look at Robustness of Vision Transformers to Backdoor Attacks WACV 2024
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level NIPS 2024
Data Free Backdoor Attacks NIPS 2024
If You Want to Be Robust, Be Wary of Initialization NIPS 2024