← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Scaling the Convex Barrier with Sparse Dual Algorithms JMLR 2024
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning NAACL 2024
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models NAACL 2024
Look Who’s Talking Now: Covert Channels From Biased LLMs EMNLP 2024
IterAlign: Iterative Constitutional Alignment of Large Language Models NAACL 2024
FLIRT: Feedback Loop In-context Red Teaming EMNLP 2024
SELF-GUARD: Empower the LLM to Safeguard Itself NAACL 2024
MART: Improving LLM Safety with Multi-round Automatic Red-Teaming NAACL 2024
A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily NAACL 2024
How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities NAACL 2024
Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NIPS 2024
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents NIPS 2024
Know Thine Enemy: Adaptive Attacks on Misinformation Detection Using Reinforcement Learning ACL 2024
Reinforcement Learning-Driven LLM Agent for Automated Attacks on LLMs ACL 2024
From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards ACL 2024
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion ACL 2024
Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition ACL 2024
LIRE: listwise reward enhancement for preference alignment ACL 2024
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts ACL 2024
One-Shot Safety Alignment for Large Language Models via Optimal Dualization NIPS 2024
Bias Detection via Signaling NIPS 2024
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models NAACL 2024
CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants NAACL 2024
Towards a Unified Framework for Adaptable Problematic Content Detection via Continual Learning NAACL 2024
Ethics in Action: Training Reinforcement Learning Agents for Moral Decision-making In Text-based Adventure Games AISTATS 2024