← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token NIPS 2024
Representation Noising: A Defence Mechanism Against Harmful Finetuning NIPS 2024
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs NIPS 2024
Fast Best-of-N Decoding via Speculative Rejection NIPS 2024
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs NIPS 2024
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NIPS 2024
Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models NIPS 2024
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NIPS 2024
Selective Generation for Controllable Language Models NIPS 2024
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence NIPS 2024
Calibrated Self-Rewarding Vision Language Models NIPS 2024
Stealth edits to large language models NIPS 2024
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models NIPS 2024
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models NIPS 2024
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature NIPS 2024
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security NIPS 2024
Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation EMNLP 2024
On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models EMNLP 2024
Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection EMNLP 2024
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections EMNLP 2024
AgentReview: Exploring Peer Review Dynamics with LLM Agents EMNLP 2024
Towards Tool Use Alignment of Large Language Models EMNLP 2024
Evaluating Psychological Safety of Large Language Models EMNLP 2024
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024
Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism EMNLP 2024