conftrace_

harmful content

66 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) safety alignment (178) adversarial attack (1621) model alignment (226) safety evaluation (94) llm safety (67) ai safety (235) model safety (101) adversarial learning (1595)

Papers

UNIWIZ: A Unified Large Language Model Orchestrated Wizard for Safe Knowledge Grounded Conversations ACL 2024
Towards Safer Large Language Models through Machine Unlearning ACL 2024
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis EMNLP 2024
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024
Course-Correction: Safety Alignment Using Synthetic Preferences EMNLP 2024
Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming EMNLP 2024
ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information EMNLP 2024
MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024
Large Language Model Unlearning NIPS 2024
Who's asking? User personas and the mechanics of latent misalignment NIPS 2024
Multi-step Jailbreaking Privacy Attacks on ChatGPT EMNLP 2023
Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems EMNLP 2023
Measuring Harmful Representations in Scandinavian Language Models EMNLP 2022
Red Teaming Language Models with Language Models EMNLP 2022
Detecting and Understanding Harmful Memes: A Survey IJCAI 2022
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models NIPS 2022