LLM Latent Adversarial Training

LLM-LAT's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

stecas 

authored a paper 9 days ago

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published 11 days ago • 16

aengusl 

authored a paper 5 months ago

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Paper • 2407.15549 • Published Jul 22, 2024

CindyXWu 

authored 2 papers 6 months ago

Using Degeneracy in the Loss Landscape for Mechanistic Interpretability

Paper • 2405.10927 • Published May 17, 2024 • 3

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Paper • 2407.15549 • Published Jul 22, 2024

stecas 

authored 2 papers 6 months ago

Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Paper • 2403.05030 • Published Mar 8, 2024

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Paper • 2407.15549 • Published Jul 22, 2024

stecas 

updated a Space 6 months ago

Running

README

🌍

abhayesian 

updated 2 models 6 months ago

LLM-LAT/robust-llama3-8b-instruct

Text Generation • Updated Aug 1, 2024 • 2.05k • 10

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust3

Updated Aug 1, 2024

stecas 

updated 2 datasets 7 months ago

LLM-LAT/benign-dataset

Viewer • Updated Jul 24, 2024 • 165k • 263 • 1

LLM-LAT/harmful-dataset

Viewer • Updated Jul 24, 2024 • 4.95k • 1.23k • 8

abhayesian 

updated 5 models 7 months ago

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust3

Updated Jul 23, 2024 • 1

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust2

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust1

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust2

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust1

Updated Jul 23, 2024

CindyXWu 

updated 3 models 7 months ago

LLM-LAT/llama2-7b-chat-lat-unlearn-harry-potter-stronger-unlearning

Text Generation • Updated Jul 22, 2024 • 9 • 1

LLM-LAT/llama2-7b-chat-lat-unlearn-harry-potter-normal

Text Generation • Updated Jul 22, 2024 • 8

LLM-LAT/zephyr7b-beta-rmu-lat-unlearn-wmdp-bio-cyber

Text Generation • Updated Jul 22, 2024 • 6 • 1

Baidicoot 

updated a model 7 months ago

LLM-LAT/llama2-7b-chat-lat-removed-backdoor5

Text Generation • Updated Jul 5, 2024 • 8