Merging Improves Self-Critique Against Jailbreak Attacks
Paper
•
2406.07188
•
Published
•
4
Victor Gallego
vicgalle
AI & ML interests
Preference fine-tuning, alignment & synthetic data.
Building LLMs in general!
Recent Activity
liked
a dataset
5 days ago
common-pile/caselaw_access_project
liked
a dataset
5 days ago
NousResearch/Hermes-3-Dataset
liked
a model
9 days ago
moonshotai/Kimi-K2-Instruct
Organizations
authored
a
paper
about 1 year ago
authored
3
papers
over 1 year ago
Configurable Safety Tuning of Language Models with Synthetic Preference Data
Paper
•
2404.00495
•
Published
•
2
Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs
Paper
•
2402.08005
•
Published
•
1
Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective
Paper
•
2312.01957
•
Published
•
1
authored
3
papers
almost 2 years ago
Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation
Paper
•
2308.07929
•
Published
•
1
Personalizing Text-to-Image Generation via Aesthetic Gradients
Paper
•
2209.12330
•
Published
•
1
ZYN: Zero-Shot Reward Models with Yes-No Questions
Paper
•
2308.06385
•
Published
•
1