-
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
Paper • 2502.15086 • Published • 15 -
How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?
Paper • 2502.14502 • Published • 83 -
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information
Paper • 2502.14258 • Published • 25 -
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper • 2502.12853 • Published • 28
Hyuhng Joon Kim
heyjoonkim
AI & ML interests
Machine Learning, Natural Language Processing (NLP), Uncertainty, Abstention for Reliability
Recent Activity
updated
a collection
10 days ago
todo
updated
a collection
10 days ago
todo
updated
a collection
10 days ago
todo
Organizations
None yet
Collections
1
models
5
heyjoonkim/llama2-7b_orca_mink_10000
Text Generation
•
Updated
•
18
heyjoonkim/llama2-7b_orca_full_50000
Text Generation
•
Updated
•
11
heyjoonkim/llama2-7b_orca_nll_average_top_10000
Text Generation
•
Updated
•
11
heyjoonkim/llama2-7b_orca_random_10000
Text Generation
•
Updated
•
10
heyjoonkim/llama2-7b_orca_entropy_average_top_9988
Text Generation
•
Updated
•
11
datasets
None public yet