Yik Siu Chan

yiksiu's activity

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

upvoted a paper about 1 month ago

Revisiting Generalization Across Difficulty Levels: It's Not So Easy

Paper • 2511.21692 • Published Nov 26, 2025 • 15

updated a model 6 months ago

yiksiu/mib_test_submission_2

Updated Jun 23, 2025

published a model 6 months ago

yiksiu/mib_test_submission_2

Updated Jun 23, 2025

updated a model 6 months ago

yiksiu/mib_causal_variable_test

Updated Jun 23, 2025

published a model 6 months ago

yiksiu/mib_causal_variable_test

Updated Jun 23, 2025

updated a collection 9 months ago

MIB Datasets

Collection

The tasks and counterfactuals from the Mechanistic Interpretability Benchmark. • 7 items • Updated Apr 16, 2025 • 4

updated a dataset 9 months ago

mib-bench/ravel

Viewer • Updated May 31, 2025 • 117k • 32

published a dataset 9 months ago

mib-bench/ravel

Viewer • Updated May 31, 2025 • 117k • 32

updated a collection 9 months ago

MIB Datasets

Collection

The tasks and counterfactuals from the Mechanistic Interpretability Benchmark. • 7 items • Updated Apr 16, 2025 • 4

updated a dataset 9 months ago

yiksiu/mib_ravel

Viewer • Updated Apr 3, 2025 • 132k • 14

published a dataset 11 months ago

yiksiu/mib_ravel

Viewer • Updated Apr 3, 2025 • 132k • 14

upvoted a paper 11 months ago

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

Paper • 2502.04322 • Published Feb 6, 2025 • 3

updated 6 datasets 12 months ago

yiksiu/arithmetic_division

Viewer • Updated Jan 15, 2025 • 1.22k • 29

yiksiu/arithmetic_multiplication

Viewer • Updated Jan 15, 2025 • 44.3k • 25

mib-bench/arithmetic_subtraction

Viewer • Updated May 31, 2025 • 20.9k • 39

yiksiu/arithmetic_subtraction

Viewer • Updated Jan 15, 2025 • 22.4k • 20

mib-bench/arithmetic_addition

Viewer • Updated May 31, 2025 • 40.4k • 87

yiksiu/arithmetic_addition

Viewer • Updated Jan 15, 2025 • 44.3k • 34

updated a model 12 months ago

yiksiu/EuroLLM-1.7B-DPO-full_with_refusal

Text Generation • 2B • Updated Jan 12, 2025 • 8

updated a dataset 12 months ago

mib-bench/arithmetic_subtraction

Viewer • Updated May 31, 2025 • 20.9k • 39