jc z

nickzzZzz's activity

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

upvoted a paper 9 days ago

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

Paper • 2606.06667 • Published 17 days ago • 1

published a model about 1 month ago

nickzzZzz/Llama-3.1-8B-instruct-risky-finance

Updated about 1 month ago

published a dataset about 1 month ago

nickzzZzz/EM

Updated about 1 month ago • 12

upvoted a paper about 1 month ago

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use

Paper • 2605.14038 • Published May 13 • 15

upvoted a paper 8 months ago

Can Aha Moments Be Fake? Identifying True and Decorative Thinking Steps in Chain-of-Thought

Paper • 2510.24941 • Published Oct 28, 2025 • 4

updated a dataset 8 months ago

nickzzZzz/Identify_true_decorative_thinking

Viewer • Updated Oct 20, 2025 • 618 • 8

published a dataset 8 months ago

nickzzZzz/Identify_true_decorative_thinking

Viewer • Updated Oct 20, 2025 • 618 • 8

authored a paper 11 months ago

LLMs Encode Harmfulness and Refusal Separately

Paper • 2507.11878 • Published Jul 16, 2025 • 1

liked a dataset 12 months ago

EleutherAI/hendrycks_math

Viewer • Updated Jan 12, 2025 • 12.5k • 128k • 105

liked a dataset about 1 year ago

sorry-bench/sorry-bench-202503

Viewer • Updated Feb 28, 2025 • 9.24k • 3.7k • 18

liked a dataset over 1 year ago

stanford-crfm/air-bench-2024

Viewer • Updated Aug 14, 2024 • 21.9k • 4.26k • 26

updated 2 datasets almost 2 years ago

CHATS-Lab/Persuasive-Jailbreaker-Data

Updated Sep 16, 2024 • 35 • 13

nickzzZzz/mckd-pseudolabels

Viewer • Updated Aug 6, 2024 • 48.5k • 7

updated a model about 3 years ago

nickzzZzz/1k_counter_stereo_disambig_llama_7b

Updated Jun 15, 2023 • 10