XuHao Hu

Foreshhh's activity

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

commented a paper 3 months ago

LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

Paper • 2510.08211 • Published Oct 9, 2025 • 22 •

2

New activity in OpenSafetyLab/MD-Judge-v0_2-internlm2_7b 5 months ago

Unable to download the model

5

#2 opened about 1 year ago by

sriharshasurineni

New activity in Foreshhh/vlsbench 5 months ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

Question about image files - no images found when loading dataset

3

#2 opened 5 months ago by

leo1200213

New activity in OpenSafetyLab/t2i_safety_dataset 5 months ago

Improve dataset card for T2ISafety benchmark

#1 opened 6 months ago by

nielsr

commented a paper about 1 year ago

VLSBench: Unveiling Visual Leakage in Multimodal Safety

Paper • 2411.19939 • Published Nov 29, 2024 • 10 •

2

New activity in OpenSafetyLab/Salad-Data about 1 year ago

Paraphrased questions from the base set in a new dataset

👍 2

2

#2 opened about 1 year ago by

skirdey-inflection

New activity in OpenSafetyLab/MD-Judge-v0_2-internlm2_7b over 1 year ago

It's a great model, and I have a few questions.

3

#1 opened over 1 year ago by

chelcy

New activity in OpenSafetyLab/MD-Judge-v0.1 over 1 year ago

Batch inference via huggingface.

1

#2 opened over 1 year ago by

anki08

New activity in OpenSafetyLab/Salad-Bench-Leaderboard almost 2 years ago

What is `dommension`?

1

#1 opened almost 2 years ago by

zhiminy

New activity in OpenSafetyLab/MD-Judge-v0.1 almost 2 years ago

Is there a suitable method of fine tuning for multiple languages?

2

#1 opened almost 2 years ago by

shimatar0