RIMA HAZRA

rimahazra's activity

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

liked a dataset 17 days ago

SoftMINER-Group/SafeTutors

Preview • Updated Aug 27 • 37 • 3

updated a dataset about 1 month ago

SoftMINER-Group/SafeTutors

Preview • Updated Aug 27 • 37 • 3

published a dataset about 1 month ago

SoftMINER-Group/SafeTutors

Preview • Updated Aug 27 • 37 • 3

updated a collection 12 months ago

AI and Safety

Collection

We published in several top NLP/AI conferences such as ACL, EMNLP, AAAI, ICWSM • 11 items • Updated Oct 16, 2025 • 6

updated a collection about 1 year ago

AI and Safety

Collection

We published in several top NLP/AI conferences such as ACL, EMNLP, AAAI, ICWSM • 11 items • Updated Oct 16, 2025 • 6

liked a dataset about 1 year ago

SoftMINER-Group/Soteria

Viewer • Updated Aug 22, 2025 • 1.2k • 10 • 4

authored a paper over 1 year ago

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation

Paper • 2502.11246 • Published Feb 16, 2025 • 1

upvoted a paper over 1 year ago

MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation

Paper • 2502.11246 • Published Feb 16, 2025 • 1

updated a collection over 1 year ago

AI and Safety

Collection

We published in several top NLP/AI conferences such as ACL, EMNLP, AAAI, ICWSM • 11 items • Updated Oct 16, 2025 • 6

authored a paper over 1 year ago

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment

Paper • 2502.11244 • Published Feb 16, 2025

liked 4 datasets over 1 year ago

SoftMINER-Group/CulturalKaleidoscope_Multiturn

Preview • Updated Jan 26, 2025 • 8 • 2

SoftMINER-Group/CulturalKaleidoscope

Preview • Updated Jan 26, 2025 • 15 • 7

SoftMINER-Group/CulturalKaleidoscope_Preference

Viewer • Updated Jan 26, 2025 • 30k • 10 • 3

SoftMINER-Group/NicheHazardQA

Viewer • Updated Jan 26, 2025 • 388 • 41 • 7

commented 2 papers over 1 year ago

How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries

Paper • 2402.15302 • Published Feb 23, 2024 • 4 •

1

SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models

Paper • 2406.12274 • Published Jun 18, 2024 • 16 •

3

authored a paper over 1 year ago

Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions

Paper • 2501.01872 • Published Jan 3, 2025 • 2

upvoted a paper over 1 year ago

Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions

Paper • 2501.01872 • Published Jan 3, 2025 • 2

liked a dataset over 1 year ago

SoftMINER-Group/HarmEval

Viewer • Updated Aug 22, 2025 • 550 • 49 • 7

authored a paper almost 2 years ago

Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models

Paper • 2410.12880 • Published Oct 15, 2024 • 3