Sayan Layek

caprion's activity

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

liked a dataset 5 days ago

SoftMINER-Group/NicheHazardQA

Viewer • Updated 24 days ago • 388 • 60 • 6

authored 3 papers 8 months 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

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Paper • 2406.11801 • Published Jun 17, 2024 • 16

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance

Paper • 2406.11139 • Published Jun 17, 2024 • 13

upvoted a paper 8 months 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

upvoted a collection 8 months ago

AI and Safety

Collection

We published in several top NLP/AI conferences such as ACL, EMNLP, AAAI, ICWSM • 8 items • Updated Jan 14 • 4

authored a paper 8 months ago

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

Paper • 2406.12274 • Published Jun 18, 2024 • 16

upvoted 3 papers 8 months ago

Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance

Paper • 2406.11139 • Published Jun 17, 2024 • 13

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

Paper • 2406.12274 • Published Jun 18, 2024 • 16

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

Paper • 2406.11801 • Published Jun 17, 2024 • 16

updated 2 datasets 10 months ago

caprion/Data_Annotation

Viewer • Updated May 5, 2024 • 30.5k • 38

caprion/Temp

Viewer • Updated Apr 16, 2024 • 700 • 40

upvoted a paper about 1 year ago

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

Paper • 2401.10647 • Published Jan 19, 2024 • 4

authored 2 papers about 1 year ago

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context

Paper • 2401.12671 • Published Jan 23, 2024 • 2

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models

Paper • 2401.10647 • Published Jan 19, 2024 • 4