Nicholas Crispino

ncrispino's activity

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

updated a dataset about 1 month ago

ncrispino/tool-call-steering-data

Updated Dec 4, 2025 • 11

published a dataset about 1 month ago

ncrispino/tool-call-steering-data

Updated Dec 4, 2025 • 11

updated a dataset about 1 month ago

WangResearchLab/SteeringSafety

Viewer • Updated Nov 25, 2025 • 84.5k • 561 • 3

updated a dataset 3 months ago

WangResearchLab/AgentInstruct

Viewer • Updated Oct 20, 2025 • 53 • 47 • 2

upvoted 2 papers 3 months ago

Budget-aware Test-time Scaling via Discriminative Verification

Paper • 2510.14913 • Published Oct 16, 2025 • 4

Predicting Task Performance with Context-aware Scaling Laws

Paper • 2510.14919 • Published Oct 16, 2025 • 3

authored a paper 4 months ago

RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16, 2025 • 4

updated a collection 4 months ago

LLM Interpretability

Collection

Interpretability papers from Prof. Chenguang Wang's lab at UCSC • 3 items • Updated Sep 19, 2025

upvoted a paper 4 months ago

COSMIC: Generalized Refusal Direction Identification in LLM Activations

Paper • 2506.00085 • Published May 30, 2025 • 2

New activity in WangResearchLab/SteeringSafety 4 months ago

Add license, task categories, language, tags, and detailed sample usage

1

#2 opened 4 months ago by

nielsr

upvoted a paper 4 months ago

RepIt: Representing Isolated Targets to Steer Language Models

Paper • 2509.13281 • Published Sep 16, 2025 • 4

authored a paper 4 months ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16, 2025 • 7

commented a paper 4 months ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16, 2025 • 7 •

2

liked a dataset 4 months ago

WangResearchLab/SteeringSafety

Viewer • Updated Nov 25, 2025 • 84.5k • 561 • 3

updated a collection 4 months ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated Oct 20, 2025 • 1

upvoted a collection 4 months ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated Oct 20, 2025 • 1

upvoted a paper 4 months ago

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

Paper • 2509.13450 • Published Sep 16, 2025 • 7

updated a collection 4 months ago

SteeringSafety

Collection

A benchmark for evaluating effectiveness and entanglement in representation steering across seven safety-relevant perspectives • 2 items • Updated Oct 20, 2025 • 1