README
⚡
AI & ML interests
Benchmarks and Evaluation, Agentic AI for Science, AI Safety and Security, Human-AI Interaction
Recent Activity
View all activity
shreyanshpadarha
updated a Space about 19 hours ago
ammaox
authored a paper about 21 hours ago
shreyanshpadarha
authored a paper about 22 hours ago
shreyanshpadarha
updated a dataset 1 day ago
shreyanshpadarha
published a Space 3 days ago
shreyanshpadarha
published a dataset 3 days ago
ammaox
updated a dataset 3 days ago
shreyanshpadarha
authored a paper 19 days ago
ambean
authored a paper 11 months ago
ammaox
authored a paper 11 months ago
ammaox
authored a paper about 1 year ago
ammaox
authored 3 papers over 1 year ago
Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction
Paper
• 2411.06424 • Published
• 5
Can sparse autoencoders be used to decompose and interpret steering vectors?
Paper
• 2411.08790 • Published
• 8
Evaluating the role of `Constitutions' for learning from AI feedback
Paper
• 2411.10168 • Published
• 5
ambean
authored 4 papers over 1 year ago
Evaluating the role of `Constitutions' for learning from AI feedback
Paper
• 2411.10168 • Published
• 5
The PRISM Alignment Project: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
Paper
• 2404.16019 • Published
• 1
LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct Languages
Paper
• 2406.06196 • Published
Casteist but Not Racist? Quantifying Disparities in Large Language Model Bias between India and the West
Paper
• 2309.08573 • Published