Harry Mayne

HarryMayne's activity

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

upvoted a paper 2 months ago

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Paper • 2511.04703 • Published Nov 3, 2025 • 8

upvoted a paper 9 months ago

Clinical knowledge in LLMs does not translate to human interactions

Paper • 2504.18919 • Published Apr 26, 2025 • 26

upvoted a paper 10 months ago

LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation

Paper • 2503.02972 • Published Mar 4, 2025 • 25

upvoted 2 papers about 1 year ago

Can sparse autoencoders be used to decompose and interpret steering vectors?

Paper • 2411.08790 • Published Nov 13, 2024 • 8

Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction

Paper • 2411.06424 • Published Nov 10, 2024 • 5

upvoted a paper over 1 year ago

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4, 2024 • 101