arxiv:2611.05287
🏗️ Building on HF
Sohan Venkatesh
sohv
AI & ML interests
NLP | Large Language Models | AI Safety
Recent Activity
updated a model about 1 hour ago
knowingly-wrong/cem updated a dataset about 10 hours ago
sohv/lasr authored a paper 1 day ago
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce MisalignmentOrganizations
models 9
sohv/finetuned-qwen2.5-1.5b-finance-correct
Text Generation • 2B • Updated • 8
sohv/nanokimi-mini
Text Generation • Updated • 86 • 1
sohv/finetuned-qwen2.5-1.5b-finance-incorrect
Text Generation • 2B • Updated • 3
sohv/finetuned-qwen2.5-1.5b-auto-incorrect-subtle
Text Generation • 2B • Updated • 3
sohv/finetuned-qwen2.5-1.5b-auto-correct
Text Generation • 2B • Updated • 5
sohv/finetuned-qwen2.5-1.5b-auto-incorrect
Text Generation • 2B • Updated • 6
sohv/finetuned-qwen3-bad-medical-advice
Text Generation • Updated • 9 • 1
sohv/finetuned-qwen3-32B-medical-reasoning
Updated
sohv/qwen1.5-1.8b-insecure
Text Generation • 2B • Updated • 5