Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection
Paper • 2505.17558 • Published • 15
Shubham Gandhi
shubhamrgandhi
·
AI & ML interests
AI4Code
Recent Activity
updated a model 22 days ago
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think published a model 22 days ago
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think updated a model 23 days ago
shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_cleanOrganizations
upvoted a paper 11 months ago