Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
J Li
jiazhengli
AI & ML interests
LLM Post-train, AI for Education
Recent Activity
upvoted a paper 10 days ago
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability submitted a paper 10 days ago
Self-Distillation with Verbal Regularization upvoted a paper 10 days ago
Self-Distillation with Verbal RegularizationOrganizations
models 19
jiazhengli/Qwen2.5-3B-Instruct-Critic
3B • Updated • 8
jiazhengli/Qwen2.5-3B-Instruct-Reasoner
3B • Updated • 3
jiazhengli/Llama-2-7b-esnli-lora
Question Answering • 7B • Updated • 5
jiazhengli/deberta-large-asap_6
Text Classification • Updated • 13
jiazhengli/deberta-large-asap_5
Text Classification • Updated • 11
jiazhengli/deberta-large-asap_2
Text Classification • Updated • 10
jiazhengli/deberta-large-asap_1
Text Classification • Updated • 11
jiazhengli/Qwen2.5-7B-RoleMRC-sft
8B • Updated • 18
jiazhengli/Qwen2.5-7B-RoleMRC-dpo
8B • Updated • 21
jiazhengli/Llama-3.1-8B-RoleMRC-sft
8B • Updated • 35