Paper
LLMs & Texto
A Verifiable Search Is Not a Learnable Chain-of-Thought
Training models on chain-of-thought demonstrations fails for tasks requiring backtracking search because the forward derivation cannot be faithfully imitated, demonstrating a funda…
Hugging Face · Daily Papers
·Harsh Patel
·
·▲ 2 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Harsh Patel
- 2 upvotes da comunidade
- Temas: chain-of-thought, fine-tuning, distillation, LoRA, Nemotron, backtracking search
Resumo
Resumo original (em inglês), extraído do paper:
Training models on chain-of-thought demonstrations fails for tasks requiring backtracking search because the forward derivation cannot be faithfully imitated, demonstrating a fundamental limitation in learning search procedures through demonstration.
