التفاصيل البيبلوغرافية
| العنوان: |
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought |
| المؤلفون: |
Xiang, Violet, Snell, Charlie, Gandhi, Kanishk, Albalak, Alon, Singh, Anikait, Blagden, Chase, Phung, Duy, Rafailov, Rafael, Lile, Nathan, Mahan, Dakota, Castricato, Louis, Franken, Jan-Philipp, Haber, Nick, Finn, Chelsea |
| سنة النشر: |
2025 |
| المجموعة: |
Computer Science |
| مصطلحات موضوعية: |
Computer Science - Artificial Intelligence, Computer Science - Computation and Language |
| الوصف: |
We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT. We present empirical evidence from state-of-the-art models exhibiting behaviors consistent with in-context search, and explore methods for producing Meta-CoT via process supervision, synthetic data generation, and search algorithms. Finally, we outline a concrete pipeline for training a model to produce Meta-CoTs, incorporating instruction tuning with linearized search traces and reinforcement learning post-training. Finally, we discuss open research questions, including scaling laws, verifier roles, and the potential for discovering novel reasoning algorithms. This work provides a theoretical and practical roadmap to enable Meta-CoT in LLMs, paving the way for more powerful and human-like reasoning in artificial intelligence. |
| نوع الوثيقة: |
Working Paper |
| URL الوصول: |
http://arxiv.org/abs/2501.04682 |
| رقم الانضمام: |
edsarx.2501.04682 |
| قاعدة البيانات: |
arXiv |