The following papers were recommended by the Semantic Scholar API
\n- \n
- DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search (2024) \n
- ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement (2024) \n
- CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks (2024) \n
- VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment (2024) \n
- Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths (2024) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
Abstract
A novel approach using online learning Flows with Direct Preference Optimization enhances the quality of reasoning traces for LLMs in mathematical reasoning tasks.
Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning Flows. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and updating models in real-time. We directly compare the quality of reasoning traces generated by our method with those produced through direct model inference, demonstrating the effectiveness of our approach in improving LLM performance in mathematical reasoning tasks.
Community
Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning Flows. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and updating models in real-time. We directly compare the quality of reasoning traces generated by our method with those produced through direct model inference, demonstrating the effectiveness of our approach in improving LLM performance in mathematical reasoning tasks.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search (2024)
- ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement (2024)
- CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks (2024)
- VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment (2024)
- Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper