arxiv Moonshot AI (arXiv) · 609d ago

DeepSeek-R1 incentivizes LLM reasoning via reinforcement learning

from English

DeepSeek has released DeepSeek-R1, a large language model trained using pure reinforcement learning to enhance its reasoning capabilities without relying on human-annotated demonstrations.

The model exhibits emergent advanced reasoning patterns, including self-reflection, verification, and dynamic strategy adaptation. It achieves superior performance on verifiable tasks in mathematics, coding competitions, and STEM fields compared to models trained via conventional supervised learning. Additionally, the reasoning patterns developed by this large-scale model can be used to guide and improve smaller models.

This approach demonstrates that reinforcement learning alone can effectively incentivize complex reasoning behaviors in LLMs, reducing dependency on extensive human-labeled data.

Importance 2/3 Moonshot AI (arXiv) DeepSeek Research paper Training methods

Read original

arxiv Moonshot AI (arXiv) · 609d ago · 32 views

DeepSeek releases R1 reasoning models via reinforcement learning

DeepSeek introduces its first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1, which achieve performance comparable to OpenAI-o1-1217 on reasoning tasks. DeepSeek-R1-Zero is trained via large-scale reinforcement learning without supervised fine-tuning, while DeepSeek-R1 uses a multi-stage pipeline with cold-start data to improve readability.

arxiv Moonshot AI (arXiv) · 635d ago · 24 views

DeepSeek-V3: 671B MoE model with auxiliary-loss-free balancing

DeepSeek-AI presents DeepSeek-V3, a strong Mixture-of-Experts language model with 671B total parameters and 37B activated per token. The model adopts Multi-head Latent Attention and DeepSeekMoE architectures to achieve efficient inference and cost-effective training.

arxiv arXiv cs.LG · 1d ago · 10 views

Fathom-Vaidya improves medical reasoning with rubric-based rewards

The authors introduce Fathom-Vaidya, a 30B parameter model that uses synthetic data and rubric-based reinforcement learning to enhance diagnostic and clinical healthcare reasoning. The training framework first applies rule-guided RL to MedBullets-derived questions for diagnosis, then utilizes 5.3k synthetic multi-turn scenarios with multi-dimensional rubrics for interactive clinical tasks.

arxiv arXiv cs.AI · 1d ago · 12 views

Fathom-Vaidya improves medical reasoning with rubric-based rewards

The authors introduce Fathom-Vaidya, a 30B parameter model that uses synthetic data and rubric-based reinforcement learning to enhance both diagnostic and clinical healthcare reasoning. The training framework first targets diagnostic accuracy using MedBullets-derived questions and then addresses multi-turn clinical interactions through 5.3k generated scenarios with multi-dimensional rubrics.

arxiv arXiv cs.CL · 1d ago · 12 views

Fathom-Vaidya improves medical reasoning with rubric-based rewards

The authors introduce Fathom-Vaidya, a 30B parameter model that uses synthetic data and rubric-based reinforcement learning to enhance both diagnostic and clinical healthcare reasoning.