DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

dc.contributor.authorDeepSeek-AI
dc.date.accessioned2025-06-02T13:25:53Z
dc.date.available2025-06-02T13:25:53Z
dc.date.issued2025-01-22
dc.descriptionRL 기반 학습을 통해 LLM의 추론 능력을 강화하는 DeepSeek-R1 모델을 제안하며 다양한 벤치마크에서 실험적 우수성을 입증합니다. ©2025 DeepSeek-AI This work was authored by the DeepSeek-AI research team with contributions from 41 individuals. Due to the extensive author list, only the organizational author is listed in the metadata. The full list of authors is provided below for reference: https://arxiv.org/abs/2501.12948 :
dc.description.abstractWe introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrates remarkable reasoning capabilities. Through RL, DeepSeek-R1-Zero naturally emerges with numerous powerful and intriguing reasoning behaviors. However, it encounters challenges such as poor readability, and language mixing. To address these issues and further enhance reasoning performance, we introduce DeepSeek-R1, which incorporates multi-stage training and cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1-1217 on reasoning tasks. To support the research community, we open-source DeepSeek-R1-Zero, DeepSeek-R1, and six dense models (1.5B, 7B, 8B, 14B, 32B, 70B) distilled from DeepSeek-R1 based on Qwen and Llama.
dc.description.sponsorshipDeepSeek-AI
dc.identifier.urihttps://arxiv.org/abs/2501.12948
dc.identifier.urihttp://data.inu.ac.kr/handle/123456789/1958
dc.language.isoen_US
dc.subjectDeepSeek-R1
dc.subjectRLHF
dc.subjectReasoning
dc.subjectLLM
dc.subjectReinforcement Learning
dc.titleDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2501.12948v1.pdf
Size:
1.25 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
97 B
Format:
Item-specific license agreed to upon submission
Description: