978 citations · 1.4k across the 17 of their papers we have counts for
17 papers
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang +195
General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large language models (LLMs) and chain-of-tho…
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
DeepSeek-AI, Aixin Liu, Bei Feng +154
We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which…
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
DeepSeek-AI, Qihao Zhu, Daya Guo +37
We present DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks. Specifically, D…
Learning Task Decomposition to Assist Humans in Competitive Programming
Jiaxin Wen, Ruiqi Zhong, Pei Ke +3
When using language models (LMs) to solve complex problems, humans might struggle to understand the LM-generated solutions and repair the flawed ones. To assist humans in repairing…
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Zhihong Shao, Peiyi Wang, Qihao Zhu +8
Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature. In this paper, we introduce DeepSeekMath 7B, which continues pre-…
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
DeepSeek-AI, :, Xiao Bi +85
The rapid development of open-source large language models (LLMs) has been truly remarkable. However, the scaling law described in previous literature presents varying conclusions,…
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Peiyi Wang, Lei Li, Zhihong Shao +6
In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solution…
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Zhibin Gou, Zhihong Shao, Yeyun Gong +5
Large language models have made significant progress in various language tasks, yet they still struggle with complex mathematics. In this paper, we propose ToRA a series of Tool-in…
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
Zhihong Shao, Yeyun Gong, Yelong Shen +3
Large language models are powerful text processors and reasoners, but are still subject to limitations including outdated knowledge and hallucinations, which necessitates connectin…
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Zhibin Gou, Zhihong Shao, Yeyun Gong +4
Recent developments in large language models (LLMs) have been impressive. However, these models sometimes show inconsistencies and problematic behavior, such as hallucinating facts…
Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
Zhihong Shao, Yeyun Gong, Yelong Shen +3
Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the q…
Chaining Simultaneous Thoughts for Numerical Reasoning
Zhihong Shao, Fei Huang, Minlie Huang
Given that rich information is hidden behind ubiquitous numbers in text, numerical reasoning over text should be an essential skill of AI systems. To derive precise equations to so…
Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Framework
Zhihong Shao, Minlie Huang
Open-domain questions are likely to be open-ended and ambiguous, leading to multiple valid answers. Existing approaches typically adopt the rerank-then-read framework, where a read…
A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering
Zhihong Shao, Lifeng Shang, Qun Liu +1
Weakly supervised question answering usually has only the final answers as supervision signals while the correct solutions to derive the answers are not provided. This setting give…
AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text
Zhihong Shao, Zitao Liu, Jiyong Zhang +2
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some cha…
CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
Fei Huang, Dazhen Wan, Zhihong Shao +5
In text generation evaluation, many practical issues, such as inconsistent experimental settings and metric implementations, are often ignored but lead to unfair evaluation and unt…
Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Zhihong Shao, Minlie Huang, Jiangtao Wen +2
Existing neural methods for data-to-text generation are still struggling to produce long and diverse texts: they are insufficient to model input data dynamically during generation,…