paper-with-me

홈 › Papers

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

2025-01-28 · Manojkumar Parmar, Yuvaraj Govindarajulu

Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a critical challenge, particularly in advanced models like DeepSeek-R1. This paper examines the limitations of Reinforcement Learning (RL) as the primary approach for reducing harmful outputs in DeepSeek-R1 and compares it with Supervised Fine-Tuning (SFT). While RL improves reasoning capabilities, it faces challenges such as reward hacking, generalization failures, language mixing, and high computational costs. We propose hybrid training approaches combining RL and SFT to achieve robust harmlessness reduction. Usage recommendations and future directions for deploying DeepSeek-R1 responsibly are also presented.

📄 PDF Abstract BibTeX arXiv:2501.17030

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

Safety Evaluation and Enhancement of DeepSeek Models in Chinese Contexts

2025-03-18 · Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu, Limin Han 외

DeepSeek-R1, renowned for its exceptional reasoning capabilities and open-source strategy, is significantly influencing the global artificial intelligence landscape. However, it exhibits notable safety shortcomings. Rece…

Output Length Effect on DeepSeek-R1's Safety in Forced Thinking

2025-03-02 · Xuying Li, Zhuo Li, Yuji Kosuga, Victor Bian

Large Language Models (LLMs) have demonstrated strong reasoning capabilities, but their safety under adversarial conditions remains a challenge. This study examines the impact of output length on the robustness of DeepSe…

Modular Control Architecture for Safe Marine Navigation: Reinforcement Learning and Predictive Safety Filters

2023-12-04 · Aksel Vaaler, Svein Jostein Husa, Daniel Menges, Thomas Nakken Larsen 외

Many autonomous systems face safety challenges, requiring robust closed-loop control to handle physical limitations and safety constraints. Real-world systems, like autonomous ships, encounter nonlinear dynamics and envi…

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

2025-01-22 · DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang 외

We 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 st…

Mathematical ReasoningMulti-task Language UnderstandingQuestion AnsweringReinforcement Learning (RL)

Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops

2026-01-19 · Zainab Ghafoor, Md Shafiqul Islam, Koushik Howlader, Md Rasel Khondokar 외 arxiv

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinemen…