Built on

Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)
Original
2023
Earlier work this paper cites.
Cai, W., Jiang, J., Wang, F., Tang, J., Kim, S., Huang, J.: A survey on mixture of experts. arXiv preprint arXiv:2407.06204 (2024)
Original
2024
Earlier work this paper cites.
Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., et al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)
Original
2024
Earlier work this paper cites.
Liu, J., Tang, P., Wang, W., Ren, Y., Hou, X., Heng, P.A., Guo, M., Li, C.: A survey on inference optimization techniques for mixture of experts models. arXiv preprint arXiv:2412.14219 (2024)
Original
2024
Earlier work this paper cites.
MAA: American invitational mathematics examination - aime. In: American Invitational Mathematics Examination - AIME 2024 (February 2024), https://maa.org/math-competitions/american-invitational-mathematics-examination-aime
2024
Earlier work this paper cites.
Mazeika, M., Phan, L., Yin, X., Zou, A., Wang, Z., Mu, N., Sakhaee, E., Li, N., Basart, S., Li, B., et al.: Harmbench: A standardized evaluation framework for automated red teaming and robust refusal. arXiv preprint arXiv:2402.04249 (2024)
Original
2024
Earlier work this paper cites.

Similar

OpenAI: Learning to reason with llms (2024), https://openai.com/index/learning-to-reason-with-llms/
2024
Cited alongside, same era.
Team, Q.: Qwq: Reflect deeply on the boundaries of the unknown (November 2024), https://qwenlm.github.io/blog/qwq-32b-preview/
2024
Cited alongside, same era.
Xu, D., Chen, W., Peng, W., Zhang, C., Xu, T., Zhao, X., Wu, X., Zheng, Y., Wang, Y., Chen, E.: Large language models for generative information extraction: A survey. Frontiers of Computer Science 18
2024
Cited alongside, same era.
Zhang, W., Lei, X., Liu, Z., An, M., Yang, B., Zhao, K., Wang, K., Lian, S.: Chisafetybench: A chinese hierarchical safety benchmark for large language models. arXiv preprint arXiv:2406.10311 (2024)
Original
2024
Cited alongside, same era.
adversa.ai: Introducing safety aligned deepseek r1 model by enkrypt ai (2025), https://adversa.ai/blog/deepseek-jailbreak/

Then

Arrieta, A., Ugarte, M., Valle, P., Parejo, J.A., Segura, S.: o3-mini vs deepseek-r1: Which one is safer? arXiv preprint arXiv:2501.18438 (2025)
Original
2025
Closest in time.
chatterbox: Gen ai reasoning model comparison & ai safety results (2025), https://chatterbox.co/blog/gen-ai-reasoning-model-comparison-ai-safety-results/
2025
Closest in time.
cisco: Evaluating security risk in deepseek and other frontier reasoning models (2025), https://blogs.cisco.com/security/evaluating-security-risk-in-deepseek-and-other-frontier-reasoning-models
2025
Closest in time.
Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al.: Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)
Original
2025
Closest in time.
Patil, A.: Advancing reasoning in large language models: Promising methods and approaches. arXiv preprint arXiv:2502.03671 (2025)

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2025

Safety Evaluation of DeepSeek Models in Chinese Contexts

Zhang, Wenjing, Lei, Xuejiao, Liu, Zhaoxiang et al.

Understand

Recently, the DeepSeek series of models, leveraging their exceptional reasoning capabilities and open-source strategy, is reshaping the global AI landscape.

Despite these advantages, they exhibit significant safety deficiencies.
Research conducted by Robust Intelligence, a subsidiary of Cisco, in collaboration with the University of Pennsylvania, revealed that DeepSeek-R1 has a 100\% attack success rate when processing harmful prompts.
Additionally, multiple safety companies and research institutions have confirmed critical safety vulnerabilities in this model.

Built on

Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)
Original
2023
Earlier work this paper cites.
Cai, W., Jiang, J., Wang, F., Tang, J., Kim, S., Huang, J.: A survey on mixture of experts. arXiv preprint arXiv:2407.06204 (2024)
Original
2024
Earlier work this paper cites.
Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., Ruan, C., et al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)
Original
2024
Earlier work this paper cites.
Liu, J., Tang, P., Wang, W., Ren, Y., Hou, X., Heng, P.A., Guo, M., Li, C.: A survey on inference optimization techniques for mixture of experts models. arXiv preprint arXiv:2412.14219 (2024)
Original
2024
Earlier work this paper cites.
MAA: American invitational mathematics examination - aime. In: American Invitational Mathematics Examination - AIME 2024 (February 2024), https://maa.org/math-competitions/american-invitational-mathematics-examination-aime
2024
Earlier work this paper cites.
Mazeika, M., Phan, L., Yin, X., Zou, A., Wang, Z., Mu, N., Sakhaee, E., Li, N., Basart, S., Li, B., et al.: Harmbench: A standardized evaluation framework for automated red teaming and robust refusal. arXiv preprint arXiv:2402.04249 (2024)
Original
2024
Earlier work this paper cites.

Similar

OpenAI: Learning to reason with llms (2024), https://openai.com/index/learning-to-reason-with-llms/
2024
Cited alongside, same era.
Team, Q.: Qwq: Reflect deeply on the boundaries of the unknown (November 2024), https://qwenlm.github.io/blog/qwq-32b-preview/
2024
Cited alongside, same era.
Xu, D., Chen, W., Peng, W., Zhang, C., Xu, T., Zhao, X., Wu, X., Zheng, Y., Wang, Y., Chen, E.: Large language models for generative information extraction: A survey. Frontiers of Computer Science 18
2024
Cited alongside, same era.
Zhang, W., Lei, X., Liu, Z., An, M., Yang, B., Zhao, K., Wang, K., Lian, S.: Chisafetybench: A chinese hierarchical safety benchmark for large language models. arXiv preprint arXiv:2406.10311 (2024)
Original
2024
Cited alongside, same era.
adversa.ai: Introducing safety aligned deepseek r1 model by enkrypt ai (2025), https://adversa.ai/blog/deepseek-jailbreak/

Then

Arrieta, A., Ugarte, M., Valle, P., Parejo, J.A., Segura, S.: o3-mini vs deepseek-r1: Which one is safer? arXiv preprint arXiv:2501.18438 (2025)
Original
2025
Closest in time.
chatterbox: Gen ai reasoning model comparison & ai safety results (2025), https://chatterbox.co/blog/gen-ai-reasoning-model-comparison-ai-safety-results/
2025
Closest in time.
cisco: Evaluating security risk in deepseek and other frontier reasoning models (2025), https://blogs.cisco.com/security/evaluating-security-risk-in-deepseek-and-other-frontier-reasoning-models
2025
Closest in time.
Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al.: Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)
Original
2025
Closest in time.
Patil, A.: Advancing reasoning in large language models: Promising methods and approaches. arXiv preprint arXiv:2502.03671 (2025)

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

2025

Cited alongside, same era.

AI, E.: Deepseek jailbreak’s (2025), https://www.enkryptai.com/blog/introducing-safety-aligned-deepseek-r1-model-by-enkrypt-ai

2025

Cited alongside, same era.

Introducing meta llama 3: The most capable openly available llm to date, https://ai.meta.com/blog/meta-llama-3/

Cited in the paper.

Original

2025

Closest in time.