paper-with-me

홈 › Papers

o3-mini vs DeepSeek-R1: Which One is Safer?

2025-01-30 · Aitor Arrieta, Miriam Ugarte, Pablo Valle, José Antonio Parejo, Sergio Segura

The irruption of DeepSeek-R1 constitutes a turning point for the AI industry in general and the LLMs in particular. Its capabilities have demonstrated outstanding performance in several tasks, including creative thinking, code generation, maths and automated program repair, at apparently lower execution cost. However, LLMs must adhere to an important qualitative property, i.e., their alignment with safety and human values. A clear competitor of DeepSeek-R1 is its American counterpart, OpenAI's o3-mini model, which is expected to set high standards in terms of performance, safety and cost. In this technical report, we systematically assess the safety level of both DeepSeek-R1 (70b version) and OpenAI's o3-mini (beta version). To this end, we make use of our recently released automated safety testing tool, named ASTRAL. By leveraging this tool, we automatically and systematically generated and executed 1,260 test inputs on both models. After conducting a semi-automated assessment of the outcomes provided by both LLMs, the results indicate that DeepSeek-R1 produces significantly more unsafe responses (12%) than OpenAI's o3-mini (1.2%).

📄 PDF Abstract BibTeX arXiv:2501.18438

Code (1)

trust4ai/astral 공식 구현

Tasks

Code GenerationProgram RepairQuestion Answering

Methods 이 논문이 사용한 방법론

American 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

SafeRun: Enabling Determinism in LLM Planning for Running

2026-06-08 · Meilin Chen, Zepeng Zhai, Jiaxuan Zhao, Yuan Lu arxiv

Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature. This limitation is especially problematic in running planning, wher…

LLMs in Disease Diagnosis: A Comparative Study of DeepSeek-R1 and O3 Mini Across Chronic Health Conditions

2025-03-13 · Gaurav Kumar Gupta, Pranal Pande

Large Language Models (LLMs) are revolutionizing medical diagnostics by enhancing both disease classification and clinical decision-making. In this study, we evaluate the performance of two LLM- based diagnostic tools, D…

Diagnostic

DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning

2025-02-25 · Pusheng Xu, Yue Wu, Kai Jin, Xiaolan Chen 외

Purpose: To evaluate the accuracy and reasoning ability of DeepSeek-R1 and three other recently released large language models (LLMs) in bilingual complex ophthalmology cases. Methods: A total of 130 multiple-choice ques…

ManagementMultiple-choice

DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search

2024-08-15 · Huajian Xin, Z. Z. Ren, Junxiao Song, Zhihong Shao 외

We introduce DeepSeek-Prover-V1.5, an open-source language model designed for theorem proving in Lean 4, which enhances DeepSeek-Prover-V1 by optimizing both training and inference processes. Pre-trained on DeepSeekMath-…

Automated Theorem ProvingLanguage ModelingLanguage Modelling

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

2024-06-17 · DeepSeek-AI, Qihao Zhu, Daya Guo, Zhihong Shao 외

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, DeepSeek-Coder-V2 is further pre-trained …

16kLanguage ModelingLanguage ModellingMath+2