pith. sign in

arxiv: 2504.10081 · v1 · pith:5UYVCOMKnew · submitted 2025-04-14 · 💻 cs.AI · cs.CL

RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability

classification 💻 cs.AI cs.CL
keywords modelsreasoningdeepseek-r1realsafe-r1safetyapplicationsopen-sourceperformance
0
0 comments X
read the original abstract

Large Reasoning Models (LRMs), such as OpenAI o1 and DeepSeek-R1, have been rapidly progressing and achieving breakthrough performance on complex reasoning tasks such as mathematics and coding. However, the open-source R1 models have raised safety concerns in wide applications, such as the tendency to comply with malicious queries, which greatly impacts the utility of these powerful models in their applications. In this paper, we introduce RealSafe-R1 as safety-aligned versions of DeepSeek-R1 distilled models. To train these models, we construct a dataset of 15k safety-aware reasoning trajectories generated by DeepSeek-R1, under explicit instructions for expected refusal behavior. Both quantitative experiments and qualitative case studies demonstrate the models' improvements, which are shown in their safety guardrails against both harmful queries and jailbreak attacks. Importantly, unlike prior safety alignment efforts that often compromise reasoning performance, our method preserves the models' reasoning capabilities by maintaining the training data within the original distribution of generation. Model weights of RealSafe-R1 are open-source at https://huggingface.co/RealSafe.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Cybersecurity AI (CAI) Dataset

    cs.CR 2026-05 unverdicted novelty 7.0

    CAI Dataset is presented as the largest described corpus of LLM-driven hacker trajectories, with the claim that operator data concentration in frontier-model providers creates a major security risk best addressed by o...

  2. Addressing Over-Refusal in LLMs with Competing Rewards

    cs.LG 2026-06 unverdicted novelty 6.0

    SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.

  3. Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories

    cs.AI 2026-05 unverdicted novelty 6.0

    Self-ReSET is a reinforcement learning approach that lets large reasoning models learn to recover from their own unsafe reasoning trajectories, improving robustness to adversarial jailbreaks while preserving utility.

  4. Reasoning Structure Matters for Safety Alignment of Reasoning Models

    cs.AI 2026-04 unverdicted novelty 6.0

    Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.

  5. ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments

    cs.CL 2025-08 unverdicted novelty 6.0

    ReasoningGuard is an inference-time method that uses attention mechanisms to inject safety aha moments and scaling sampling to defend large reasoning models against jailbreak attacks.

  6. Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing

    cs.LG 2026-05 unverdicted novelty 5.0

    SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.