Pith. sign in

REVIEW 7 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.10081 v1 pith:5UYVCOMK submitted 2025-04-14 cs.AI cs.CL

classification cs.AIcs.CL
keywords modelsreasoningdeepseek-r1realsafe-r1safetyapplicationsopen-sourceperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. UniNDM: A Unified Noise-driven Detection and Mitigation Framework Against Sexual Content in Text-to-Image Generation

    cs.CV 2026-07 conditional novelty 7.0 of 10

    UniNDM detects sexual intent from early-stage diffusion noise and mitigates it via LLM-generated negative prompts and initial-noise optimization, across U-Net and DiT models.

  2. Does More Inference-Time Compute Really Help Robustness?

    cs.AI 2025-07 conditional novelty 6.0 of 10

    With exposed reasoning chains, increasing inference-time compute consistently decreases measured robustness across 12 open-source reasoning models, while hidden chains show improvements.

  3. Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space

    cs.CR 2025-05 conditional novelty 6.0 of 10

    A component-based, genetically optimized jailbreak framework reports over 90% success on Claude-3.5 and strong cross-model transferability.

  4. Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

    cs.AI 2025-05 conditional novelty 6.0 of 10

    A new benchmark shows that top reasoning models identify all relevant risks in under 40% of cases even when their final answers look safe.

  5. R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge

    cs.AI 2025-08 conditional novelty 5.0 of 10

    Adding an explicit 'is this harmful?' step to the reasoning chain, trained on just 1,000 examples, substantially reduces harmful responses from reasoning models while roughly preserving benchmark reasoning performance.

  6. A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models

    cs.CL 2025-09 conditional novelty 4.0 of 10

    A structured literature survey concluding that reasoning capabilities do not automatically make LLMs more trustworthy and can introduce new vulnerabilities in safety, robustness, and privacy.

  7. A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents

    cs.AI 2025-06 conditional novelty 4.0 of 10

    The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.

Pith tools