Skip to content
AI News HubLIVE
Original source2 min read

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

Summary

Large language models (LLMs) face a persistent challenge in balancing safety, helpfulness, and trustworthiness. Traditional refusal-oriented alignment strategies mitigate harmful content but often fail to serve legitimate user needs. Oyster-II proposes a reinforcement learning (RL)-based constructive safety alignment framework, employing a Zero-RL paradigm combined with a multi-stage RL strategy. It addresses two critical limitations of Oyster-I's Supervised Fine-Tuning (SFT) scheme: insufficient safety generalization to out-of-distribution scenarios and safety chain-of-thought (CoT) over-generalization. Evaluated on extensive benchmarks, Oyster-II comprehensively surpasses Qwen3-14B and Oyster-I on safety dimensions, achieving cross-scale performance comparable to Qwen3-Max and Qwen3.5-3…

SourcearXiv AIAuthor: Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu, Zipeng Ye, Defeng Li, Jiayu Shen, Jialing Tao, Hui Xue
Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 3 Jul 2026]

Title:Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models

View a PDF of the paper titled Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models, by Jiyang Guan and 8 other authors

View PDF HTML (experimental)

Abstract:Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge. Conventional refusal-oriented alignment strategies mitigate harmful content generation but systematically fail to serve legitimate user needs, often withholding information that could safely and constructively address the underlying intent of sensitive queries. Building upon the constructive safety paradigm pioneered by Oyster-I, which moves beyond blanket refusal toward thoughtful, response-oriented safety alignment, we identify two critical limitations of its Supervised Fine-Tuning (SFT)-based scheme: insufficient safety generalization to out-of-distribution scenarios and a phenomenon we term safety chain-of-thought (CoT) over-generalization, wherein safety-oriented reasoning patterns are excessively applied to benign queries, degrading helpfulness and user experience. To address these limitations, we propose Oyster-II, a reinforcement learning (RL)-based constructive safety alignment framework that adopts a Zero-RL paradigm combined with a multi-stage reinforcement learning this http URL across extensive benchmarks, Oyster-II comprehensively surpasses both Qwen3-14B and its predecessor Oyster-I on safety dimensions, achieving cross-scale performance comparable to Qwen3-Max and Qwen3.5-397B.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.02914 [cs.AI]

(or arXiv:2607.02914v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.02914

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jiyang Guan [view email] [v1] Fri, 3 Jul 2026 03:19:39 UTC (955 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models, by Jiyang Guan and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-07

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Oyster-II improves upon Oyster-I by using reinforcement learning instead of supervised fine-tuning for safety alignment.
  • It introduces a Zero-RL paradigm combined with multi-stage reinforcement learning.
  • It overcomes safety chain-of-thought over-generalization, where safety reasoning is excessively applied to benign queries.
  • Oyster-II outperforms existing models in safety and matches larger models in cross-scale performance.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models