paper-with-me

Papers

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models

2025-09-02 · Ranjie Duan, Jiexi Liu, Xiaojun Jia, Shiji Zhao, Ruoxi Cheng, Fengxiang Wang, Cheng Wei, Yong Xie, Chang Liu, Defeng Li, Yinpeng Dong, Yichi Zhang, Yuefeng Chen, Chongwen Wang, Xingjun Ma, Xingxing Wei, Yang Liu, Hang Su, Jun Zhu, Xinfeng Li, Yitong Sun, Jie Zhang, Jinzhao Hu, Sha Xu, Wenchao Yang, Yitong Yang, Xingyao Zhang, Yingshui Tan, Jialing Tao, Hui Xue arxiv

Large language models (LLMs) typically deploy safety mechanisms to prevent harmful content generation. Most current approaches focus narrowly on risks posed by malicious actors, often framing risks as adversarial events and relying on defensive refusals. However, in real-world settings, risks also come from non-malicious users seeking help while under psychological distress (e.g., self-harm intentions). In such cases, the model's response can strongly influence the user's next actions. Simple refusals may lead them to repeat, escalate, or move to unsafe platforms, creating worse outcomes. We introduce Constructive Safety Alignment (CSA), a human-centric paradigm that protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results. Implemented in Oyster-I (Oy1), CSA combines game-theoretic anticipation of user reactions, fine-grained risk boundary discovery, and interpretable reasoning control, turning safety into a trust-building process. Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities. On our Constructive Benchmark, it shows strong constructive engagement, close to GPT-5, and unmatched robustness on the Strata-Sword jailbreak dataset, nearing GPT-o1 levels. By shifting from refusal-first to guidance-first safety, CSA redefines the model-user relationship, aiming for systems that are not just safe, but meaningfully helpful. We release Oy1, code, and the benchmark to support responsible, user-centered AI.

📄 PDF Abstract BibTeX arXiv:2509.01909

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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

2026-07-03 · Jiyang Guan, Yong Xie, Jun Chen, Jiexi Liu 외 arxiv

Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge. Conventional re…

Reinforcement Learning

ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

2026-08-31 · Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim, YoungBin Kim arxiv

Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-tim…

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law

2025-06-05 · John Mavi, Diana Teodora Găitan, Sergio Coronado

Large Language Models (LLMs) are widely used across sectors, yet their alignment with International Humanitarian Law (IHL) is not well understood. This study evaluates eight leading LLMs on their ability to refuse prompt…

Humanitarian

Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment

2026-03-12 · Zhiyu Xue, Zimo Qi, Guangliang Liu, Bocheng Chen 외 arxiv

Safety alignment aims to ensure that large language models (LLMs) refuse harmful requests by post-training on harmful queries paired with refusal answers. Although safety alignment is widely adopted in industry, the over…

DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair

2026-06-02 · Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang 외 arxiv

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (De…