@misc{ouyang2026densesteersteeringsmalllanguage,title={DenseSteer: Steering Small Language Models towards Dense Math Reasoning},author={Ouyang, Yang and Lin, Shuhang and Kim, Jung-Eun},year={2026},archiveprefix={arXiv},primaryclass={cs.AI},journal={Forty-Third International Conference on Machine Learning},url={https://arxiv.org/abs/2605.29247},}
2025
ICML
Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
@article{dou2025plan,title={Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning},author={Dou, Zhihao and Zhao, Qinjian and Wan, Zhongwei and Zhang, Dinggen and Wang, Weida and Raiyan, Towsif and Chen, Benteng and Pan, Qingtao and Ouyang, Yang and Gao, Zhiqiang and others},journal={arXiv preprint arXiv:2510.01833},year={2025},}
NAACL
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Meijun Gao, Tianlong Chen, and Kaixiong Zhou
In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Apr 2025
As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks, which exploit vulnerabilities to elicit unintended or harmful outputs, threaten LLMs safety significantly. In this paper, we introduce Layer-AdvPatcher, a novel methodology designed to defend against jailbreak attacks by utilizing an unlearning strategy to patch specific layers within LLMs through self-augmented datasets. Our insight is that certain layer(s), tend to produce affirmative tokens when faced with harmful prompts. By identifying these layers and adversarially exposing them to generate more harmful data, one can understand their inherent and diverse vulnerabilities to attacks. With these exposures, we then “unlearn” these issues, reducing the impact of affirmative tokens and hence minimizing jailbreak risks while keeping the model’s responses to safe queries intact.We conduct extensive experiments on two models, four benchmark datasets, and multiple state-of-the-art jailbreak attacks to demonstrate the efficacy of our approach. Results indicate that our framework reduces the harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to recent defense methods. Our code is publicly available at: https://github.com/oyy2000/LayerAdvPatcher
@inproceedings{ouyang-etal-2025-layer,title={Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense},author={Ouyang, Yang and Gu, Hengrui and Lin, Shuhang and Hua, Wenyue and Peng, Jie and Kailkhura, Bhavya and Gao, Meijun and Chen, Tianlong and Zhou, Kaixiong},editor={Chiruzzo, Luis and Ritter, Alan and Wang, Lu},booktitle={Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},month=apr,year={2025},address={Albuquerque, New Mexico},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2025.naacl-long.623/},doi={10.18653/v1/2025.naacl-long.623},pages={12541--12554},isbn={979-8-89176-189-6},}
ICLR
Min-k%++: Improved baseline for detecting pre-training data from large language models
Jingyang Zhang*, Jingwei Sun*, Eric Yeats, Yang Ouyang, Martin Kuo, Jianyi Zhang, Hao Frank Yang, and Hai Li
The Thirteenth International Conference on Learning Representations, 2025
@article{zhang2024min,title={Min-k\%++: Improved baseline for detecting pre-training data from large language models},author={Zhang, Jingyang and Sun, Jingwei and Yeats, Eric and Ouyang, Yang and Kuo, Martin and Zhang, Jianyi and Yang, Hao Frank and Li, Hai},journal={The Thirteenth International Conference on Learning Representations},year={2025},}