| Unveiling the implicit toxicity in large language models J Wen, P Ke, H Sun, Z Zhang, C Li, J Bai, M Huang arXiv preprint arXiv:2311.17391, 2023 | 59 | 2023 |
| Robustness testing of language understanding in task-oriented dialog J Liu, R Takanobu, J Wen, D Wan, H Li, W Nie, C Li, W Peng, M Huang arXiv preprint arXiv:2012.15262, 2020 | 53 | 2020 |
| Augesc: Dialogue augmentation with large language models for emotional support conversation C Zheng, S Sabour, J Wen, Z Zhang, M Huang arXiv preprint arXiv:2202.13047, 2022 | 50 | 2022 |
| A chatbot for mental health support: exploring the impact of Emohaa on reducing mental distress in China S Sabour, W Zhang, X Xiao, Y Zhang, Y Zheng, J Wen, J Zhao, M Huang Frontiers in digital health 5, 1133987, 2023 | 49 | 2023 |
| Eva2. 0: Investigating open-domain chinese dialogue systems with large-scale pre-training Y Gu, J Wen, H Sun, Y Song, P Ke, C Zheng, Z Zhang, J Yao, L Liu, X Zhu, ... Machine Intelligence Research 20 (2), 207-219, 2023 | 45 | 2023 |
| Ethicist: Targeted training data extraction through loss smoothed soft prompting and calibrated confidence estimation Z Zhang, J Wen, M Huang arXiv preprint arXiv:2307.04401, 2023 | 29 | 2023 |
| Persona-guided planning for controlling the protagonist's persona in story generation Z Zhang, J Wen, J Guan, M Huang arXiv preprint arXiv:2204.10703, 2022 | 23 | 2022 |
| Augesc: Large-scale data augmentation for emotional support conversation with pre-trained language models C Zheng, S Sabour, J Wen, M Huang arXiv preprint arXiv:2202.13047, 2022 | 17 | 2022 |
| Autocad: Automatically generating counterfactuals for mitigating shortcut learning J Wen, Y Zhu, J Zhang, J Zhou, M Huang arXiv preprint arXiv:2211.16202, 2022 | 13 | 2022 |
| Language models learn to mislead humans via rlhf J Wen, R Zhong, A Khan, E Perez, J Steinhardt, M Huang, SR Bowman, ... arXiv preprint arXiv:2409.12822, 2024 | 12 | 2024 |
| Learning task decomposition to assist humans in competitive programming J Wen, R Zhong, P Ke, Z Shao, H Wang, M Huang Proceedings of the 62nd Annual Meeting of the Association for Computational …, 2024 | 4 | 2024 |
| Adaptivebackdoor: Backdoored language model agents that detect human overseers H Wang, R Zhong, J Wen, J Steinhardt ICML 2024 Next Generation of AI Safety Workshop, 2024 | 3 | 2024 |
| Robustness testing of language understanding in dialog systems J Liu, R Takanobu, J Wen, D Wan, W Nie, H Li, C Li, W Peng, M Huang CoRR, abs, 2012 | 3 | 2012 |
| Codeplan: Unlocking reasoning potential in large langauge models by scaling code-form planning J Wen, J Guan, H Wang, W Wu, M Huang CoRR, 2024 | 2 | 2024 |
| Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats J Wen, V Hebbar, C Larson, A Bhatt, A Radhakrishnan, M Sharma, ... arXiv preprint arXiv:2411.17693, 2024 | | 2024 |
| Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning J Wen, J Guan, H Wang, W Wu, M Huang arXiv preprint arXiv:2409.12452, 2024 | | 2024 |
| Re3Dial: Retrieve, Reorganize and Rescale Conversations for Long-Turn Open-Domain Dialogue Pre-training J Wen, H Zhou, J Guan, J Zhou, M Huang Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | | 2023 |
| SmartBackdoor: Malicious Language Model Agents that Avoid Being Caught H Wang, R Zhong, J Wen, J Steinhardt | | |
Pei KeTsinghua UniversityEmail yang diverifikasi di mail.tsinghua.edu.cn