🧑‍🔬 Who cites Juntao Dai

298 citations of their works from 296 papers of our library (of the 149,439 whose bibliographies we read) · 84 with a page here, the most cited first · ← Juntao Dai

1. A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and TechnologyYupeng Chang, Xu Wang, Jindong Wang, et al.2023 · 3,648 citations
2. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your PhonearXiv:2404.14219Marah Abdin, Jyoti Aneja, Hany Awadalla, et al.2024 · 1,134 citations
3. Baichuan 2: Open Large-scale Language ModelsarXiv:2309.10305Aiyuan Yang, Bin Xiao, Bingning Wang, et al.2023 · 517 citations
4. Phi-4 Technical ReportarXiv:2412.08905Marah Abdin, Jyoti Aneja, Harkirat Behl, et al.2024 · 502 citations
5. Yi: Open Foundation Models by 01.AIarXiv:2403.04652Alex Young, Bei Chen, Chao Li, et al.2024 · 408 citations
6. Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and InferencearXiv:2412.13663Benjamin Warner, Antoine Chaffin, Benjamin Clavié, et al.2024 · 358 citations
7. Aya Model: An Instruction Finetuned Open-Access Multilingual Language ModelarXiv:2402.07827Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong, et al.2024 · 253 citations
8. Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyConference on Neural Information Processing Systems (NeurIPS)Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, et al.2023 · 251 citations
9. TrustLLM: Trustworthiness in Large Language ModelsarXiv:2401.05561Yue Huang, Lichao Sun, Haoran Wang, et al.2024 · 237 citations
10. Safe RLHF: Safe Reinforcement Learning from Human FeedbackarXiv:2310.12773Josef Dai, Xuehai Pan, Ruiyang Sun, et al.2023 · 217 citations
11. Large Language Model UnlearningConference on Neural Information Processing Systems (NeurIPS)Yuanshun Yao, Xiaojun Xu, Yang Liu2023 · 174 citations
12. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
13. WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMsConference on Neural Information Processing Systems (NeurIPS)Seungju Han, Kavel Rao, Allyson Ettinger, et al.2024 · 165 citations
14. Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-ExpertsFindings of the Association for Computational LinguisticsHaoxiang Wang, Wei Xiong, Tengyang Xie, et al.2024 · 153 citations
15. Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAsarXiv:2503.01743Microsoft, Abdelrahman Abouelenin, Atabak Ashfaq, et al.2025 · 152 citations
16. Negative Preference Optimization: From Catastrophic Collapse to Effective UnlearningarXiv:2404.05868Ruiqi Zhang, Licong Lin, Yu Bai, et al.2024 · 126 citations
17. Generative Judge for Evaluating AlignmentarXiv:2310.05470Junlong Li, Shichao Sun, Weizhe Yuan, et al.2023 · 125 citations
18. SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language ModelsFindings of the Association for Computational LinguisticsLijun Li, Bowen Dong, Ruohui Wang, et al.2024 · 119 citations
19. Skywork-Reward: Bag of Tricks for Reward Modeling in LLMsarXiv:2410.18451Chris Yuhao Liu, Liang Zeng, Jiacai Liu, et al.2024 · 112 citations
20. R-Judge: Benchmarking Safety Risk Awareness for LLM AgentsFindings of the Association for Computational LinguisticsTongxin Yuan, Zhiwei He, Lingzhong Dong, et al.2024 · 106 citations
21. Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Wenxuan Wang, Wenxiang Jiao, Jingyuan Huang, et al.2024 · 96 citations
22. Do-Not-Answer: Evaluating Safeguards in LLMsFindings of the Association for Computational LinguisticsYuxia Wang, Haonan Li, Xudong Han, et al.2024 · 93 citations
23. WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language ModelsConference on Neural Information Processing Systems (NeurIPS)Liwei Jiang, Kavel Rao, Seungju Han, et al.2024 · 92 citations
24. PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human PreferenceAnnual Meeting of the Association for Computational Linguistics (ACL)Jiaming Ji, Donghai Hong, Borong Zhang, et al.2025 · 83 citations
25. Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMsarXiv:2308.13387Yuxia Wang, Haonan Li, Xudong Han, et al.2023 · 78 citations
26. OR-Bench: An Over-Refusal Benchmark for Large Language ModelsarXiv:2405.20947Justin Cui, Wei-Lin Chiang, Ion Stoica, et al.2024 · 76 citations
27. VoiceBench: Benchmarking LLM-Based Voice AssistantsTransactions of the Association for Computational Linguistics (TACL)Yiming Chen, Xianghu Yue, Chen Zhang, et al.2026 · 74 citations
28. Black-Box Prompt Optimization: Aligning Large Language Models without Model TrainingAnnual Meeting of the Association for Computational Linguistics (ACL)Jiale Cheng, Xiao Liu, Kehan Zheng, et al.2024 · 72 citations
29. HelpSteer: Multi-attribute Helpfulness Dataset for SteerLMConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Zhilin Wang, Yi Dong, Jiaqi Zeng, et al.2024 · 72 citations
30. Towards Safer Large Language Models through Machine UnlearningFindings of the Association for Computational LinguisticsZheyuan Liu, Guangyao Dou, Zhaoxuan Tan, et al.2024 · 72 citations
31. Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective RewardsAnnual Meeting of the Association for Computational Linguistics (ACL)Haoxiang Wang, Yong Lin, Wei Xiong, et al.2024 · 68 citations
32. AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM GuardrailsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, et al.2025 · 53 citations
33. SOUL: Unlocking the Power of Second-Order Optimization for LLM UnlearningConference on Empirical Methods in Natural Language Processing (EMNLP)Jinghan Jia, Yihua Zhang, Yimeng Zhang, et al.2024 · 46 citations
34. Introducing v0.5 of the AI Safety Benchmark from MLCommonsarXiv:2404.12241Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, et al.2024 · 38 citations
35. Direct Judgement Preference OptimizationConference on Empirical Methods in Natural Language Processing (EMNLP)PeiFeng Wang, Austin Xu, Yilun Zhou, et al.2025 · 35 citations
36. Qwen3Guard Technical ReportarXiv:2510.14276Haiquan Zhao, Chenhan Yuan, Fei Huang, et al.2025 · 33 citations
37. SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model SafetyarXiv:2404.05399Paul Rottger, Fabio Pernisi, Bertie Vidgen, et al.2024 · 33 citations
38. Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language ModelarXiv:2404.04167Xinrun Du; Zhouliang Yu; Songyang Gao; Ding Pan; Yuyang Cheng; Ziyang Ma; Ruibin Yuan; Xingwei Qu; Jiaheng Liu; Tianyu Zheng; Xinchen Luo; Guorui Zhou; Wenhu Chen;, Ge Zhang2024 · 23 citations
39. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal TrainingAnnual Meeting of the Association for Computational Linguistics (ACL)Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, et al.2025 · 19 citations
40. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution ShiftsAnnual Meeting of the Association for Computational Linguistics (ACL)Qibing Ren, Hao Li, Dongrui Liu, et al.2025 · 18 citations
41. MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingAnnual Meeting of the Association for Computational Linguistics (ACL)Weiyang Guo, Jing Li, Wenya Wang, et al.2025 · 14 citations
42. Alignment at Pre-training! Towards Native Alignment for Arabic LLMsConference on Neural Information Processing Systems (NeurIPS)Juhao Liang, Zhenyang Cai, Jianqing Zhu, et al.2024 · 14 citations
43. Safety Alignment via Constrained Knowledge UnlearningAnnual Meeting of the Association for Computational Linguistics (ACL)Zesheng Shi, Yucheng Zhou, Jing Li, et al.2025 · 13 citations
44. Phi-3 Safety Post-Training: Aligning Language Models with a "Break-Fix" CyclearXiv:2407.13833Emman Haider, Daniel Perez-Becker, Thomas Portet, et al.2024 · 13 citations
45. Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User PersonasAnnual Meeting of the Association for Computational Linguistics (ACL)Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, et al.2025 · 12 citations
46. SaRO: Enhancing LLM Safety through Reasoning-based AlignmentarXiv:2504.09420Yutao Mou, Yuxiao Luo, Shikun Zhang, et al.2025 · 11 citations
47. Automated Progressive Red TeamingInternational Conference on Computational Linguistics (COLING)Bojian Jiang, Yi Jing, Tong Wu, et al.2025 · 10 citations
48. WildFeedback: Aligning LLMs With In-situ User Interactions And FeedbackAnnual Meeting of the Association for Computational Linguistics (ACL)Taiwei Shi, Zhuoer Wang, Longqi Yang, et al.2026 · 9 citations
49. Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Weixiang Zhao, Yulin Hu, Yang Deng, et al.2025 · 9 citations
50. Red Teaming Large Reasoning ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Jiawei Chen, Yang Yang, Chao Yu, et al.2026 · 7 citations
51. False Sense of Security: Why Probing-based Malicious Input Detection Fails to GeneralizeFindings of the Association for Computational LinguisticsCheng Wang, Zeming Wei, Qin Liu, et al.2026 · 5 citations
52. FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Masoomali Fatehkia, Enes Altinisik, Husrev Taha Sencar2026 · 5 citations
53. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning DatasetsAnnual Meeting of the Association for Computational Linguistics (ACL)Lei Hsiung, Tianyu Pang, Yung-Chen Tang, et al.2026 · 4 citations
54. SDD: Self-Degraded Defense against Malicious Fine-tuningAnnual Meeting of the Association for Computational Linguistics (ACL)ZiXuan Chen, Weikai Lu, Xin Lin, et al.2025 · 4 citations
55. Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language ModelsarXiv:2412.15265Yingshui Tan, Boren Zheng, Baihui Zheng, et al.2024 · 4 citations
56. CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-TuningAnnual Meeting of the Association for Computational Linguistics (ACL)Biao Yi, Tiansheng Huang, Baolei Zhang, et al.2026 · 3 citations
57. Do Large Language Models Reflect Demographic Pluralism in Safety?Findings of the Association for Computational LinguisticsUsman Naseem, Gautam Siddharth Kashyap, Sushant Kumar Ray, et al.2026 · 3 citations
58. Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Cui Yakun, Peng Qi, Fushuo Huo, et al.2026 · 3 citations
59. SafeMT: Multi-turn Safety for Multimodal Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Han Zhu, Juntao Dai, Jiaming Ji, et al.2026 · 3 citations
60. Activation-Guided Local Editing for Jailbreaking AttacksAnnual Meeting of the Association for Computational Linguistics (ACL)Jiecong Wang, Haoran Li, Hao Peng, et al.2026 · 1 citation
61. AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in AlbanianSIGUL Joint Workshop with ELE, EURALI, and DCLRL: Towards Inclusivity and Equality: Language Resources and Technologies for Under-Resourced and Endangered LanguagesWajdi Zaghouani, Kholoud Khalil Aldous, Isra Fejzullaj2026 · 1 citation
62. Beyond Compromise: Pareto-Lenient Consensus for Efficient Multi-Preference LLM AlignmentFindings of the Association for Computational LinguisticsRenxuan Tan, Rongpeng Li, Zhifeng Zhao, et al.2026 · 1 citation
63. H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMsConference of the European Chapter of the Association for Computational Linguistics (EACL)Selim Furkan Tekin, Fatih Ilhan, Sihao Hu, et al.2026 · 1 citation
64. HARM: Learning Hate-Aware Reward Model for Evaluating Natural Language Explanations of Offensive ContentFindings of the Association for Computational LinguisticsLorenzo Puppi Vecchi, Alceu de Souza Britto Jr, Emerson Cabrera Paraiso, et al.2026 · 1 citation
65. MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrumFindings of the Association for Computational LinguisticsSadat Shahriar, Zheng Qi, Nikolaos Pappas, et al.2026 · 1 citation
66. MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn DialoguesFindings of the Association for Computational LinguisticsZheyuan Liu, Dongwhi Kim, Yixin Wan, et al.2026 · 1 citation
67. SafeAgent: Safeguarding LLM Agents via an Automated Risk SimulatorAnnual Meeting of the Association for Computational Linguistics (ACL)Xueyang Zhou, Weidong Wang, Lin Lu, et al.2026 · 1 citation
68. Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard CalibrationarXiv:2608.29378Mohamad Zbib, Ammar Mohanna2026
69. Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language ModelsarXiv:2609.16006Enes Altinisik, Hamdy Mubarak, Masoomali Fatehkia, et al.2026
70. CachePrune: Teaching LLMs What Not to Follow via KV-Cache EditingAnnual Meeting of the Association for Computational Linguistics (ACL)Rui Wang, Junda Wu, Yu Xia, et al.2026
71. CSULoRA: Closest Safe Update Low-Rank AdaptationInternational Conference on Natural Language Processing and Artificial Intelligence for Cyber SecurityOleksandr Marchenko, Adelaide Danilov, Aria Nourbakhsh, et al.2026
72. DialogGuard: Multi-Agent Psychosocial Safety Evaluation Interface of Sensitive LLM ResponsesAnnual Meeting of the Association for Computational Linguistics (ACL)Han Luo, Guy Laban2026
73. How Does "English (US)" Become the Default? Triangulating Structural Bias Towards American English Across the LLM PipelinearXiv:2604.04204Mir Tafseer Nayeem, Davood Rafiei2026
74. How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response DraftingAnnual Meeting of the Association for Computational Linguistics (ACL)Parker Seegmiller, Joseph Gatto, Sarah E. Greer, et al.2026
75. Jailbreaking Large Language Models with Morality AttacksFindings of the Association for Computational LinguisticsYing Su, Zheng Mingen, Weili Diao, et al.2026
76. OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment StrategyAnnual Meeting of the Association for Computational Linguistics (ACL)Jiayu Tang, Guowei Peng, Qiuhao Xie, et al.2026
77. Preventing Safety Drift in Large Language Models via Coupled Weight and Activation ConstraintsFindings of the Association for Computational LinguisticsSongping Peng, Zhiheng Zhang, Daojian Zeng, et al.2026
78. Safe-FedLLM: Delving into the Safety of Federated Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mingxiang Tao, Yu Tian, Wenxuan Tu, et al.2026
79. Safeguarding LLM Fine-tuning via Push-Pull Distributional AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Haozhong Wang, Zhuo Li, Yibo Yang, et al.2026
80. SAME: Safety-Aware Model Editing Guided by Safety TransformationAnnual Meeting of the Association for Computational Linguistics (ACL)Jiayi Wang, Shipeng Wang, Ji Wu, et al.2026
81. SEA-SafeguardBench: Culturally Grounded Safety Benchmark for Southeast Asian LanguagesFindings of the Association for Computational LinguisticsPanuthep Tasawong, Jian Gang Ngui, Alham Fikri Aji, et al.2026
82. SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance TriggerAnnual Meeting of the Association for Computational Linguistics (ACL)Sunguk Shin, Fangzhao Wu, Byung-Jun Lee, et al.2026
83. Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward ModelingAnnual Meeting of the Association for Computational Linguistics (ACL)Pankayaraj Pathmanathan, Furong Huang2026
84. Thinking Twice Makes Large Language Models Safer and More HelpfulFindings of the Association for Computational LinguisticsYutao Mou, Yuxiao Luo, Shikun Zhang, et al.2026

212 more citing papers of our library have no page here yet.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/juntao-dai/cited-by/