Elamur Research⌕
☰
home / authors / Xiangyu Qi / cited by

Who cites Xiangyu Qi

905 citations of their works from 772 papers of our library (of the 149,439 whose bibliographies we read) · 215 with a page here, the most cited first · page 1 of 3 · 1–100 · ← Xiangyu Qi

1 2 3

  1. A Survey of Large Language ModelsFrontiers of Computer ScienceWayne Xin Zhao, Kun Zhou, Junyi Li, et al.2023 · 2,875 citations
  2. Jailbreaking Black Box Large Language Models in Twenty QueriesarXiv:2310.08419Patrick Chao, Alexander Robey, Edgar Dobriban, et al.2023 · 553 citations
  3. Security and Privacy Challenges of Large Language Models: A SurveyACM Computing SurveysBadhan Chandra Das, M. Hadi Amini, Yanzhao Wu2024 · 424 citations
  4. A Survey on Large Language Models for Code GenerationACM Transactions on Software Engineering and MethodologyJuyong Jiang, Fan Wang, Jiasi Shen, et al.2024 · 367 citations
  5. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!arXiv:2310.03693Xiangyu Qi, Yi Zeng, Tinghao Xie, et al.2023 · 355 citations
  6. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalarXiv:2402.04249Mantas Mazeika, Long Phan, Xuwang Yin, et al.2024 · 330 citations
  7. TrustLLM: Trustworthiness in Large Language ModelsarXiv:2401.05561Yue Huang, Lichao Sun, Haoran Wang, et al.2024 · 237 citations
  8. Baseline Defenses for Adversarial Attacks Against Aligned Language ModelsarXiv:2309.00614Neel Jain, Avi Schwarzschild, Yuxin Wen, et al.2023 · 236 citations
  9. Steering Language Models With Activation EngineeringarXiv:2308.10248Alexander Matt Turner, Lisa Thiergart, Gavin Leech, et al.2023 · 233 citations
  10. Combating Misinformation in the Age of LLMs: Opportunities and ChallengesAI MagazineCanyu Chen, Kai Shu2023 · 214 citations
  11. How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Yi Zeng, Hongpeng Lin, Jingwen Zhang, et al.2024 · 202 citations
  12. Refusal in Language Models Is Mediated by a Single DirectionarXiv:2406.11717Andy Arditi, Oscar Obeso, Aaquib Syed, et al.2024 · 196 citations
  13. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation MethodsarXiv:2412.05579Haitao Li, Qian Dong, Junjie Chen, et al.2024 · 195 citations
  14. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and EfficiencyarXiv:2508.18265Weiyun Wang, Zhangwei Gao, Lixin Gu, et al.2025 · 179 citations
  15. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
  16. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and TrustworthinessACM Transactions on Intelligent Systems and TechnologyFali Wang, Zhiwei Zhang, Xianren Zhang, et al.2024 · 159 citations
  17. DeepInception: Hypnotize Large Language Model to Be JailbreakerarXiv:2311.03191Xuan Li, Zhanke Zhou, Jianing Zhu, et al.2023 · 141 citations
  18. Olmo 3arXiv:2512.13961Team Olmo: Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, et al.2025 · 130 citations
  19. Jailbreak and Guard Aligned Language Models with Only Few In-Context DemonstrationsarXiv:2310.06387Zeming Wei, Yifei Wang, Ang Li, et al.2023 · 130 citations
  20. SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware DecodingAnnual Meeting of the Association for Computational Linguistics (ACL)Zhangchen Xu, Fengqing Jiang, Luyao Niu, et al.2024 · 127 citations
  21. The WMDP Benchmark: Measuring and Reducing Malicious Use With UnlearningarXiv:2403.03218Nathaniel Li, Alexander Pan, Anjali Gopal, et al.2024 · 127 citations
  22. Large Language Model Alignment: A SurveyarXiv:2309.15025Tianhao Shen, Renren Jin, Yufei Huang, et al.2023 · 124 citations
  23. OpenThoughts: Data Recipes for Reasoning ModelsarXiv:2506.04178Etash Guha, Ryan Marten, Sedrick Keh, et al.2025 · 122 citations
  24. 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
  25. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive AttacksarXiv:2404.02151Maksym Andriushchenko, Francesco Croce, Nicolas Flammarion2024 · 118 citations
  26. Safety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citations
  27. 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
  28. AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsarXiv:2310.15140Sicheng Zhu, Ruiyi Zhang, Bang An, et al.2023 · 90 citations
  29. Foundational Challenges in Assuring Alignment and Safety of Large Language ModelsarXiv:2404.09932Usman Anwar, Abulhair Saparov, Javier Rando, et al.2024 · 87 citations
  30. SORRY-Bench: Systematically Evaluating Large Language Model Safety RefusalarXiv:2406.14598Tinghao Xie, Xiangyu Qi, Yi Zeng, et al.2024 · 87 citations
  31. 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
  32. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMsarXiv:2402.11753Fengqing Jiang, Zhangchen Xu, Luyao Niu, et al.2024 · 83 citations
  33. Survey of Vulnerabilities in Large Language Models Revealed by Adversarial AttacksarXiv:2310.10844Erfan Shayegani, Md Abdullah Al Mamun, Yu Fu, et al.2023 · 83 citations
  34. Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language ModelsarXiv:2307.14539Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh2023 · 81 citations
  35. PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language ModelsarXiv:2402.07867Wei Zou, Runpeng Geng, Binghui Wang, et al.2024 · 80 citations
  36. OR-Bench: An Over-Refusal Benchmark for Large Language ModelsarXiv:2405.20947Justin Cui, Wei-Lin Chiang, Ion Stoica, et al.2024 · 76 citations
  37. Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsarXiv:2402.05162Boyi Wei, Kaixuan Huang, Yangsibo Huang, et al.2024 · 66 citations
  38. JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak AttacksarXiv:2404.03027Weidi Luo, Siyuan Ma, Xiaogeng Liu, et al.2024 · 66 citations
  39. A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and ToxicityarXiv:2401.01967Andrew Lee, Xiaoyan Bai, Itamar Pres, et al.2024 · 64 citations
  40. Self-Distillation Bridges Distribution Gap in Language Model Fine-TuningAnnual Meeting of the Association for Computational Linguistics (ACL)Zhaorui Yang, Tianyu Pang, Haozhe Feng, et al.2024 · 63 citations
  41. Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language ModelsarXiv:2402.02207Yongshuo Zong, Ondrej Bohdal, Tingyang Yu, et al.2024 · 60 citations
  42. Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task ArithmeticAnnual Meeting of the Association for Computational Linguistics (ACL)Rishabh Bhardwaj, Duc Anh Do, Soujanya Poria2024 · 59 citations
  43. The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce HarmConference on Empirical Methods in Natural Language Processing (EMNLP)Aakanksha, Arash Ahmadian, Beyza Ermis, et al.2024 · 49 citations
  44. SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language ModelsarXiv:2311.08370Bertie Vidgen, Nino Scherrer, Hannah Rose Kirk, et al.2023 · 42 citations
  45. Introducing v0.5 of the AI Safety Benchmark from MLCommonsarXiv:2404.12241Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed, et al.2024 · 38 citations
  46. 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
  47. The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1International Joint Conference on Natural Language Processing (IJCNLP)Kaiwen Zhou, Chengzhi Liu, Xuandong Zhao, et al.2025 · 30 citations
  48. Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red TeamingarXiv:2501.18837Mrinank Sharma, Meg Tong, Jesse Mu, et al.2025 · 29 citations
  49. Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language ModelsFindings of the Association for Computational LinguisticsYeeun Kim, Youngrok Choi, Eunkyung Choi, et al.2024 · 24 citations
  50. Language Models in Dialogue: Conversational Maxims for Human-AI InteractionsFindings of the Association for Computational LinguisticsErik Miehling, Manish Nagireddy, Prasanna Sattigeri, et al.2024 · 23 citations
  51. Scaling Latent Reasoning via Looped Language ModelsarXiv:2510.25741Rui-Jie Zhu, Zixuan Wang, Kai Hua, et al.2025 · 22 citations
  52. Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from JailbreakingConference on Empirical Methods in Natural Language Processing (EMNLP)Junda Zhu, Lingyong Yan, Shuaiqiang Wang, et al.2025 · 21 citations
  53. Jailbreak Large Vision-Language Models Through Multi-Modal LinkageAnnual Meeting of the Association for Computational Linguistics (ACL)Yu Wang, Xiaofei Zhou, Yichen Wang, et al.2025 · 20 citations
  54. 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
  55. 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
  56. Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Sarah Ball, Frauke Kreuter, Nina Panickssery2026 · 17 citations
  57. Revisiting Jailbreaking for Large Language Models: A Representation Engineering PerspectiveInternational Conference on Computational Linguistics (COLING)Tianlong Li, Zhenghua Wang, Wenhao Liu, et al.2025 · 17 citations
  58. Jailbreaking LLMs with Arabic Transliteration and ArabiziConference on Empirical Methods in Natural Language Processing (EMNLP)Mansour Al Ghanim, Saleh Almohaimeed, Mengxin Zheng, et al.2024 · 16 citations
  59. HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden StatesAnnual Meeting of the Association for Computational Linguistics (ACL)Yilei Jiang, Xinyan Gao, Tianshuo Peng, et al.2025 · 15 citations
  60. When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex CiphersarXiv:2402.10601Divij Handa, Zehua Zhang, Amir Saeidi, et al.2024 · 15 citations
  61. 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
  62. Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to ArtifactsAnnual Meeting of the Association for Computational Linguistics (ACL)Hongyu Chen, Seraphina Goldfarb-Tarrant2025 · 13 citations
  63. 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
  64. Distilling LLM Agent into Small Models with Retrieval and Code ToolsarXiv:2505.17612Minki Kang, Jongwon Jeong, Seanie Lee, et al.2025 · 11 citations
  65. Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Hao Li, Lijun Li, Zhenghao Lu, et al.2025 · 11 citations
  66. Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable RewardAnnual Meeting of the Association for Computational Linguistics (ACL)Weiyang Guo, Zesheng Shi, Zeen Zhu, et al.2026 · 10 citations
  67. Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive ScoringAnnual Meeting of the Association for Computational Linguistics (ACL)Peichun Hua, Hao Li, Shanghao Shi, et al.2026 · 10 citations
  68. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language ModelsFindings of the Association for Computational LinguisticsHengyuan Zhang, Zhihao Zhang, Ercong Nie, et al.2026 · 9 citations
  69. MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMsarXiv:2603.07539Abdessalam Bouchekif; Shahd Gaben; Samer Rashwani; Somaya Eltanbouly; Mutaz Al-Khatib; Heba Sbahi; Mohammed Ghaly;, Emad Mohamed2026 · 9 citations
  70. 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
  71. SafeKey: Amplifying Aha-Moment Insights for Safety ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Kaiwen Zhou, Xuandong Zhao, Jayanth Srinivasa, et al.2025 · 9 citations
  72. VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Bingrui Sima, Linhua Cong, Wenxuan Wang, et al.2025 · 9 citations
  73. The Dark Side of Function Calling: Pathways to Jailbreaking Large Language ModelsInternational Conference on Computational Linguistics (COLING)Zihui Wu, Haichang Gao, Jianping He, et al.2025 · 8 citations
  74. GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiangdong Hu, Yangyang Jiang, Qin Hu, et al.2026 · 6 citations
  75. OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QAarXiv:2510.06371Firoj Alam, Ali Ezzat Shahroor, Md. Arid Hasan, et al.2025 · 6 citations
  76. Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context InjectionConference on Empirical Methods in Natural Language Processing (EMNLP)Miao Ziqi, Yi Ding, Lijun Li, et al.2025 · 6 citations
  77. MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and BenchmarkarXiv:2602.01714Mouath Abu-Daoud, Leen Kharouf, Omar El Hajj, et al.2026 · 5 citations
  78. MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal InteractionarXiv:2604.27393Junbo Cui, Bokai Xu, Chongyi Wang, et al.2026 · 5 citations
  79. LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-DisjointAnnual Meeting of the Association for Computational Linguistics (ACL)Qianli Ma, Dongrui Liu, Qian Chen, et al.2025 · 5 citations
  80. UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and GranularitiesAnnual Meeting of the Association for Computational Linguistics (ACL)Woongyeong Yeo, Kangsan Kim, Soyeong Jeong, et al.2026 · 4 citations
  81. 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
  82. Kimi-Dev: Agentless Training as Skill Prior for SWE-AgentsarXiv:2509.23045Zonghan Yang, Shengjie Wang, Kelin Fu, et al.2025 · 4 citations
  83. 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
  84. 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
  85. QIAS 2026: Overview of the Shared Task on Islamic Inheritance ReasoningWorkshop on Open-Source Arabic Corpora and Processing Tools with Shared TasksAbdessalam Bouchekif, Somaya Eltanbouly, Shahd Gaben, et al.2026 · 3 citations
  86. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language ModelsarXiv:2605.11887Boyi Deng, Xu Wang, Yaoning Wang, et al.2026 · 3 citations
  87. 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
  88. TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process RewardsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiqiao Xiong, Ouxiang Li, Zhuo Liu, et al.2026 · 3 citations
  89. Universal Jailbreak Suffixes Are Strong Attention HijackersTransactions of the Association for Computational Linguistics (TACL)Matan Ben-Tov, Mor Geva, Mahmood Sharif2026 · 3 citations
  90. Unraveling LLM Jailbreaks Through Safety Knowledge NeuronsConference of the European Chapter of the Association for Computational Linguistics (EACL)Chongwen Zhao, Yutong Ke, Kaizhu Huang2026 · 3 citations
  91. DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal GenerationarXiv:2510.14949Yu Zhou, Sohyun An, Haikang Deng, et al.2025 · 3 citations
  92. Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-MakingarXiv:2602.06570Chengfeng Dou, Fan Yang, Fei Li, et al.2026 · 2 citations
  93. Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge TracingFindings of the Association for Computational LinguisticsJun Seo, Sangwon Ryu, Heejin Do, et al.2026 · 2 citations
  94. Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMsConference of the European Chapter of the Association for Computational Linguistics (EACL)Chi Zhang, Wenxuan Ding, Jiale Liu, et al.2026 · 2 citations
  95. Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Hanwen Shen, Ting Ying, Jiajie Lu, et al.2026 · 2 citations
  96. PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health EthicsFindings of the Association for Computational LinguisticsYaling Shen, Stephanie Fong, Yiwen Jiang, et al.2026 · 2 citations
  97. RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, et al.2026 · 2 citations
  98. WASIL: In-the-Wild Arabic Spoken Interactions with LLMsarXiv:2605.16364Zien Sheikh Ali, Hamdy Mubarak, Soon-Gyo Jung, et al.2026 · 2 citations
  99. 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
  100. Adversarial Decoding: Generating Readable Documents for Adversarial ObjectivesFindings of the Association for Computational LinguisticsCollin Zhang, Tingwei Zhang, Vitaly Shmatikov2026 · 1 citation

1 2 3

↑ back to top

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