Elamur Research⌕
☰
home / authors / Matt Fredrikson / cited by / page 2

Who cites Matt Fredrikson

1,295 citations of their works from 1,148 papers of our library (of the 149,439 whose bibliographies we read) · 272 with a page here, the most cited first · page 2 of 3 · 101–200 · ← Matt Fredrikson

1 2 3

  1. Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation EngineeringAnnual Meeting of the Association for Computational Linguistics (ACL)Xinyu Tang, Xiaolei Wang, Zhihao Lv, et al.2025 · 19 citations
  2. 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
  3. 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
  4. 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
  5. Adaptive Tool Use in Large Language Models with Meta-Cognition TriggerAnnual Meeting of the Association for Computational Linguistics (ACL)Wenjun Li, Dexun Li, Kuicai Dong, et al.2025 · 16 citations
  6. Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal CausesConference on Empirical Methods in Natural Language Processing (EMNLP)Mingyang Wang, Lukas Lange, Heike Adel, et al.2025 · 16 citations
  7. Rethinking Reflection in Pre-TrainingarXiv:2504.04022Essential AI: Darsh J Shah, Peter Rushton, Somanshu Singla, et al.2025 · 15 citations
  8. What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient PerspectiveAnnual Meeting of the Association for Computational Linguistics (ACL)Ming Li, Yanhong Li, Tianyi Zhou2025 · 15 citations
  9. 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
  10. 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
  11. Towards Knowledge Checking in Retrieval-augmented Generation: A Representation PerspectiveConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Shenglai Zeng, Jiankun Zhang, Bingheng Li, et al.2025 · 14 citations
  12. Personalized Text Generation with Contrastive Activation SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Jinghao Zhang, Yuting Liu, Wenjie Wang, et al.2025 · 13 citations
  13. 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
  14. Activation Steering Decoding: Mitigating Hallucination in Large Vision-Language Models through Bidirectional Hidden State InterventionAnnual Meeting of the Association for Computational Linguistics (ACL)Jingran Su, Jingfan Chen, Hongxin Li, et al.2025 · 12 citations
  15. from Benign import Toxic: Jailbreaking the Language Model via Adversarial MetaphorsAnnual Meeting of the Association for Computational Linguistics (ACL)Yu Yan, Sheng Sun, Zenghao Duan, et al.2025 · 12 citations
  16. Prompt-Guided Internal States for Hallucination Detection of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Fujie Zhang, Peiqi Yu, Biao Yi, et al.2025 · 12 citations
  17. SAEs Are Good for Steering – If You Select the Right FeaturesConference on Empirical Methods in Natural Language Processing (EMNLP)Dana Arad, Aaron Mueller, Yonatan Belinkov2025 · 12 citations
  18. AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak DefenderConference on Empirical Methods in Natural Language Processing (EMNLP)Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.2025 · 11 citations
  19. Calibrating Verbal Uncertainty as a Linear Feature to Reduce HallucinationsConference on Empirical Methods in Natural Language Processing (EMNLP)Ziwei Ji, Lei Yu, Yeskendir Koishekenov, et al.2025 · 11 citations
  20. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Zihao Li, Xu Wang, Yuzhe Yang, et al.2025 · 11 citations
  21. 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
  22. Yi-Lightning Technical ReportarXiv:2412.01253Alan Wake, Bei Chen, C.X. Lv, et al.2024 · 11 citations
  23. CLEVA: Chinese Language Models EVAluation PlatformarXiv:2308.04813Yanyang Li, Jianqiao Zhao, Duo Zheng, et al.2023 · 11 citations
  24. 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
  25. 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
  26. Automated Progressive Red TeamingInternational Conference on Computational Linguistics (COLING)Bojian Jiang, Yi Jing, Tong Wu, et al.2025 · 10 citations
  27. LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through ProbingAnnual Meeting of the Association for Computational Linguistics (ACL)Dario Di Palma, Alessandro De Bellis, Giovanni Servedio, et al.2025 · 10 citations
  28. Too Late to Train, Too Early To Use? A Study on Necessity and Viability of Low-Resource Bengali LLMsInternational Conference on Computational Linguistics (COLING)Tamzeed Mahfuz, Satak Kumar Dey, Ruwad Naswan, et al.2025 · 10 citations
  29. 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
  30. Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and AlignmentarXiv:2501.13080Melissa Kazemi Rad, Huy Nghiem, Andy Luo, et al.2025 · 9 citations
  31. 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
  32. Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical ExpressionFindings of the Association for Computational LinguisticsJingyu Peng, Maolin Wang, Nan Wang, et al.2026 · 8 citations
  33. Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Zifeng Cheng, Zhonghui Wang, Yuchen Fu, et al.2025 · 8 citations
  34. 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
  35. CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language ModelsFindings of the Association for Computational LinguisticsZhenhong Zhou, Zherui Li, Jie Zhang, et al.2026 · 7 citations
  36. Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement LearningConference on Empirical Methods in Natural Language Processing (EMNLP)Wenbin Hu, Haoran Li, Huihao Jing, et al.2025 · 7 citations
  37. Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy MaximizationInternational Conference on Computational Linguistics (COLING)Zhaohan Zhang, Ziquan Liu, Ioannis Patras2025 · 7 citations
  38. MPO: Multilingual Safety Alignment via Reward Gap OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Weixiang Zhao, Yulin Hu, Yang Deng, et al.2025 · 7 citations
  39. Cutting Through the Noise: Boosting LLM Performance on Math Word ProblemsUjjwala Anantheswaran, Himanshu Gupta, Kevin Scaria, et al.2024 · 7 citations
  40. Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationarXiv:2402.14874Phuc Phan, Hieu Tran, Long Phan2024 · 7 citations
  41. CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving ChallengesFindings of the Association for Computational LinguisticsZihan Wang, Lam Nguyen, Zhengyang Zhao, et al.2026 · 6 citations
  42. Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Wenrui Zhou, Mohamed Hendy, Shu Yang, et al.2026 · 6 citations
  43. From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction TuningAnnual Meeting of the Association for Computational Linguistics (ACL)Jiajun Zhang, Zeyu Cui, Jiaxi Yang, et al.2026 · 6 citations
  44. 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
  45. Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMsFindings of the Association for Computational LinguisticsZara Siddique, Irtaza Khalid, Liam Turner, et al.2026 · 6 citations
  46. Detecting Training Data of Large Language Models via Expectation MaximizationConference of the European Chapter of the Association for Computational Linguistics (EACL)Gyuwan Kim, Yang Li, Evangelia Spiliopoulou, et al.2026 · 5 citations
  47. 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
  48. 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
  49. Towards Context-Robust LLMs: A Gated Representation Fine-tuning ApproachAnnual Meeting of the Association for Computational Linguistics (ACL)Shenglai Zeng, Pengfei He, Kai Guo, et al.2025 · 5 citations
  50. BILLY: Steering Large Language Models via Merging Persona Vectors for Creative GenerationConference of the European Chapter of the Association for Computational Linguistics (EACL)Tsung-Min Pai, Jui-I Wang, Li-Chun Lu, et al.2026 · 4 citations
  51. GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, et al.2026 · 4 citations
  52. HiddenGuard: Fine-Grained Safe Generation with Specialized Representation RouterAnnual Meeting of the Association for Computational Linguistics (ACL)Lingrui Mei, Shenghua Liu, Yiwei Wang, et al.2026 · 4 citations
  53. Spotlight Your Instructions: Instruction-following with Dynamic Attention SteeringConference of the European Chapter of the Association for Computational Linguistics (EACL)Praveen Venkateswaran, Danish Contractor2026 · 4 citations
  54. Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Zirui Song, Qian Jiang, Mingxuan Cui, et al.2026 · 3 citations
  55. 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
  56. Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model SteeringFindings of the Association for Computational LinguisticsHaiyan Zhao, Xuansheng Wu, Fan Yang, et al.2026 · 3 citations
  57. Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?Findings of the Association for Computational LinguisticsYuan Xin, Dingfan Chen, Linyi Yang, et al.2026 · 3 citations
  58. SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web AgentsFindings of the Association for Computational LinguisticsZonghao Ying, Yangguang Shao, Jianle Gan, et al.2026 · 3 citations
  59. Steering Large Language Models for Machine Translation PersonalizationConference of the European Chapter of the Association for Computational Linguistics (EACL)Daniel Scalena, Gabriele Sarti, Arianna Bisazza, et al.2026 · 3 citations
  60. 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
  61. Universal Jailbreak Suffixes Are Strong Attention HijackersTransactions of the Association for Computational Linguistics (TACL)Matan Ben-Tov, Mor Geva, Mahmood Sharif2026 · 3 citations
  62. 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
  63. Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Tiancheng Xing, Jerry Li, Yixuan Du, et al.2026 · 2 citations
  64. Attacker's Noise Can Manipulate Your Audio-based LLM in the Real WorldConference of the European Chapter of the Association for Computational Linguistics (EACL)Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews, et al.2026 · 2 citations
  65. Competence Collapse in Code-Mixed Generation: Spectral Evidence and Mechanistic Recovery via Cross-Lingual Activation SteeringWorkshop on Language Models for Low-Resource LanguagesTanushree Ravindra Pratap Yadav2026 · 2 citations
  66. 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
  67. DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP ProtectionFindings of the Association for Computational LinguisticsYuliang Yan, Haochun Tang, Shuo Yan, et al.2026 · 2 citations
  68. Harnessing Consistency for Robust Test-Time LLM EnsembleFindings of the Association for Computational LinguisticsZhichen Zeng, Qi Yu, Xiao Lin, et al.2026 · 2 citations
  69. In-Context Representation HijackingAnnual Meeting of the Association for Computational Linguistics (ACL)Itay Yona, Amir Sarid, Michael Karasik, et al.2026 · 2 citations
  70. Logit Arithmetic Elicits Long Reasoning Capabilities Without TrainingFindings of the Association for Computational LinguisticsYunxiang Zhang, Muhammad Khalifa, Lechen Zhang, et al.2026 · 2 citations
  71. Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM UnlearningAnnual Meeting of the Association for Computational Linguistics (ACL)Naixin Zhai, Pengyang Shao, Binbin Zheng, et al.2026 · 2 citations
  72. Modeling LLM Unlearning as an Asymmetric Two-Task Learning ProblemAnnual Meeting of the Association for Computational Linguistics (ACL)Zeguan Xiao, Siqing Li, Yong Wang, et al.2026 · 2 citations
  73. Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern AnalysisConference of the European Chapter of the Association for Computational Linguistics (EACL)Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar, et al.2026 · 2 citations
  74. Persona Jailbreaking in Large Language ModelsFindings of the Association for Computational LinguisticsJivnesh Sandhan, Fei Cheng, Tushar Sandhan, et al.2026 · 2 citations
  75. 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
  76. Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA ExpertsAnnual Meeting of the Association for Computational Linguistics (ACL)Christos Ziakas, Nicholas Loo, Nishita Jain, et al.2026 · 2 citations
  77. RedCoder: Automated Multi-Turn Red Teaming for Code LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, et al.2026 · 2 citations
  78. The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMsFindings of the Association for Computational LinguisticsOmar Mahmoud, Ali Khalil, Thommen George Karimpanal, et al.2026 · 2 citations
  79. XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding AssistantsAnnual Meeting of the Association for Computational Linguistics (ACL)Adam Štorek, Mukur Gupta, Noopur Bhatt, et al.2026 · 2 citations
  80. 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
  81. AMALIA: A Fully Open Large Language Model for European PortugueseInternational Conference on Computational Processing of PortugueseAfonso Simplício, Gonçalo Vinagre, Miguel Moura Ramos, et al.2026 · 1 citation
  82. Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration SystemsAnnual Meeting of the Association for Computational Linguistics (ACL)Ziyuan Yang, Wenxuan Ding, Shangbin Feng, et al.2026 · 1 citation
  83. Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience ReplayFindings of the Association for Computational LinguisticsHao Wang, Yanting Wang, Hao Li, et al.2026 · 1 citation
  84. BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream CamouflageFindings of the Association for Computational LinguisticsKalyan Nakka, Nitesh Saxena2026 · 1 citation
  85. Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMsarXiv:2607.03936Kareem Elozeiri, Mervat Abassy, Omar Kallas, et al.2026 · 1 citation
  86. Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy BackdoorsAnnual Meeting of the Association for Computational Linguistics (ACL)Rui Yin, Tianxu Han, Naen Xu, et al.2026 · 1 citation
  87. Enhancing the Safety of Medical Vision-Language Models by Synthetic DemonstrationsConference of the European Chapter of the Association for Computational Linguistics (EACL)Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani2026 · 1 citation
  88. From Attack Surfaces to Actual Operations: A Survey of Modern LLM JailbreaksFindings of the Association for Computational LinguisticsRuikang Zhou, Changsheng Sun, Mark Huasong Meng2026 · 1 citation
  89. From Weights to Activations: Is Steering the Next Frontier of Adaptation?Annual Meeting of the Association for Computational Linguistics (ACL)Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, et al.2026 · 1 citation
  90. Hey, That's My Data! Token-Only Dataset Inference in Large Language ModelsFindings of the Association for Computational LinguisticsChen Xiong, Zihao Wang, Rui Zhu, et al.2026 · 1 citation
  91. IHLC@LT-EDI 2026: Steering Toward Inclusivity - A Representation Engineering for Gender-Neutral RewritingWorkshop on Language Technology for Equality, Diversity, InclusionAkhil Rajeev P, Manoj Balaji Jagadeeshan2026 · 1 citation
  92. In-Distribution Steering: Balancing Control and Coherence in Language Model GenerationLanguage Resources and Evaluation Conference (LREC)Arthur Vogels, Benjamin Wong, Yann Choho, et al.2026 · 1 citation
  93. Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAGAnnual Meeting of the Association for Computational Linguistics (ACL)Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi, et al.2026 · 1 citation
  94. Knowing-but-Doing: Diagnosing and Defending Role-Play-Driven LLMs Jailbreaks via Moral DisengagementFindings of the Association for Computational LinguisticsHaiming Qin, Jianxun Lian, Qimin Zhong, et al.2026 · 1 citation
  95. LogicPoison: Logical Attacks on Graph Retrieval-Augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Yilin Xiao, Jin Chen, Qinggang Zhang, et al.2026 · 1 citation
  96. PARASITE: Conditional System Prompt Poisoning to Hijack LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Viet Pham, Thai Le2026 · 1 citation
  97. Reasoning Up the Instruction Ladder for Controllable Language ModelsFindings of the Association for Computational LinguisticsZishuo Zheng, Vidhisha Balachandran, Chan Young Park, et al.2026 · 1 citation
  98. ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha MomentsAnnual Meeting of the Association for Computational Linguistics (ACL)Yuquan Wang, Mi Zhang, Yining Wang, et al.2026 · 1 citation
  99. Representation Interventions Enable Lifelong Knowledge Memory Control in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Xuyuan Liu, Shengyu Chen, Xinshuai Dong, et al.2026 · 1 citation
  100. The Model's Language Matters: A Comparative Privacy Analysis of LLMsFindings of the Association for Computational LinguisticsAbhishek Kumar Mishra, Antoine Boutet, Lucas Magnana2026 · 1 citation

1 2 3

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/matt-fredrikson/cited-by/page/2/