Elamur Research⌕
☰
home / authors / Wes Gurnee / cited by

Who cites Wes Gurnee

303 citations of their works from 286 papers of our library (of the 149,439 whose bibliographies we read) · 77 with a page here, the most cited first · ← Wes Gurnee

  1. Do Llamas Work in English? On the Latent Language of Multilingual TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Chris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.2024 · 177 citations
  2. The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False DatasetsarXiv:2310.06824Samuel Marks, Max Tegmark2023 · 169 citations
  3. Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Tianyi Tang, Wenyang Luo, Haoyang Huang, et al.2024 · 156 citations
  4. Emergent Linear Representations in World Models of Self-Supervised Sequence ModelsarXiv:2309.00941Neel Nanda, Andrew Lee, Martin Wattenberg2023 · 116 citations
  5. Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2arXiv:2408.05147Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al.2024 · 115 citations
  6. Mechanistic Interpretability for AI Safety — A ReviewarXiv:2404.14082Leonard Bereska, Efstratios Gavves2024 · 108 citations
  7. Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsarXiv:2309.16042Fred Zhang, Neel Nanda2023 · 97 citations
  8. Do Llamas Work in English? On the Latent Language of Multilingual TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Chris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.2024 · 96 citations
  9. Rethinking Interpretability in the Era of Large Language ModelsarXiv:2402.01761Chandan Singh, Jeevana Priya Inala, Michel Galley, et al.2024 · 87 citations
  10. A Primer on the Inner Workings of Transformer-based Language ModelsarXiv:2405.00208Javier Ferrando, Gabriele Sarti, Arianna Bisazza, et al.2024 · 72 citations
  11. Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse AutoencodersarXiv:2410.20526Zhengfu He, Wentao Shu, Xuyang Ge, et al.2024 · 63 citations
  12. Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in ChinchillaarXiv:2307.09458Tom Lieberum, Matthew Rahtz, Janos Kramar, et al.2023 · 58 citations
  13. Future Lens: Anticipating Subsequent Tokens from a Single Hidden StateConference on Computational Natural Language Learning (CoNLL)Koyena Pal, Jiuding Sun, Andrew Yuan, et al.2023 · 49 citations
  14. Benchmarking Distributional Alignment of Large Language ModelsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Nicole Meister, Carlos Guestrin, Tatsunori Hashimoto2025 · 35 citations
  15. Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Mingyang Wang, Heike Adel, Lukas Lange, et al.2025 · 31 citations
  16. Language Model Alignment in Multilingual Trolley ProblemsarXiv:2407.02273Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, et al.2024 · 23 citations
  17. 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
  18. Unveiling Language-Specific Features in Large Language Models via Sparse AutoencodersAnnual Meeting of the Association for Computational Linguistics (ACL)Boyi Deng, Yu Wan, Baosong Yang, et al.2025 · 18 citations
  19. 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
  20. 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
  21. 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
  22. 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
  23. Explainability and Interpretability of Multilingual Large Language Models: A SurveyConference on Empirical Methods in Natural Language Processing (EMNLP)Lucas Resck, Isabelle Augenstein, Anna Korhonen2025 · 11 citations
  24. 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
  25. Route Sparse Autoencoder to Interpret Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Wei Shi, Sihang Li, Tao Liang, et al.2025 · 11 citations
  26. 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
  27. 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
  28. Paths Not Taken: Understanding and Mending the Multilingual Factual Recall PipelineConference on Empirical Methods in Natural Language Processing (EMNLP)Meng Lu, Ruochen Zhang, Carsten Eickhoff, et al.2025 · 9 citations
  29. Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesAnnual Meeting of the Association for Computational Linguistics (ACL)Bryan R Christ, Zachary Gottesman, Jonathan Kropko, et al.2025 · 7 citations
  30. 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
  31. Qwen-Scope: Turning Sparse Features into Development Tools for Large Language ModelsarXiv:2605.11887Boyi Deng, Xu Wang, Yaoning Wang, et al.2026 · 3 citations
  32. 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
  33. Universal Jailbreak Suffixes Are Strong Attention HijackersTransactions of the Association for Computational Linguistics (TACL)Matan Ben-Tov, Mor Geva, Mahmood Sharif2026 · 3 citations
  34. In-Context Representation HijackingAnnual Meeting of the Association for Computational Linguistics (ACL)Itay Yona, Amir Sarid, Michael Karasik, et al.2026 · 2 citations
  35. Latent Agents: A Post-Training Procedure for Internalized Multi-Agent DebateAnnual Meeting of the Association for Computational Linguistics (ACL)John Seon Keun Yi, Aaron Mueller, Dokyun Lee2026 · 2 citations
  36. Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation FrameworkFindings of the Association for Computational LinguisticsJiaqi Weng, Han Zheng, Hanyu Zhang, et al.2026 · 2 citations
  37. 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
  38. Towards Controllable Natural Language Inference through Lexical Inference TypesarXiv:2308.03581Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, et al.2023 · 2 citations
  39. 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
  40. Constructing Interpretable Features from Compositional Neuron GroupsAnnual Meeting of the Association for Computational Linguistics (ACL)Or David Shafran, Atticus Geiger, Mor Geva2026 · 1 citation
  41. Deciphering Cultural Representations in Large Language Models via Sparse AutoencodersFindings of the Association for Computational LinguisticsChenye Zou, Difan Jiao, Lijie Hu2026 · 1 citation
  42. Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User ProfilesarXiv:2604.21152Irti Haq, Belen Saldias2026 · 1 citation
  43. 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
  44. 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
  45. 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
  46. SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Utsav Maskey, Sumit Yadav, Mark Dras, et al.2026 · 1 citation
  47. Tug-of-war between idioms' figurative and literal interpretations in LLMsConference of the European Chapter of the Association for Computational Linguistics (EACL)Soyoung Oh, Xinting Huang, Mathis Pink, et al.2026 · 1 citation
  48. Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Jiayi Zhang, Shu Yang, Junchao Wu, et al.2026 · 1 citation
  49. Vocab Diet: Reshaping the Vocabulary of LLMs via Vector ArithmeticFindings of the Association for Computational LinguisticsYuval Reif, Guy Kaplan, Roy Schwartz2026 · 1 citation
  50. Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages — A Singlish Case StudyarXiv:2502.12485Isaac Lim, Shaun Khoo, Roy Ka-Wei Lee, et al.2025 · 1 citation
  51. Activation Decomposition and Steering for LLM Backdoor RemediationAnnual Meeting of the Association for Computational Linguistics (ACL)Lingfeng Zhong, Qiongkai Xu, Usman Naseem2026
  52. AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model RepresentationsFindings of the Association for Computational LinguisticsYifei Yao, Hanrong Zhang, Mengnan Du2026
  53. Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard CalibrationarXiv:2608.29378Mohamad Zbib, Ammar Mohanna2026
  54. Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language ModelsFindings of the Association for Computational LinguisticsHanqi Yan, Xiangxiang Cui, Lu Yin, et al.2026
  55. Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language ModelsFindings of the Association for Computational LinguisticsBoyang Zhang, Istemi Ekin Akkus, Ruichuan Chen, et al.2026
  56. Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation MonitoringAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaohao Luo, Ying Wei, Rui Zhao2026
  57. FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Zixuan Weng, Jinghuai Zhang, Kunlin Cai, et al.2026
  58. From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Ling Shi, Xinwei Wu, Xiaohu Zhao, et al.2026
  59. From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?Annual Meeting of the Association for Computational Linguistics (ACL)Aaron Mueller, Andrew Lee, Shruti Joshi, et al.2026
  60. From Narrow Unlearning to Emergent Misalignment in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, et al.2026
  61. Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace AdaptationAnnual Meeting of the Association for Computational Linguistics (ACL)Dianyun Wang, Qingsen Ma, Yuhu Shang, et al.2026
  62. LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Haonan Zhang, Dongxia Wang, Yi Liu, et al.2026
  63. LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation SteeringarXiv:2607.06845Huan Wu, Ali Emami, Muhammad Furquan Hassan, et al.2026
  64. Mapping the Circumplex of Affect: Geometric Analysis of Emotion Representations via Hyperspherical Contrastive LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Yusuke Yamauchi, Akiko Aizawa2026
  65. Mechanistic Insights into Deferred Semantic Drift in LLMsFindings of the Association for Computational LinguisticsJingjie Zeng, Huayang Li, Liang Yang, et al.2026
  66. Model Directions, Not Words: Mechanistic Topic Models Using Sparse AutoencodersTransactions of the Association for Computational Linguistics (TACL)Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar, et al.2026
  67. Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output SpaceWorkshop on Structured Understanding, Retrieval, and Generation in the LLM EraTobias Materzok2026
  68. PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information LeakageWorkshop on Trustworthy NLPKrishna Kanth Nakka, Xue Jiang, Dmitrii Usynin, et al.2026
  69. SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language ModelsFindings of the Association for Computational LinguisticsXinyi Zeng, Xue Yang, Jingyuan Zhang, et al.2026
  70. Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation AblationFindings of the Association for Computational LinguisticsWenpeng Xing, Moran Fang, Guangtai Wang, et al.2026
  71. Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-TuningFindings of the Association for Computational LinguisticsMax Schaffelder, Albert Gatt2026
  72. Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language ModelsFindings of the Association for Computational LinguisticsZhen Yang, Xinyue Zhang, Ping Jian, et al.2026
  73. The Geometry of Refusal: Linear Instability in Safety-Aligned LLMsWorkshop on Trustworthy NLPShivam Ratnakar, Kartikeya Vats2026
  74. Understanding Emergent Misalignment via Feature Superposition GeometryAnnual Meeting of the Association for Computational Linguistics (ACL)Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, et al.2026
  75. When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical PressureAnnual Meeting of the Association for Computational Linguistics (ACL)Boyu Xiao, Xiuqi Tian, Xuwen Song, et al.2026
  76. When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoxiao Ma, Kuofeng Gao, Zeyi Lu, et al.2026
  77. You Only Need One Single Token to Refine Safety AlignmentFindings of the Association for Computational LinguisticsWenqian Yu, Shuo Chen, Zhijiang Li, et al.2026

209 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/wes-gurnee/cited-by/