---
title: "Who cites Wes Gurnee — 286 papers of our library"
description: "286 papers of the Elamur Research library cite the works of Wes Gurnee, found in their bibliographies; the most cited first."
canonical: "https://research.elamur.ai/free/en/authors/wes-gurnee/cited-by/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wes-gurnee/cited-by/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Wes Gurnee](https://md.research.elamur.ai/free/en/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](https://md.research.elamur.ai/free/en/authors/wes-gurnee/)

1. **[Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://md.research.elamur.ai/free/en/papers/wendler-2024-do-llamas-work-english-latent/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 Datasets arXiv:2310.06824**Samuel Marks, Max Tegmark*2023 · 169 citations*](https://md.research.elamur.ai/free/en/papers/marks-2023-geometry-truth-emergent-linear-structure/)
3. **[Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://md.research.elamur.ai/free/en/papers/tang-2024-language-specific-neurons-key-multilingual/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Tianyi Tang, Wenyang Luo, Haoyang Huang, et al.*2024 · 156 citations*
4. [**Emergent Linear Representations in World Models of Self-Supervised Sequence Models arXiv:2309.00941**Neel Nanda, Andrew Lee, Martin Wattenberg*2023 · 116 citations*](https://md.research.elamur.ai/free/en/papers/nanda-2023-emergent-linear-representations-world-models/)
5. [**Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 arXiv:2408.05147**Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, et al.*2024 · 115 citations*](https://md.research.elamur.ai/free/en/papers/lieberum-2024-gemma-scope-open-sparse-autoencoders/)
6. [**Mechanistic Interpretability for AI Safety — A Review arXiv:2404.14082**Leonard Bereska, Efstratios Gavves*2024 · 108 citations*](https://md.research.elamur.ai/free/en/papers/bereska-2024-mechanistic-interpretability-ai-safety-review/)
7. [**Towards Best Practices of Activation Patching in Language Models: Metrics and Methods arXiv:2309.16042**Fred Zhang, Neel Nanda*2023 · 97 citations*](https://md.research.elamur.ai/free/en/papers/zhang-2023-towards-best-practices-activation-patching/)
8. **[Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://md.research.elamur.ai/free/en/papers/wendler-2024-llamas-work-english-latent-language/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Chris Wendler, Veniamin Veselovsky, Giovanni Monea, et al.*2024 · 96 citations*
9. [**Rethinking Interpretability in the Era of Large Language Models arXiv:2402.01761**Chandan Singh, Jeevana Priya Inala, Michel Galley, et al.*2024 · 87 citations*](https://md.research.elamur.ai/free/en/papers/singh-2024-rethinking-interpretability-era-large-language/)
10. [**A Primer on the Inner Workings of Transformer-based Language Models arXiv:2405.00208**Javier Ferrando, Gabriele Sarti, Arianna Bisazza, et al.*2024 · 72 citations*](https://md.research.elamur.ai/free/en/papers/ferrando-2024-primer-inner-workings-transformer-based/)
11. [**Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders arXiv:2410.20526**Zhengfu He, Wentao Shu, Xuyang Ge, et al.*2024 · 63 citations*](https://md.research.elamur.ai/free/en/papers/he-2024-llama-scope-extracting-millions-features/)
12. [**Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla arXiv:2307.09458**Tom Lieberum, Matthew Rahtz, Janos Kramar, et al.*2023 · 58 citations*](https://md.research.elamur.ai/free/en/papers/lieberum-2023-circuit-analysis-interpretability-scale-evidence/)
13. **[Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://md.research.elamur.ai/free/en/papers/pal-2023-future-lens-anticipating-subsequent-tokens/) [Conference on Computational Natural Language Learning (CoNLL)](https://md.research.elamur.ai/free/en/venues/conll/)**Koyena Pal, Jiuding Sun, Andrew Yuan, et al.*2023 · 49 citations*
14. **[Benchmarking Distributional Alignment of Large Language Models](https://md.research.elamur.ai/free/en/papers/meister-2025-benchmarking-distributional-alignment-large-language/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Nicole Meister, Carlos Guestrin, Tatsunori Hashimoto*2025 · 35 citations*
15. **[Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://md.research.elamur.ai/free/en/papers/wang-2025-lost-multilinguality-dissecting-cross-lingual/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Mingyang Wang, Heike Adel, Lukas Lange, et al.*2025 · 31 citations*
16. [**Language Model Alignment in Multilingual Trolley Problems arXiv:2407.02273**Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, et al.*2024 · 23 citations*](https://md.research.elamur.ai/free/en/papers/jin-2024-language-model-alignment-multilingual-trolley/)
17. **[Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering](https://md.research.elamur.ai/free/en/papers/tang-2025-unlocking-general-long-chain-thought/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xinyu Tang, Xiaolei Wang, Zhihao Lv, et al.*2025 · 19 citations*
18. **[Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/deng-2025-unveiling-language-specific-features-large/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 Models](https://md.research.elamur.ai/free/en/papers/ball-2026-understanding-jailbreak-success-study-latent/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Sarah Ball, Frauke Kreuter, Nina Panickssery*2026 · 17 citations*
20. **[What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective](https://md.research.elamur.ai/free/en/papers/li-2025-what-happened-llms-layers-when/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Ming Li, Yanhong Li, Tianyi Zhou*2025 · 15 citations*
21. **[AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender](https://md.research.elamur.ai/free/en/papers/zhao-2025-adasteer-your-aligned-llm-is/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.*2025 · 11 citations*
22. **[Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations](https://md.research.elamur.ai/free/en/papers/ji-2025-calibrating-verbal-uncertainty-as-linear/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Ziwei Ji, Lei Yu, Yeskendir Koishekenov, et al.*2025 · 11 citations*
23. **[Explainability and Interpretability of Multilingual Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/resck-2025-explainability-interpretability-multilingual-large-language/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Lucas Resck, Isabelle Augenstein, Anna Korhonen*2025 · 11 citations*
24. **[Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment](https://md.research.elamur.ai/free/en/papers/li-2025-layer-aware-representation-filtering-purifying/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Hao Li, Lijun Li, Zhenghao Lu, et al.*2025 · 11 citations*
25. **[Route Sparse Autoencoder to Interpret Large Language Models](https://md.research.elamur.ai/free/en/papers/shi-2025-route-sparse-autoencoder-interpret-large/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Wei Shi, Sihang Li, Tao Liang, et al.*2025 · 11 citations*
26. **[Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://md.research.elamur.ai/free/en/papers/hua-2026-rethinking-jailbreak-detection-large-vision/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 Models](https://md.research.elamur.ai/free/en/papers/zhang-2026-locate-steer-improve-practical-survey/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Hengyuan Zhang, Zhihao Zhang, Ercong Nie, et al.*2026 · 9 citations*
28. **[Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline](https://md.research.elamur.ai/free/en/papers/lu-2025-paths-not-taken-understanding-mending/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Meng Lu, Ruochen Zhang, Carsten Eickhoff, et al.*2025 · 9 citations*
29. **[Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes](https://md.research.elamur.ai/free/en/papers/christ-2025-math-neurosurgery-isolating-language-models/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Bryan R Christ, Zachary Gottesman, Jonathan Kropko, et al.*2025 · 7 citations*
30. **[Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs](https://md.research.elamur.ai/free/en/papers/siddique-2026-shifting-perspectives-steering-vectors-robust/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zara Siddique, Irtaza Khalid, Liam Turner, et al.*2026 · 6 citations*
31. [**Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models arXiv:2605.11887**Boyi Deng, Xu Wang, Yaoning Wang, et al.*2026 · 3 citations*](https://md.research.elamur.ai/free/en/papers/deng-2026-qwen-scope-turning-sparse/)
32. **[Steering Large Language Models for Machine Translation Personalization](https://md.research.elamur.ai/free/en/papers/scalena-2026-steering-large-language-models-machine/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Daniel Scalena, Gabriele Sarti, Arianna Bisazza, et al.*2026 · 3 citations*
33. **[Universal Jailbreak Suffixes Are Strong Attention Hijackers](https://md.research.elamur.ai/free/en/papers/tov-2026-universal-jailbreak-suffixes-are-strong/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Matan Ben-Tov, Mor Geva, Mahmood Sharif*2026 · 3 citations*
34. **[In-Context Representation Hijacking](https://md.research.elamur.ai/free/en/papers/yona-2026-context-representation-hijacking/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Itay Yona, Amir Sarid, Michael Karasik, et al.*2026 · 2 citations*
35. **[Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate](https://md.research.elamur.ai/free/en/papers/yi-2026-latent-agents-post-training-procedure/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**John Seon Keun Yi, Aaron Mueller, Dokyun Lee*2026 · 2 citations*
36. **[Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework](https://md.research.elamur.ai/free/en/papers/weng-2026-safe-sail-fine-grained-safety/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jiaqi Weng, Han Zheng, Hanyu Zhang, et al.*2026 · 2 citations*
37. **[The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs](https://md.research.elamur.ai/free/en/papers/mahmoud-2026-unintended-trade-off-ai-alignment/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Omar Mahmoud, Ali Khalil, Thommen George Karimpanal, et al.*2026 · 2 citations*
38. [**Towards Controllable Natural Language Inference through Lexical Inference Types arXiv:2308.03581**Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, et al.*2023 · 2 citations*](https://md.research.elamur.ai/free/en/papers/zhang-2023-towards-controllable-natural-language-inference/)
39. **[Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors](https://md.research.elamur.ai/free/en/papers/yin-2026-compiling-activation-steering-into-weights/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Rui Yin, Tianxu Han, Naen Xu, et al.*2026 · 1 citation*
40. **[Constructing Interpretable Features from Compositional Neuron Groups](https://md.research.elamur.ai/free/en/papers/shafran-2026-constructing-interpretable-features-compositional-neuron/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Or David Shafran, Atticus Geiger, Mor Geva*2026 · 1 citation*
41. **[Deciphering Cultural Representations in Large Language Models via Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/zou-2026-deciphering-cultural-representations-large-language/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Chenye Zou, Difan Jiao, Lijie Hu*2026 · 1 citation*
42. [**Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles arXiv:2604.21152**Irti Haq, Belen Saldias*2026 · 1 citation*](https://md.research.elamur.ai/free/en/papers/haq-2026-dialect-vs-demographics-quantifying-llm/)
43. **[From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://md.research.elamur.ai/free/en/papers/ostermann-2026-weights-activations-is-steering-next/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Simon Ostermann, Daniil Gurgurov, Tanja Baeumel, et al.*2026 · 1 citation*
44. **[In-Distribution Steering: Balancing Control and Coherence in Language Model Generation](https://md.research.elamur.ai/free/en/papers/vogels-2026-distribution-steering-balancing-control-coherence/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Arthur Vogels, Benjamin Wong, Yann Choho, et al.*2026 · 1 citation*
45. **[Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs](https://md.research.elamur.ai/free/en/papers/liu-2026-representation-interventions-enable-lifelong-knowledge/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xuyuan Liu, Shengyu Chen, Xinshuai Dong, et al.*2026 · 1 citation*
46. **[SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering](https://md.research.elamur.ai/free/en/papers/maskey-2026-safeconstellations-mitigating-over-refusals-llms/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Utsav Maskey, Sumit Yadav, Mark Dras, et al.*2026 · 1 citation*
47. **[Tug-of-war between idioms' figurative and literal interpretations in LLMs](https://md.research.elamur.ai/free/en/papers/oh-2026-tug-war-between-idioms-figurative/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Soyoung Oh, Xinting Huang, Mathis Pink, et al.*2026 · 1 citation*
48. **[Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models](https://md.research.elamur.ai/free/en/papers/zhang-2026-understanding-mitigating-political-stance-cross/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jiayi Zhang, Shu Yang, Junchao Wu, et al.*2026 · 1 citation*
49. **[Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic](https://md.research.elamur.ai/free/en/papers/reif-2026-vocab-diet-reshaping-vocabulary-llms/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yuval Reif, Guy Kaplan, Roy Schwartz*2026 · 1 citation*
50. [**Safe at the Margins: A General Approach to Safety Alignment in Low-Resource English Languages — A Singlish Case Study arXiv:2502.12485**Isaac Lim, Shaun Khoo, Roy Ka-Wei Lee, et al.*2025 · 1 citation*](https://md.research.elamur.ai/free/en/papers/lim-2025-safe-margins-general-approach-safety/)
51. **[Activation Decomposition and Steering for LLM Backdoor Remediation](https://md.research.elamur.ai/free/en/papers/zhong-2026-activation-decomposition-steering-llm-backdoor/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Lingfeng Zhong, Qiongkai Xu, Usman Naseem*2026*
52. **[AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations](https://md.research.elamur.ai/free/en/papers/yao-2026-adaptivek-complexity-driven-sparse-autoencoders/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yifei Yao, Hanrong Zhang, Mengnan Du*2026*
53. [**Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration arXiv:2608.29378**Mohamad Zbib, Ammar Mohanna*2026*](https://md.research.elamur.ai/free/en/papers/zbib-2026-arabic-safety-alignment-selective-refusal/)
54. **[Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models](https://md.research.elamur.ai/free/en/papers/yan-2026-beyond-cross-modal-alignment-measuring/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Hanqi Yan, Xiangxiang Cui, Lu Yin, et al.*2026*
55. **[Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language Models](https://md.research.elamur.ai/free/en/papers/zhang-2026-defeating-cerberus-privacy-leakage-mitigation/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Boyang Zhang, Istemi Ekin Akkus, Ruichuan Chen, et al.*2026*
56. **[Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring](https://md.research.elamur.ai/free/en/papers/luo-2026-detecting-what-queries-seek-steering/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaohao Luo, Ying Wei, Rui Zhao*2026*
57. **[FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models](https://md.research.elamur.ai/free/en/papers/weng-2026-finesteer-unified-framework-fine-grained/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 Models](https://md.research.elamur.ai/free/en/papers/shi-2026-insight-action-novel-framework-interpretability/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Ling Shi, Xinwei Wu, Xiaohu Zhao, et al.*2026*
59. **[From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?](https://md.research.elamur.ai/free/en/papers/mueller-2026-isolation-entanglement-when-do-interpretability/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Aaron Mueller, Andrew Lee, Shruti Joshi, et al.*2026*
60. **[From Narrow Unlearning to Emergent Misalignment in LLMs](https://md.research.elamur.ai/free/en/papers/mushtaq-2026-narrow-unlearning-emergent-misalignment-llms/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, et al.*2026*
61. **[Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation](https://md.research.elamur.ai/free/en/papers/wang-2026-interpretable-safety-alignment-sae-constructed/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Dianyun Wang, Qingsen Ma, Yuhu Shang, et al.*2026*
62. **[LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment](https://md.research.elamur.ai/free/en/papers/zhang-2026-llm-va-resolving-jailbreak-overrefusal/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Haonan Zhang, Dongxia Wang, Yi Liu, et al.*2026*
63. [**LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering arXiv:2607.06845**Huan Wu, Ali Emami, Muhammad Furquan Hassan, et al.*2026*](https://md.research.elamur.ai/free/en/papers/wu-2026-llms-silently-correct-african-american/)
64. **[Mapping the Circumplex of Affect: Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning](https://md.research.elamur.ai/free/en/papers/yamauchi-2026-mapping-circumplex-affect-geometric-analysis/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yusuke Yamauchi, Akiko Aizawa*2026*
65. **[Mechanistic Insights into Deferred Semantic Drift in LLMs](https://md.research.elamur.ai/free/en/papers/zeng-2026-mechanistic-insights-into-deferred-semantic/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jingjie Zeng, Huayang Li, Liang Yang, et al.*2026*
66. **[Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/zheng-2026-model-directions-not-words-mechanistic/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar, et al.*2026*
67. **[Output-Space Search: Targeting LLM Generations in a Frozen Encoder-Defined Output Space](https://md.research.elamur.ai/free/en/papers/materzok-2026-output-space-search-targeting-llm/) [Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era](https://md.research.elamur.ai/free/en/venues/surgellm/)**Tobias Materzok*2026*
68. **[PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage](https://md.research.elamur.ai/free/en/papers/nakka-2026-pii-jailbreaking-llms-activation-steering/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin, et al.*2026*
69. **[SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/zeng-2026-safesteer-decoding-level-defense-mechanism/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Xinyi Zeng, Xue Yang, Jingyuan Zhang, et al.*2026*
70. **[Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation](https://md.research.elamur.ai/free/en/papers/xing-2026-silencing-guardrails-inference-time-jailbreaking/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Wenpeng Xing, Moran Fang, Guangtai Wang, et al.*2026*
71. **[Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning](https://md.research.elamur.ai/free/en/papers/schaffelder-2026-synthetic-eggs-many-baskets-impact/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Max Schaffelder, Albert Gatt*2026*
72. **[Temporal Token Matters: Investigating and Interpreting the Consistency of Temporal Ordering in Large Language Models](https://md.research.elamur.ai/free/en/papers/yang-2026-temporal-token-matters-investigating-interpreting/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zhen Yang, Xinyue Zhang, Ping Jian, et al.*2026*
73. **[The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs](https://md.research.elamur.ai/free/en/papers/ratnakar-2026-geometry-refusal-linear-instability-safety/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Shivam Ratnakar, Kartikeya Vats*2026*
74. **[Understanding Emergent Misalignment via Feature Superposition Geometry](https://md.research.elamur.ai/free/en/papers/minegishi-2026-understanding-emergent-misalignment-feature-superposition/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, et al.*2026*
75. **[When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure](https://md.research.elamur.ai/free/en/papers/xiao-2026-when-correct-beliefs-collapse-epistemic/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/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 Models](https://md.research.elamur.ai/free/en/papers/ma-2026-when-efficiency-meets-safety-benchmark/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaoxiao Ma, Kuofeng Gao, Zeyi Lu, et al.*2026*
77. **[You Only Need One Single Token to Refine Safety Alignment](https://md.research.elamur.ai/free/en/papers/yu-2026-you-only-need-one-single/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Wenqian Yu, Shuo Chen, Zhijiang Li, et al.*2026*

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

- [← back to](https://md.research.elamur.ai/free/en/authors/wes-gurnee/) — Wes Gurnee