Who cites «A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity»
- Refusal in Language Models Is Mediated by a Single DirectionarXiv:2406.11717Andy Arditi, Oscar Obeso, Aaquib Syed, et al.2024 · 196 citations
- Mechanistic Interpretability for AI Safety — A ReviewarXiv:2404.14082Leonard Bereska, Efstratios Gavves2024 · 108 citations
- Foundational Challenges in Assuring Alignment and Safety of Large Language ModelsarXiv:2404.09932Usman Anwar, Abulhair Saparov, Javier Rando, et al.2024 · 87 citations
- PaperBench: Evaluating AI's Ability to Replicate AI ResearcharXiv:2504.01848Giulio Starace, Oliver Jaffe, Dane Sherburn, et al.2025 · 86 citations
- Detoxifying Large Language Models via Knowledge EditingAnnual Meeting of the Association for Computational Linguistics (ACL)Mengru Wang, Ningyu Zhang, Ziwen Xu, et al.2024 · 84 citations
- Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank ModificationsarXiv:2402.05162Boyi Wei, Kaixuan Huang, Yangsibo Huang, et al.2024 · 66 citations
- On Memorization of Large Language Models in Logical ReasoningInternational Joint Conference on Natural Language Processing (IJCNLP)Chulin Xie, Yangsibo Huang, Chiyuan Zhang, et al.2025 · 45 citations
- 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
- Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of RaceAnnual Meeting of the Association for Computational Linguistics (ACL)Lihao Sun, Chengzhi Mao, Valentin Hofmann, et al.2025 · 10 citations
- 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
- 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
- Universal Jailbreak Suffixes Are Strong Attention HijackersTransactions of the Association for Computational Linguistics (TACL)Matan Ben-Tov, Mor Geva, Mahmood Sharif2026 · 3 citations
- Aligned Probing: Relating Toxic Behavior and Model InternalsTransactions of the Association for Computational Linguistics (TACL)Andreas Waldis, Vagrant Gautam, Anne Lauscher, et al.2026 · 1 citation
- How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and ActivationFindings of the Association for Computational LinguisticsHao Yang, Qinghua Zhao, Lei Li, et al.2026 · 1 citation
- CausalDetox: Causal Head Selection and Intervention for Language Model DetoxificationFindings of the Association for Computational LinguisticsYian Wang, Yuen Chen, Agam Goyal, et al.2026
- Defeating Cerberus: Privacy-Leakage Mitigation in Vision Language ModelsFindings of the Association for Computational LinguisticsBoyang Zhang, Istemi Ekin Akkus, Ruichuan Chen, et al.2026
- Detoxification for LLM: From Dataset ItselfAnnual Meeting of the Association for Computational Linguistics (ACL)Wei Shao, Yihang Wang, Gao yu Zhu, et al.2026
- Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Wai Man Si, Mingjie Li, Michael Backes, et al.2026
- What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge RepresentationsAnnual Meeting of the Association for Computational Linguistics (ACL)Yujie Luo, Zhuoyun Yu, Xuehai Wang, et al.2026
This page in Markdown → https://md.research.elamur.ai/free/en/papers/lee-2024-mechanistic-understanding-alignment-algorithms-case/cited-by/