Elamur Research⌕
☰
home / authors / Shane Legg / cited by

Who cites Shane Legg

571 citations of their works from 511 papers of our library (of the 149,439 whose bibliographies we read) · 102 with a page here, the most cited first · page 1 of 2 · 1–100 · ← Shane Legg

1 2

  1. TensorFlow: A system for large-scale machine learningarXiv:1605.08695Martin Abadi, Paul Barham, Jianmin Chen, et al.2016 · 12,711 citations
  2. Training language models to follow instructions with human feedbackarXiv:2203.02155Long Ouyang, Jeff Wu, Xu Jiang, et al.2022 · 10,224 citations
  3. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed SystemsarXiv:1603.04467Martín Abadi, Ashish Agarwal, Paul Barham, et al.2016 · 9,512 citations
  4. Representation Learning with Contrastive Predictive CodingarXiv:1807.03748Aaron van den Oord, Yazhe Li, Oriol Vinyals2018 · 7,022 citations
  5. On the Opportunities and Risks of Foundation ModelsarXiv:2108.07258Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, et al.2021 · 3,160 citations
  6. Sparks of Artificial General Intelligence: Early experiments with GPT-4arXiv:2303.12712Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, et al.2023 · 2,439 citations
  7. Measuring Mathematical Problem Solving With the MATH DatasetarXiv:2103.03874Dan Hendrycks, Collin Burns, Saurav Kadavath, et al.2021 · 2,395 citations
  8. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelsarXiv:2206.04615 · Transactions on Machine Learning Research, May/2022, https://openreview.net/forum?id=uyTL5BvosjAarohi Srivastava, Abhinav Rastogi, Abhishek Rao, et al.2022 · 1,756 citations
  9. Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentsIEEE Computer Society Conference on Computer Vision and Pattern RecognitionPeter Anderson, Qi Wu, Damien Teney, et al.2017 · 1,414 citations
  10. GPQA: A Graduate-Level Google-Proof Q&A BenchmarkarXiv:2311.12022David Rein, Betty Li Hou, Asa Cooper Stickland, et al.2023 · 1,018 citations
  11. Universal and Transferable Adversarial Attacks on Aligned Language ModelsarXiv:2307.15043Andy Zou, Zifan Wang, Nicholas Carlini, et al.2023 · 1,005 citations
  12. Explainability for Large Language Models: A SurveyACM Transactions on Intelligent Systems and TechnologyHaiyan Zhao, Hanjie Chen, Fan Yang, et al.2023 · 790 citations
  13. WebGPT: Browser-assisted question-answering with human feedbackarXiv:2112.09332Reiichiro Nakano, Jacob Hilton, Suchir Balaji, et al.2021 · 721 citations
  14. Tulu 3: Pushing Frontiers in Open Language Model Post-TrainingarXiv:2411.15124Nathan Lambert, Jacob Morrison, Valentina Pyatkin, et al.2024 · 423 citations
  15. Representation Engineering: A Top-Down Approach to AI TransparencyarXiv:2310.01405Andy Zou, Long Phan, Sarah Chen, et al.2023 · 397 citations
  16. Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General AgentsJournal of Artificial Intelligence ResearchMarlos C. Machado, Marc G. Bellemare, Erik Talvitie, et al.2017 · 393 citations
  17. Towards Understanding Sycophancy in Language ModelsarXiv:2310.13548Mrinank Sharma, Meg Tong, Tomasz Korbak, et al.2023 · 384 citations
  18. Improving alignment of dialogue agents via targeted human judgementsarXiv:2209.14375Amelia Glaese, Nat McAleese, Maja Trębacz, et al.2022 · 362 citations
  19. Compressive Transformers for Long-Range Sequence ModellingarXiv:1911.05507Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar, et al.2019 · 340 citations
  20. TextWorld: A Learning Environment for Text-based GamesCommunications in computer and information scienceMarc-Alexandre Cote, Akos Kadar, Xingdi Yuan, et al.2018 · 339 citations
  21. Scaling Laws for Reward Model OveroptimizationarXiv:2210.10760Leo Gao, John Schulman, Jacob Hilton2022 · 323 citations
  22. Exploration by Random Network DistillationarXiv:1810.12894Yuri Burda, Harrison Edwards, Amos Storkey, et al.2018 · 302 citations
  23. xLSTM: Extended Long Short-Term MemoryConference on Neural Information Processing Systems (NeurIPS)Maximilian Beck, Korbinian Pöppel, Markus Spanring, et al.2024 · 296 citations
  24. OpenAI GPT-5 System CardarXiv:2601.03267Aaditya Singh, Adam Fry, Adam Perelman, et al.2025 · 279 citations
  25. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language ModelsarXiv:2410.05229Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, et al.2024 · 273 citations
  26. RAFT: Reward rAnked FineTuning for Generative Foundation Model AlignmentarXiv:2304.06767Hanze Dong, Wei Xiong, Deepanshu Goyal, et al.2023 · 252 citations
  27. Learning and Evaluating General Linguistic IntelligencearXiv:1901.11373Dani Yogatama, Cyprien de Masson d'Autume, Jerome Connor, et al.2019 · 248 citations
  28. Gradient Surgery for Multi-Task LearningarXiv:2001.06782Tianhe Yu, Saurabh Kumar, Abhishek Gupta, et al.2020 · 233 citations
  29. Scalable agent alignment via reward modeling: a research directionarXiv:1811.07871Jan Leike, David Krueger, Tom Everitt, et al.2018 · 227 citations
  30. Reinforced Self-Training (ReST) for Language ModelingarXiv:2308.08998Caglar Gulcehre, Tom Le Paine, Srivatsan Srinivasan, et al.2023 · 224 citations
  31. Teaching language models to support answers with verified quotesarXiv:2203.11147Jacob Menick, Maja Trebacz, Vladimir Mikulik, et al.2022 · 218 citations
  32. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human FeedbackIEEE Computer Society Conference on Computer Vision and Pattern RecognitionTianyu Yu, Yuan Yao, Haoye Zhang, et al.2023 · 217 citations
  33. Recursively Summarizing Books with Human FeedbackarXiv:2109.10862Jeff Wu, Long Ouyang, Daniel M. Ziegler, et al.2021 · 208 citations
  34. Grounded Language Learning in a Simulated 3D WorldarXiv:1706.06551Karl Moritz Hermann, Felix Hill, Simon Green, et al.2017 · 190 citations
  35. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
  36. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak SupervisionarXiv:2312.09390Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, et al.2023 · 172 citations
  37. Process Reinforcement through Implicit RewardsarXiv:2502.01456Ganqu Cui, Lifan Yuan, Zefan Wang, et al.2025 · 151 citations
  38. HyperTree Proof Search for Neural Theorem ProvingConference on Neural Information Processing Systems (NeurIPS)Guillaume Lample, Marie-Anne Lachaux, Thibaut Lavril, et al.2022 · 151 citations
  39. Unsolved Problems in ML SafetyarXiv:2109.13916Dan Hendrycks, Nicholas Carlini, John Schulman, et al.2021 · 151 citations
  40. A Roadmap to Pluralistic AlignmentarXiv:2402.05070Taylor Sorensen, Jared Moore, Jillian Fisher, et al.2024 · 143 citations
  41. The Impact of Positional Encoding on Length Generalization in TransformersConference on Neural Information Processing Systems (NeurIPS)Amirhossein Kazemnejad, Inkit Padhi, Karthikeyan Natesan Ramamurthy, et al.2023 · 134 citations
  42. DeepMind LabarXiv:1612.03801Charles Beattie, Joel Z. Leibo, Denis Teplyashin, et al.2016 · 134 citations
  43. Humans or LLMs as the Judge? A Study on Judgement BiasConference on Empirical Methods in Natural Language Processing (EMNLP)Guiming Hardy Chen, Shunian Chen, Ziche Liu, et al.2024 · 133 citations
  44. Large Language Model Alignment: A SurveyarXiv:2309.15025Tianhao Shen, Renren Jin, Yufei Huang, et al.2023 · 124 citations
  45. BabyAI: A Platform to Study the Sample Efficiency of Grounded Language LearningarXiv:1810.08272Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, et al.2018 · 123 citations
  46. The Alignment Problem from a Deep Learning PerspectivearXiv:2209.00626Richard Ngo, Lawrence Chan, Soren Mindermann2022 · 121 citations
  47. Best Practices and Lessons Learned on Synthetic DataarXiv:2404.07503Ruibo Liu, Jerry Wei, Fangyu Liu, et al.2024 · 119 citations
  48. Measuring Progress on Scalable Oversight for Large Language ModelsarXiv:2211.03540Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez, et al.2022 · 117 citations
  49. Emergent Linear Representations in World Models of Self-Supervised Sequence ModelsarXiv:2309.00941Neel Nanda, Andrew Lee, Martin Wattenberg2023 · 116 citations
  50. Mechanistic Interpretability for AI Safety — A ReviewarXiv:2404.14082Leonard Bereska, Efstratios Gavves2024 · 108 citations
  51. Safety Alignment Should Be Made More Than Just a Few Tokens DeeparXiv:2406.05946Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, et al.2024 · 97 citations
  52. Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsarXiv:2309.16042Fred Zhang, Neel Nanda2023 · 97 citations
  53. Identifying the Risks of LM Agents with an LM-Emulated SandboxarXiv:2309.15817Yangjun Ruan, Honghua Dong, Andrew Wang, et al.2023 · 96 citations
  54. Training Socially Aligned Language Models on Simulated Social InteractionsarXiv:2305.16960Ruibo Liu, Ruixin Yang, Chenyan Jia, et al.2023 · 94 citations
  55. A Survey of Reinforcement Learning from Human FeedbackTransactions on Machine Learning ResearchTimo Kaufmann, Paul Weng, Viktor Bengs, et al.2023 · 92 citations
  56. Language Modeling Is CompressionarXiv:2309.10668Gregoire Deletang, Anian Ruoss, Paul-Ambroise Duquenne, et al.2023 · 91 citations
  57. Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewardsConference on Neural Information Processing Systems (NeurIPS)Alexandre Rame, Guillaume Couairon, Mustafa Shukor, et al.2023 · 90 citations
  58. Deep Reinforcement Learning at the Edge of the Statistical PrecipicearXiv:2108.13264Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, et al.2021 · 90 citations
  59. Foundational Challenges in Assuring Alignment and Safety of Large Language ModelsarXiv:2404.09932Usman Anwar, Abulhair Saparov, Javier Rando, et al.2024 · 87 citations
  60. Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language GenerationTransactions of the Association for Computational Linguistics (TACL)Patrick Fernandes, Aman Madaan, Emmy Liu, et al.2023 · 84 citations
  61. AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language ReasoningConference on Neural Information Processing Systems (NeurIPS)Wei Fu, Jiaxuan Gao, Xujie Shen, et al.2025 · 80 citations
  62. Humans or LLMs as the Judge? A Study on Judgement BiasesarXiv:2402.10669Guiming Hardy Chen, Shunian Chen, Ziche Liu, et al.2024 · 78 citations
  63. A Primer on the Inner Workings of Transformer-based Language ModelsarXiv:2405.00208Javier Ferrando, Gabriele Sarti, Arianna Bisazza, et al.2024 · 72 citations
  64. Secrets of RLHF in Large Language Models Part II: Reward ModelingarXiv:2401.06080Binghai Wang, Rui Zheng, Lu Chen, et al.2024 · 72 citations
  65. Mission: Impossible Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Julie Kallini, Isabel Papadimitriou, Richard Futrell, et al.2024 · 70 citations
  66. Modular Pluralism: Pluralistic Alignment via Multi-LLM CollaborationConference on Empirical Methods in Natural Language Processing (EMNLP)Shangbin Feng, Taylor Sorensen, Yuhan Liu, et al.2024 · 68 citations
  67. What Algorithms can Transformers Learn? A Study in Length GeneralizationarXiv:2310.16028Hattie Zhou, Arwen Bradley, Etai Littwin, et al.2023 · 67 citations
  68. Linear Representations of Sentiment in Large Language ModelsarXiv:2310.15154Curt Tigges, Oskar John Hollinsworth, Atticus Geiger, et al.2023 · 64 citations
  69. MLLM-Protector: Ensuring MLLM's Safety without Hurting PerformanceConference on Empirical Methods in Natural Language Processing (EMNLP)Renjie Pi, Tianyang Han, Jianshu Zhang, et al.2024 · 58 citations
  70. Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackarXiv:2303.05453Hannah Rose Kirk, Bertie Vidgen, Paul Rottger, et al.2023 · 57 citations
  71. Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop QueriesConference on Empirical Methods in Natural Language Processing (EMNLP)Eden Biran, Daniela Gottesman, Sohee Yang, et al.2024 · 55 citations
  72. 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
  73. HyperCLOVA X Technical ReportarXiv:2404.01954Kang Min Yoo, Jaegeun Han, Sookyo In, et al.2024 · 44 citations
  74. Information Flow Routes: Automatically Interpreting Language Models at ScaleConference on Empirical Methods in Natural Language Processing (EMNLP)Javier Ferrando, Elena Voita2024 · 43 citations
  75. When does In-context Learning Fall Short and Why? A Study on Specification-Heavy TasksarXiv:2311.08993Hao Peng, Xiaozhi Wang, Jianhui Chen, et al.2023 · 42 citations
  76. SALMON: Self-Alignment with Instructable Reward ModelsarXiv:2310.05910Zhiqing Sun, Yikang Shen, Hongxin Zhang, et al.2023 · 41 citations
  77. Aligning LLMs with Individual Preferences via InteractionInternational Conference on Computational Linguistics (COLING)Shujin Wu, Yi R. Fung, Cheng Qian, et al.2025 · 24 citations
  78. Scaling Latent Reasoning via Looped Language ModelsarXiv:2510.25741Rui-Jie Zhu, Zixuan Wang, Kai Hua, et al.2025 · 22 citations
  79. Rewarding Chatbots for Real-World Engagement with Millions of UsersarXiv:2303.06135Robert Irvine, Douglas Boubert, Vyas Raina, et al.2023 · 22 citations
  80. GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?arXiv:2502.05252Yang Zhou, Hongyi Liu, Zhuoming Chen, et al.2025 · 21 citations
  81. Language Models as Models of LanguagearXiv:2408.07144Raphael Milliere2024 · 21 citations
  82. CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and AugmentationTransactions of the Association for Computational Linguistics (TACL)Ingo Ziegler, Abdullatif Köksal, Desmond Elliott, et al.2025 · 20 citations
  83. Language Models Encode the Value of Numbers LinearlyInternational Conference on Computational Linguistics (COLING)Fangwei Zhu, Damai Dai, Zhifang Sui2025 · 15 citations
  84. Can Language Models Learn Typologically Implausible Languages?Transactions of the Association for Computational Linguistics (TACL)Tianyang Xu, Tatsuki Kuribayashi, Yohei Oseki, et al.2026 · 10 citations
  85. Targeted Syntactic Evaluation on the Chomsky HierarchyLanguage Resources and Evaluation Conference (LREC)Taiga Someya, Ryo Yoshida, Yohei Oseki2024 · 10 citations
  86. 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
  87. The Quest for the Right Mediator: Surveying Mechanistic Interpretability for NLP Through the Lens of Causal Mediation AnalysisComputational LinguisticsAaron Mueller, Jannik Brinkmann, Millicent Li, et al.2026 · 7 citations
  88. Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint VerbalizationAnnual Meeting of the Association for Computational Linguistics (ACL)Kerem Zaman, Shashank Srivastava2026 · 5 citations
  89. AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior MonitorFindings of the Association for Computational LinguisticsShu Yang, Jingyu Hu, Tong Li, et al.2026 · 2 citations
  90. CoAct: Co-Active LLM Preference Learning with Human-AI SynergyAnnual Meeting of the Association for Computational Linguistics (ACL)Ruiyao Xu, Mihir Parmar, Tiankai Yang, et al.2026 · 1 citation
  91. Incentivizing Strong Reasoning from Weak SupervisionConference of the European Chapter of the Association for Computational Linguistics (EACL)Yige Yuan, Teng Xiao, Shuchang Tao, et al.2026 · 1 citation
  92. Training Language Models to Use Prolog as a ToolFindings of the Association for Computational LinguisticsNiklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech2026 · 1 citation
  93. When Do Large Language Models Exhibit Unsolicited Deception?Transactions of the Association for Computational Linguistics (TACL)Samuel M. Taylor, Benjamin K. Bergen2026 · 1 citation
  94. Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative Side DecidablearXiv:2608.00981Wenhui Chen, Jianlin Chen, Ziyao Lin, et al.2026
  95. Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute ScalingFindings of the Association for Computational LinguisticsIvan Rodkin, Daniil Orel, Konstantin Smirnov, et al.2026
  96. Can Large Language Models Effectively Support Decision-Making in Sudden Emergencies?Findings of the Association for Computational LinguisticsMengna Zhu, Jibing Wu, Lihua Liu, et al.2026
  97. Entity-Level Sentiment Analysis with Sentence Relevance DetectionLanguage Resources and Evaluation Conference (LREC)Egil Rønningstad, Roman Klinger, Lilja Øvrelid, et al.2026
  98. GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy InputsFindings of the Association for Computational LinguisticsZhengxin Zhang, Chengyu Huang, Xufu Liu, et al.2026
  99. MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Yizhe Zeng, Wei Zhang, Yunpeng Li, et al.2026
  100. PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL)Yiqing Zhang, Xiaozhong Liu, Fabricio Murai2026

1 2

↑ back to top

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