🔗 Who cites «AI safety via debate»

81 papers of our library cite it (of the 149,439 whose bibliographies we read) · 38 with a page here, the most cited first · ← back to «AI safety via debate»

1. Training language models to follow instructions with human feedbackarXiv:2203.02155Long Ouyang, Jeff Wu, Xu Jiang, et al.2022 · 10,224 citations
2. 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
3. The Rise and Potential of Large Language Model Based Agents: A SurveyScience China Information SciencesZhiheng Xi, Wenxiang Chen, Xin Guo, et al.2023 · 1,272 citations
4. Constitutional AI: Harmlessness from AI FeedbackarXiv:2212.08073Yuntao Bai, Saurav Kadavath, Sandipan Kundu, et al.2022 · 1,028 citations
5. GPQA: A Graduate-Level Google-Proof Q&A BenchmarkarXiv:2311.12022David Rein, Betty Li Hou, Asa Cooper Stickland, et al.2023 · 1,018 citations
6. WebGPT: Browser-assisted question-answering with human feedbackarXiv:2112.09332Reiichiro Nakano, Jacob Hilton, Suchir Balaji, et al.2021 · 721 citations
7. Improving Factuality and Reasoning in Language Models through Multiagent DebatearXiv:2305.14325Yilun Du, Shuang Li, Antonio Torralba, et al.2023 · 587 citations
8. Towards Understanding Sycophancy in Language ModelsarXiv:2310.13548Mrinank Sharma, Meg Tong, Tomasz Korbak, et al.2023 · 384 citations
9. Improving alignment of dialogue agents via targeted human judgementsarXiv:2209.14375Amelia Glaese, Nat McAleese, Maja Trębacz, et al.2022 · 362 citations
10. Solving math word problems with process- and outcome-based feedbackarXiv:2211.14275Jonathan Uesato, Nate Kushman, Ramana Kumar, et al.2022 · 355 citations
11. Discovering Language Model Behaviors with Model-Written EvaluationsarXiv:2212.09251Ethan Perez, Sam Ringer, Kamilė Lukošiūtė, et al.2022 · 328 citations
12. Challenges and Applications of Large Language ModelsarXiv:2307.10169Jean Kaddour, Joshua Harris, Maximilian Mozes, et al.2023 · 301 citations
13. RAFT: Reward rAnked FineTuning for Generative Foundation Model AlignmentarXiv:2304.06767Hanze Dong, Wei Xiong, Deepanshu Goyal, et al.2023 · 252 citations
14. Scalable agent alignment via reward modeling: a research directionarXiv:1811.07871Jan Leike, David Krueger, Tom Everitt, et al.2018 · 227 citations
15. Teaching language models to support answers with verified quotesarXiv:2203.11147Jacob Menick, Maja Trebacz, Vladimir Mikulik, et al.2022 · 218 citations
16. Recursively Summarizing Books with Human FeedbackarXiv:2109.10862Jeff Wu, Long Ouyang, Daniel M. Ziegler, et al.2021 · 208 citations
17. Will we run out of data? Limits of LLM scaling based on human-generated dataarXiv:2211.04325Pablo Villalobos, Anson Ho, Jaime Sevilla, et al.2022 · 198 citations
18. AI Alignment: A Comprehensive SurveyarXiv:2310.19852Jiaming Ji, Tianyi Qiu, Boyuan Chen, et al.2023 · 173 citations
19. Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak SupervisionarXiv:2312.09390Collin Burns, Pavel Izmailov, Jan Hendrik Kirchner, et al.2023 · 172 citations
20. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherarXiv:2308.06463Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, et al.2023 · 168 citations
21. Unsolved Problems in ML SafetyarXiv:2109.13916Dan Hendrycks, Nicholas Carlini, John Schulman, et al.2021 · 151 citations
22. Large Language Model Alignment: A SurveyarXiv:2309.15025Tianhao Shen, Renren Jin, Yufei Huang, et al.2023 · 124 citations
23. The Alignment Problem from a Deep Learning PerspectivearXiv:2209.00626Richard Ngo, Lawrence Chan, Soren Mindermann2022 · 121 citations
24. Measuring Progress on Scalable Oversight for Large Language ModelsarXiv:2211.03540Samuel R. Bowman, Jeeyoon Hyun, Ethan Perez, et al.2022 · 117 citations
25. Debating with More Persuasive LLMs Leads to More Truthful AnswersarXiv:2402.06782Akbir Khan, John Hughes, Dan Valentine, et al.2024 · 101 citations
26. Training Socially Aligned Language Models on Simulated Social InteractionsarXiv:2305.16960Ruibo Liu, Ruixin Yang, Chenyan Jia, et al.2023 · 94 citations
27. Foundational Challenges in Assuring Alignment and Safety of Large Language ModelsarXiv:2404.09932Usman Anwar, Abulhair Saparov, Javier Rando, et al.2024 · 87 citations
28. Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in ChinchillaarXiv:2307.09458Tom Lieberum, Matthew Rahtz, Janos Kramar, et al.2023 · 58 citations
29. 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
30. Finding Generalizable Evidence by Learning to Convince Q&A ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Ethan Perez, Siddharth Karamcheti, Rob Fergus, et al.2019 · 43 citations
31. Multiple LLM Agents Debate for Equitable Cultural AlignmentAnnual Meeting of the Association for Computational Linguistics (ACL)Dayeon Ki, Rachel Rudinger, Tianyi Zhou, et al.2025 · 10 citations
32. A pragmatic account of the weak evidence effectOpen MindSamuel A. Barnett, Thomas L. Griffiths, Robert D. Hawkins2021 · 7 citations
33. AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language ModelsFindings of the Association for Computational LinguisticsYixu Wang, Xin Wang, Yang Yao, et al.2026 · 1 citation
34. ARGSBASE: A Multi-Agent Interface for Structured Human–AI DeliberationConference of the European Chapter of the Association for Computational Linguistics (EACL)Frieso Turkstra, Sara Nabhani, Khalid Al Khatib2026 · 1 citation
35. ART: Adaptive Reasoning Trees for Explainable Claim VerificationFindings of the Association for Computational LinguisticsSahil Wadhwa, Himanshu Kumar, Guanqun Yang, et al.2026 · 1 citation
36. Agentic Oversight via Dialectic ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Leonardo Ranaldi, Federico Ranaldi2026
37. NP-Hard Lower Bound Complexity for Semantic Self-VerificationConference of the European Chapter of the Association for Computational Linguistics (EACL)Robin Young2026
38. Tandem Training for Language ModelsConference of the European Chapter of the Association for Computational Linguistics (EACL)Robert West, Ashton Anderson, Ece Kamar, et al.2026

43 more papers of our library cite it; they have no page here yet.

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/irving-2018-ai-safety-debate/cited-by/