{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T22:01:47Z","timestamp":1784584907404,"version":"3.55.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s11432-024-4348-6","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T07:29:23Z","timestamp":1747898963000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The superalignment of superhuman intelligence with large language models"],"prefix":"10.1007","volume":"68","author":[{"given":"Minlie","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingkang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiyao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"4348_CR1","volume-title":"Introducing ChatGPT","author":"OpenAI","year":"2022","unstructured":"OpenAI. Introducing ChatGPT, 2022. https:\/\/openai.com\/index\/chatgpt\/"},{"key":"4348_CR2","volume-title":"A survey of large language models","author":"W X Zhao","year":"2023","unstructured":"Zhao W X, Zhou K, Li J, et al. A survey of large language models. 2023. ArXiv:2303.18223"},{"key":"4348_CR3","volume-title":"OpenAI Charter","author":"OpenAI","year":"2018","unstructured":"OpenAI. OpenAI Charter. 2018. https:\/\/openai.com\/charter\/"},{"key":"4348_CR4","volume-title":"Definition to AGI","author":"G Marcus","year":"2022","unstructured":"Marcus G. Definition to AGI. 2022. https:\/\/twitter.com\/GaryMarcus\/status\/1529457162811936768"},{"key":"4348_CR5","volume-title":"Human Intelligence","author":"Y LeCun","year":"2024","unstructured":"LeCun Y. Human Intelligence. 2024. https:\/\/twitter.com\/ylecun\/status\/1846034609521246234"},{"key":"4348_CR6","volume-title":"AMI (advanced machine intelligence)","author":"Y LeCun","year":"2024","unstructured":"LeCun Y. AMI (advanced machine intelligence). 2024. https:\/\/twitter.com\/ylecun\/status\/1794249923329720415"},{"key":"4348_CR7","volume-title":"Model evaluation for extreme risks","author":"T Shevlane","year":"2023","unstructured":"Shevlane T, Farquhar S, Garfinkel B, et al. Model evaluation for extreme risks. 2023. ArXiv:2305.15324"},{"key":"4348_CR8","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1126\/science.adn0117","volume":"384","author":"Y Bengio","year":"2024","unstructured":"Bengio Y, Hinton G, Yao A, et al. Managing extreme AI risks amid rapid progress. Science, 2024, 384: 842\u2013845","journal-title":"Science"},{"key":"4348_CR9","volume-title":"Large language model alignment: a survey","author":"T Shen","year":"2023","unstructured":"Shen T, Jin R, Huang Y, et al. Large language model alignment: a survey. 2023. ArXiv:2309.15025"},{"key":"4348_CR10","volume-title":"Proximal policy optimization algorithms","author":"J Schulman","year":"2017","unstructured":"Schulman J, Wolski F, Dhariwal P, et al. Proximal policy optimization algorithms. 2017. ArXiv:1707.06347"},{"key":"4348_CR11","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"R Rafailov","year":"2024","unstructured":"Rafailov R, Sharma A, Mitchell E, et al. Direct preference optimization: your language model is secretly a reward model. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4348_CR12","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"H Ji","year":"2024","unstructured":"Ji H, Lu C, Niu Y, et al. Towards efficient exact optimization of language model alignment. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4348_CR13","volume-title":"Introducing superalignment","author":"OpenAI","year":"2023","unstructured":"OpenAI. Introducing superalignment. 2023. https:\/\/openai.com\/index\/introducing-superalignment\/"},{"key":"4348_CR14","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"D Bahdanau","year":"2015","unstructured":"Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations, 2015"},{"key":"4348_CR15","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"W Yuan","year":"2024","unstructured":"Yuan W, Pang R Y, Cho K, et al. Self-rewarding language models. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4348_CR16","volume-title":"Statistical rejection sampling improves preference optimization","author":"T Liu","year":"2023","unstructured":"Liu T, Zhao Y, Joshi R, et al. Statistical rejection sampling improves preference optimization. 2023. ArXiv:2309.06657"},{"key":"4348_CR17","first-page":"18990","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"F Song","year":"2024","unstructured":"Song F, Yu B, Li M, et al. Preference ranking optimization for human alignment. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2024. 18990\u201318998"},{"key":"4348_CR18","volume-title":"KTO: model alignment as prospect theoretic optimization","author":"K Ethayarajh","year":"2024","unstructured":"Ethayarajh K, Xu W, Muennighoff N, et al. KTO: model alignment as prospect theoretic optimization. 2024. ArXiv:2402.01306"},{"key":"4348_CR19","first-page":"4447","volume-title":"Proceedings of International Conference on Artificial Intelligence and Statistics","author":"M G Azar","year":"2024","unstructured":"Azar M G, Guo Z D, Piot B, et al. A general theoretical paradigm to understand learning from human preferences. In: Proceedings of International Conference on Artificial Intelligence and Statistics, 2024. 4447\u20134455"},{"key":"4348_CR20","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"C Burns","year":"2024","unstructured":"Burns C, Izmailov P, Kirchner J H, et al. Weak-to-strong generalization: eliciting strong capabilities with weak supervision. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4348_CR21","volume-title":"Measuring progress on scalable oversight for large language models","author":"S R Bowman","year":"2022","unstructured":"Bowman S R, Hyun J, Perez E, et al. Measuring progress on scalable oversight for large language models. 2022. ArXiv:2211.03540"},{"key":"4348_CR22","volume-title":"Supervising strong learners by amplifying weak experts","author":"P Christiano","year":"2018","unstructured":"Christiano P, Shlegeris B, Amodei D. Supervising strong learners by amplifying weak experts. 2018. ArXiv:1810.08575"},{"key":"4348_CR23","first-page":"11700","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok","author":"J Wen","year":"2024","unstructured":"Wen J, Zhong R, Ke P, et al. Learning task decomposition to assist humans in competitive programming. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok, 2024. 11700\u201311723"},{"key":"4348_CR24","volume-title":"Scalable agent alignment via reward modeling: a research direction","author":"J Leike","year":"2018","unstructured":"Leike J, Krueger D, Everitt T, et al. Scalable agent alignment via reward modeling: a research direction. 2018. ArXiv:1811.07871"},{"key":"4348_CR25","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Z Sun","year":"2024","unstructured":"Sun Z, Shen Y, Zhou Q, et al. Principle-driven self-alignment of language models from scratch with minimal human supervision. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4348_CR26","volume-title":"Constitutional AI: harmlessness from AI feedback","author":"Y Bai","year":"2022","unstructured":"Bai Y, Kadavath S, Kundu S, et al. Constitutional AI: harmlessness from AI feedback. 2022. ArXiv:2212.08073"},{"key":"4348_CR27","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Y Du","year":"2024","unstructured":"Du Y, Li S, Torralba A, et al. Improving factuality and reasoning in language models through multiagent debate. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4348_CR28","volume-title":"AI safety via debate","author":"G Irving","year":"2018","unstructured":"Irving G, Christiano P, Amodei D. AI safety via debate. 2018. ArXiv:1805.00899"},{"key":"4348_CR29","volume-title":"LLM critics help catch LLM bugs","author":"N McAleese","year":"2024","unstructured":"McAleese N, Pokorny R M, Uribe J F C, et al. LLM critics help catch LLM bugs. 2024. ArXiv:2407.00215"},{"key":"4348_CR30","volume-title":"Training verifiers to solve math word problems","author":"K Cobbe","year":"2021","unstructured":"Cobbe K, Kosaraju V, Bavarian M, et al. Training verifiers to solve math word problems. 2021. ArXiv:2110.14168"},{"key":"4348_CR31","volume-title":"Proceedings of International Conference on Learning Representations","author":"D Hendrycks","year":"2021","unstructured":"Hendrycks D, Burns C, Basart S, et al. Measuring massive multitask language understanding. In: Proceedings of International Conference on Learning Representations, 2021"},{"key":"4348_CR32","volume-title":"Evaluating large language models trained on code","author":"M Chen","year":"2021","unstructured":"Chen M, Tworek J, Jun H, et al. Evaluating large language models trained on code. 2021. ArXiv:2107.03374"},{"key":"4348_CR33","first-page":"46595","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"L Zheng","year":"2023","unstructured":"Zheng L, Chiang W L, Sheng Y, et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. In: Proceedings of Advances in Neural Information Processing Systems, 2023. 46595\u201346623"},{"key":"4348_CR34","first-page":"13034","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok","author":"P Ke","year":"2024","unstructured":"Ke P, Wen B, Feng A, et al. CritiqueLLM: towards an informative critique generation model for evaluation of large language model generation. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok, 2024. 13034\u201313054"},{"key":"4348_CR35","volume-title":"Generative verifiers: reward modeling as next-token prediction","author":"L Zhang","year":"2024","unstructured":"Zhang L, Hosseini A, Bansal H, et al. Generative verifiers: reward modeling as next-token prediction. 2024. ArXiv:2408.15240"},{"key":"4348_CR36","first-page":"6786","volume-title":"Proceedings of Findings of the Association for Computational Linguistics, Miami","author":"J Cheng","year":"2024","unstructured":"Cheng J, Lu Y, Gu X, et al. AutoDetect: towards a unified framework for automated weakness detection in large language models. In: Proceedings of Findings of the Association for Computational Linguistics, Miami, 2024. 6786\u20136803"},{"key":"4348_CR37","first-page":"9460","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"J Skalse","year":"2022","unstructured":"Skalse J, Howe N, Krasheninnikov D, et al. Defining and characterizing reward gaming. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 9460\u20139471"},{"key":"4348_CR38","volume-title":"Language models learn to mislead humans via RLHF","author":"J Wen","year":"2024","unstructured":"Wen J, Zhong R, Khan A, et al. Language models learn to mislead humans via RLHF. 2024. ArXiv:2409.12822"},{"key":"4348_CR39","volume-title":"Proceedings of the International Conference on Learning Representations","author":"J Cheng","year":"2025","unstructured":"Cheng J, Liu X, Wang C, et al. SPaR: self-play with tree-search refinement. In: Proceedings of the International Conference on Learning Representations, 2025"},{"key":"4348_CR40","volume-title":"Universal and transferable adversarial attacks on aligned language models","author":"A Zou","year":"2023","unstructured":"Zou A, Wang Z, Kolter J Z, et al. Universal and transferable adversarial attacks on aligned language models. 2023. ArXiv:2307.15043"},{"key":"4348_CR41","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s11263-024-02196-3","volume":"133","author":"C Liu","year":"2025","unstructured":"Liu C, Dong Y, Xiang W, et al. A comprehensive study on robustness of image classification models: benchmarking and rethinking. Int J Comput Vis, 2025, 133: 567\u2013589","journal-title":"Int J Comput Vis"},{"key":"4348_CR42","doi-asserted-by":"publisher","first-page":"102701","DOI":"10.1016\/j.inffus.2024.102701","volume":"114","author":"C Zhang","year":"2025","unstructured":"Zhang C, Hu M, Li W, et al. Adversarial attacks and defenses on text-to-image diffusion models: a survey. Inf Fusion, 2025, 114: 102701","journal-title":"Inf Fusion"},{"key":"4348_CR43","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.18653\/v1\/2023.emnlp-main.84","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore","author":"J Wen","year":"2023","unstructured":"Wen J, Ke P, Sun H, et al. Unveiling the implicit toxicity in large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, 2023. 1322\u20131338"},{"key":"4348_CR44","volume-title":"Improving reward models with synthetic critiques","author":"Z Ye","year":"2024","unstructured":"Ye Z, Greenlee-Scott F, Bartolo M, et al. Improving reward models with synthetic critiques. 2024. ArXiv:2405.20850"},{"key":"4348_CR45","volume-title":"Reinforcement learning for generative AI: a survey","author":"Y Cao","year":"2023","unstructured":"Cao Y, Sheng Q Z, McAuley J, et al. Reinforcement learning for generative AI: a survey. 2023. ArXiv:2308.14328"},{"key":"4348_CR46","first-page":"12281","volume-title":"Proceedings of Findings of the Association for Computational Linguistics, Miami","author":"M Wadhwa","year":"2024","unstructured":"Wadhwa M, Zhao X, Li J J, et al. Learning to refine with fine-grained natural language feedback. In: Proceedings of Findings of the Association for Computational Linguistics, Miami, 2024. 12281\u201312308"},{"key":"4348_CR47","volume-title":"Improving model factuality with fine-grained critique-based evaluator","author":"Y Xie","year":"2024","unstructured":"Xie Y, Zhou W, Prakash P, et al. Improving model factuality with fine-grained critique-based evaluator. 2024. ArXiv:2410.18359"},{"key":"4348_CR48","volume-title":"Proceedings of the 38th Annual Conference on Neural Information Processing Systems","author":"A Panickssery","year":"2024","unstructured":"Panickssery A, Bowman S R, Feng S. LLM evaluators recognize and favor their own generations. In: Proceedings of the 38th Annual Conference on Neural Information Processing Systems, 2024"},{"key":"4348_CR49","doi-asserted-by":"publisher","first-page":"4757","DOI":"10.18653\/v1\/2024.emnlp-main.273","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing, Miami","author":"Y Gao","year":"2024","unstructured":"Gao Y, Xu G, Wang Z, et al. Bayesian calibration of win rate estimation with LLM evaluators. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Miami, 2024. 4757\u20134769"},{"key":"4348_CR50","volume-title":"Trust or escalate: LLM judges with provable guarantees for human agreement","author":"J Jung","year":"2024","unstructured":"Jung J, Brahman F, Choi Y. Trust or escalate: LLM judges with provable guarantees for human agreement. 2024. ArXiv:2407.18370"},{"key":"4348_CR51","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"J Li","year":"2023","unstructured":"Li J, Sun S, Yuan W, et al. Generative judge for evaluating alignment. In: Proceedings of the 12th International Conference on Learning Representations, 2023"},{"key":"4348_CR52","volume-title":"JudgeLM: fine-tuned large language models are scalable judges","author":"L Zhu","year":"2023","unstructured":"Zhu L, Wang X, Wang X. JudgeLM: fine-tuned large language models are scalable judges. 2023. ArXiv:2310.17631"},{"key":"4348_CR53","volume-title":"Self-critiquing models for assisting human evaluators","author":"W Saunders","year":"2022","unstructured":"Saunders W, Yeh C, Wu J, et al. Self-critiquing models for assisting human evaluators. 2022. ArXiv:2206.05802"},{"key":"4348_CR54","first-page":"15476","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"E Zelikman","year":"2022","unstructured":"Zelikman E, Wu Y, Mu J, et al. Star: bootstrapping reasoning with reasoning. In: Proceedings of Advances in Neural Information Processing Systems, 2022. 15476\u201315488"},{"key":"4348_CR55","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Z Chen","year":"2024","unstructured":"Chen Z, Deng Y, Yuan H, et al. Self-play fine-tuning converts weak language models to strong language models. In: Proceedings of the 41st International Conference on Machine Learning, 2024"},{"key":"4348_CR56","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Madaan","year":"2024","unstructured":"Madaan A, Tandon N, Gupta P, et al. Self-refine: iterative refinement with self-feedback. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4348_CR57","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Y Bai","year":"2024","unstructured":"Bai Y, Ying J, Cao Y, et al. Benchmarking foundation models with language-model-as-an-examiner. In: Proceedings of Advances in Neural Information Processing Systems, 2024"},{"key":"4348_CR58","doi-asserted-by":"publisher","first-page":"12621","DOI":"10.18653\/v1\/2023.emnlp-main.778","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"R Cohen","year":"2023","unstructured":"Cohen R, Hamri M, Geva M, et al. LM vs LM: detecting factual errors via cross examination. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023. 12621\u201312640"},{"key":"4348_CR59","volume-title":"The curse of recursion: training on generated data makes models forget","author":"I Shumailov","year":"2024","unstructured":"Shumailov I, Shumaylov Z, Zhao Y, et al. The curse of recursion: training on generated data makes models forget. 2024. ArXiv:2305.17493"},{"key":"4348_CR60","volume-title":"Self-consuming generative models go MAD","author":"S Alemohammad","year":"2023","unstructured":"Alemohammad S, Casco-Rodriguez J, Luzi L, et al. Self-consuming generative models go MAD. 2023. ArXiv:2307.01850"},{"key":"4348_CR61","volume-title":"The curious decline of linguistic diversity: training language models on synthetic text","author":"Y Guo","year":"2024","unstructured":"Guo Y, Shang G, Vazirgiannis M, et al. The curious decline of linguistic diversity: training language models on synthetic text. 2024. ArXiv:2311.09807"},{"key":"4348_CR62","volume-title":"Large language models suffer from their own output: an analysis of the self-consuming training loop","author":"M Briesch","year":"2024","unstructured":"Briesch M, Sobania D, Rothlauf F. Large language models suffer from their own output: an analysis of the self-consuming training loop. 2024. ArXiv:2311.16822"},{"key":"4348_CR63","volume-title":"Self-improvement reversal in post-training","author":"T Wu","year":"2024","unstructured":"Wu T, Li X, Liu P. Progress or regress? Self-improvement reversal in post-training. 2024. ArXiv:2407.05013"},{"key":"4348_CR64","volume-title":"Mind the gap: examining the self-improvement capabilities of large language models","author":"Y Song","year":"2024","unstructured":"Song Y, Zhang H, Eisenach C, et al. Mind the gap: examining the self-improvement capabilities of large language models. 2024. ArXiv:2412.02674"},{"key":"4348_CR65","volume-title":"Panacea: Pareto alignment via preference adaptation for LLMs","author":"Y Zhong","year":"2024","unstructured":"Zhong Y, Ma C, Zhang X, et al. Panacea: Pareto alignment via preference adaptation for LLMs. 2024. ArXiv:2402.02030"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4348-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4348-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T21:02:44Z","timestamp":1784581364000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4348-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":65,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["4348"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4348-6","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]},"assertion":[{"value":"3 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"160107"}}