{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T18:45:51Z","timestamp":1791485151192,"version":"4.3.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619456","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"2027-2032","source":"Crossref","is-referenced-by-count":5,"title":["Asymptotics of Language Model Alignment"],"prefix":"10.1109","author":[{"given":"Joy Qiping","family":"Yang","sequence":"first","affiliation":[{"name":"University of Sydney,Sydney,Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Salamatian","sequence":"additional","affiliation":[{"name":"MIT,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziteng","family":"Sun","sequence":"additional","affiliation":[{"name":"Google Research,New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ananda Theertha","family":"Suresh","sequence":"additional","affiliation":[{"name":"Google Research,New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmad","family":"Beirami","sequence":"additional","affiliation":[{"name":"Google Research,New York,NY,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Yang","year":"2024","journal-title":"Asymptotics of language model alignment"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning. PMLR","author":"Sohl-Dickstein","year":"2015"},{"key":"ref6","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","author":"Bai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Calibrating sequence likelihood improves conditional language generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhao","year":"2022"},{"key":"ref13","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref14","article-title":"Controlled decoding from language models","author":"Mudgal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"3511","article-title":"FUDGE: Controlled text generation with future discriminators","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Yang","year":"2021"},{"key":"ref16","article-title":"WebGPT: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"10835","article-title":"Scaling laws for reward model overoptimization","volume-title":"International Conference on Machine Learning. PMLR","author":"Gao","year":"2023"},{"key":"ref18","article-title":"Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking","author":"Eisenstein","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Mismatched guesswork","author":"Salamatian","year":"2019","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Theoretical guarantees on the best-of-n alignment policy","author":"Beirami","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"16203","article-title":"On reinforcement learning and distribution matching for fine-tuning language models with no catastrophic forgetting","volume":"35","author":"Korbak","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.77"},{"issue":"142","key":"ref23","first-page":"1","article-title":"On tilted losses in machine learning: Theory and applications","volume":"24","author":"Li","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-5320-4"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619456.pdf?arnumber=10619456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:28:55Z","timestamp":1773347335000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619456","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}