{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:21:22Z","timestamp":1751156482055,"version":"3.33.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/wsc63780.2024.10838929","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:40:24Z","timestamp":1737398424000},"page":"299-310","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Language Model with Both Human and Artificial Intelligence Feedback Data"],"prefix":"10.1109","author":[{"given":"Haoting","family":"Zhang","sequence":"first","affiliation":[{"name":"University of California at Berkeley,Berkeley,CA,USA"}]},{"given":"Jinghai","family":"He","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Berkeley,CA,USA"}]},{"given":"Jingxu","family":"Xu","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Berkeley,CA,USA"}]},{"given":"Jingshen","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Berkeley,CA,USA"}]},{"given":"Zeyu","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of California at Berkeley,Berkeley,CA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1060.0291"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-69033-9","volume-title":"Stochastic simulation: algorithms and analysis","volume":"57","author":"Asmussen","year":"2007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2023.4973"},{"journal-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback","year":"2022","author":"Bai","key":"ref4"},{"journal-title":"Constitutional AI: Harmlessness from AI feedback","year":"2022","author":"Bai","key":"ref5"},{"key":"ref6","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1108\/REGE-07-2021-0120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0331"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2018.8632506"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3213"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WSC40007.2019.9004835"},{"volume-title":"Deep learning","year":"2016","author":"Goodfellow","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.2484"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2022.1221"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2021.0225"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120141"},{"key":"ref18","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume":"26","author":"Johnson","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1070.0251"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1778"},{"key":"ref21","volume-title":"Nonlinear integer programming","volume":"84","author":"Li","year":"2006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1351"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1413"},{"key":"ref24","article-title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","volume":"36","author":"Nie","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/15M1046472"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2021.1088"},{"key":"ref27","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1404"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2020.0971"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611976595","volume-title":"Lectures on stochastic programming: modeling and theory","author":"Shapiro","year":"2021"},{"journal-title":"AI for Nonprofits: How to Use Artificial Intelligence for Good","year":"2023","author":"Millicent","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2015.0674"},{"journal-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2017.1670"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.0303"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3411080"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2014.7020219"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2023.1279"},{"journal-title":"TinyLlama: An Open-Source Small Language Model","year":"2024","author":"Zhang","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WSC52266.2021.9715437"}],"event":{"name":"2024 Winter Simulation Conference (WSC)","start":{"date-parts":[[2024,12,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 Winter Simulation Conference (WSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10838618\/10838619\/10838929.pdf?arnumber=10838929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:56:48Z","timestamp":1737442608000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10838929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/wsc63780.2024.10838929","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}