{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:49:51Z","timestamp":1772934591894,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402037","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5373-5381","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Task-Oriented Dialogue Systems with Mixture of Experts and Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Dharmendra","family":"Prajapat","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Durga","family":"Toshniwal","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Dept of Computer Science and Engineering,Roorkee,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1117562.1117565"},{"key":"ref2","article-title":"Conversational ai: The science behind the alexa prize","volume-title":"arXiv preprint","author":"Ram","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1199"},{"key":"ref5","article-title":"Unified language model pre-training for natural language understanding and generation","volume":"32","author":"Dong","year":"2019","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"ref6","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog,"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.54"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21320"},{"key":"ref10","first-page":"20179","article-title":"A simple language model for task-oriented dialogue","volume":"33","author":"Hosseini-Asl","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386495"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70365-2_10"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531920"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.112"},{"key":"ref16","article-title":"Efficient task-oriented dialogue systems with response selection as an auxiliary task","author":"Cholakov","year":"2022","journal-title":"arXiv preprint"},{"issue":"140","key":"ref17","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref18","article-title":"Space-3: Unified dialog model pre-training for task-oriented dialog understanding and generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.8"},{"key":"ref21","author":"Snell","journal-title":"Offline rl for natural language generation with implicit language q learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.181"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825582"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref25","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref27","article-title":"Adapting large language models for document-level machine translation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-demo.4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sigdial-1.21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6507"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"ref32","first-page":"532","article-title":"Augpt: Dialogue with pre-trained language models and data augmentation","volume":"26","author":"Kulhanek","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Sequence level training with recurrent neural networks","volume-title":"4th International Conference on Learning Representations, ICLR 2016, 2016","author":"Ranzato"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.464"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1347-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012596"},{"key":"ref37","article-title":"Behavior alignment via reward function optimization","volume":"36","author":"Gupta","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.759"},{"key":"ref39","article-title":"Fantastic rewards and how to tame them: A case study on reward learning for task-oriented dialogue systems","volume-title":"The Eleventh International Conference on Learning Representations, 2023","author":"Feng"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017289"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1364"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.472"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref44","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"issue":"240","key":"ref45","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref46","article-title":"Guiding large language models via directional stimulus prompting","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.57"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.740"},{"key":"ref49","article-title":"Domain state tracking for a simplified dialogue system","author":"Jeon","year":"2021","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.319"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.702"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5921"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402037.pdf?arnumber=11402037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:12:06Z","timestamp":1772867526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402037","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}