{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:18Z","timestamp":1775229618592,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819527243","type":"print"},{"value":"9789819527250","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-2725-0_21","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:20:29Z","timestamp":1761888029000},"page":"339-352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enabling Real-Time Conversations with\u00a0Minimal Training Costs"],"prefix":"10.1007","author":[{"given":"Wang","family":"Xu","sequence":"first","affiliation":[]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Weilin","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Xu","family":"Han","sequence":"additional","affiliation":[]},{"given":"Yukun","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Haiyan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Yudi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhe","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Zhiyuan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wanxiang","family":"Che","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Adlakha, V., BehnamGhader, P., Lu, X.H., Meade, N., Reddy, S.: Evaluating correctness and faithfulness of instruction-following models for question answering. arXiv preprint arXiv:2307.16877 (2023)","DOI":"10.1162\/tacl_a_00667"},{"key":"21_CR2","unstructured":"Austin, J., et\u00a0al.: Program synthesis with large language models. arXiv preprint arXiv:2108.07732 (2021)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: Gigaspeech: an evolving, multi-domain ASR corpus with 10,000 hours of transcribed audio. In: Conference of the International Speech Communication Association (2021)","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"21_CR4","unstructured":"Chen, M., et\u00a0al.: Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)"},{"key":"21_CR5","unstructured":"Chu, Y., et al.: Qwen2-audio technical report. arXiv preprint arXiv:2407.10759 (2024)"},{"key":"21_CR6","unstructured":"Clark, P., et al.: Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)"},{"key":"21_CR7","unstructured":"Cobbe, K., et\u00a0al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"21_CR8","unstructured":"Fang, Q., Guo, S., Zhou, Y., Ma, Z., Zhang, S., Feng, Y.: Llama-omni: seamless speech interaction with large language models. arXiv preprint arXiv:2409.06666 (2024)"},{"key":"21_CR9","unstructured":"Fu, C., et al.: Vita: towards open-source interactive omni multimodal LLM. arXiv preprint arXiv:2408.05211 (2024)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Han, H., Kim, J., Yoo, J., Lee, Y., Hwang, S.W.: ArchCode: incorporating software requirements in code generation with large language models. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, (vol. 1: Long Papers), pp. 13520\u201313552 (2024)","DOI":"10.18653\/v1\/2024.acl-long.730"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"He, C., et al.: Ultraeval: a lightweight platform for flexible and comprehensive evaluation for llms. arXiv preprint arXiv:2404.07584 (2024)","DOI":"10.18653\/v1\/2024.acl-demos.23"},{"key":"21_CR12","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2020)"},{"key":"21_CR13","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.chb.2015.02.026","volume":"49","author":"J Hill","year":"2015","unstructured":"Hill, J., Ford, W.R., Farreras, I.G.: Real conversations with artificial intelligence: a comparison between human-human online conversations and human-chatbot conversations. Comput. Hum. Behav. 49, 245\u2013250 (2015)","journal-title":"Comput. Hum. Behav."},{"key":"21_CR14","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021). https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"21_CR15","unstructured":"Hu, S., et\u00a0al.: Minicpm: unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395 (2024)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: CMMLU: measuring massive multitask language understanding in Chinese. arXiv preprint arXiv:2306.09212 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"21_CR17","unstructured":"Ma, Z., et al.: Language model can listen while speaking. arXiv preprint arXiv:2408.02622 (2024)"},{"key":"21_CR18","unstructured":"OpenAI: Introducing chatgpt (2023). https:\/\/openai.com\/blog\/chatgpt#OpenAI"},{"key":"21_CR19","unstructured":"Rozi\u00e8re, B., et al.: Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261100919"},{"key":"21_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101178","volume":"67","author":"G Skantze","year":"2021","unstructured":"Skantze, G.: Turn-taking in conversational systems and human-robot interaction: a review. Comput. Speech Lang. 67, 101178 (2021)","journal-title":"Comput. Speech Lang."},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Suzgun, M., et\u00a0al.: Challenging big-bench tasks and whether chain-of-thought can solve them. In: Findings of the Association for Computational Linguistics, pp. 13003\u201313051 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"21_CR22","unstructured":"Wang, C., et\u00a0al.: Survey on factuality in large language models: knowledge, retrieval and domain-specificity. arXiv preprint arXiv:2310.07521 (2023)"},{"key":"21_CR23","unstructured":"Wang, P., Lu, S., Tang, Y., Yan, S., Xiong, Y., Xia, W.: A full-duplex speech dialogue scheme based on large language models. arXiv preprint arXiv:2405.19487 (2024). https:\/\/arxiv.org\/abs\/2405.19487"},{"key":"21_CR24","unstructured":"Xie, Z., Wu, C.: Mini-omni: language models can hear, talk while thinking in streaming. arXiv preprint arXiv:2408.16725 (2024)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: Hellaswag: can a machine really finish your sentence? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4791\u20134800 (2019)","DOI":"10.18653\/v1\/P19-1472"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Beyond the turn-based game: enabling real-time conversations with duplex models. arXiv preprint arXiv:2406.15718 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.644"},{"key":"21_CR27","unstructured":"Zhao, W.X., et al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"21_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2023.107674","volume":"143","author":"Q Zhou","year":"2023","unstructured":"Zhou, Q., Li, B., Han, L., Jou, M.: Talking to a bot or a wall? How chatbots vs. human agents affect anticipated communication quality. Comput. Hum. Behav. 143, 107674 (2023)","journal-title":"Comput. Hum. Behav."},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, A., Hwang, A., Dugan, L., Callison-Burch, C.: FanOutQA: a multi-hop, multi-document question answering benchmark for large language models. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 18\u201337 (2024). https:\/\/aclanthology.org\/2024.acl-short.2","DOI":"10.18653\/v1\/2024.acl-short.2"}],"container-title":["Lecture Notes in Computer Science","Chinese Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2725-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:20:42Z","timestamp":1761888042000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2725-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819527243","9789819527250"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2725-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China National Conference on Chinese Computational Linguistics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jinan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cncl2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/link.springer.com\/conference\/cncl","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}