{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:40:29Z","timestamp":1773157229449,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T00:00:00Z","timestamp":1729555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology Project of Chengdu","award":["2023-JB00-00020-GX"],"award-info":[{"award-number":["2023-JB00-00020-GX"]}]},{"DOI":"10.13039\/100012542","name":"Sichuan Province Science and Technology Support Program","doi-asserted-by":"publisher","award":["2023YFS0424"],"award-info":[{"award-number":["2023YFS0424"]}],"id":[{"id":"10.13039\/100012542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06499-7","type":"journal-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T05:02:24Z","timestamp":1729573344000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Enhancing Chinese comprehension and reasoning for large language models: an efficient LoRA fine-tuning and tree of thoughts framework"],"prefix":"10.1007","volume":"81","author":[{"given":"Songlin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Weicheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaoliang","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Maolin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Peng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Xianyong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yajun","family":"Du","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,22]]},"reference":[{"key":"6499_CR1","unstructured":"Brown T, Mann B, Ryder N, et\u00a0al (2020) Language models are few-shot learners. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"issue":"240","key":"6499_CR2","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery A, Narang S, Devlin J et al (2023) Palm: scaling language modeling with pathways. J Mach Learn Res 24(240):1\u201313","journal-title":"J Mach Learn Res"},{"key":"6499_CR3","unstructured":"Vaswani A, Shazeer N, Parmar N, et\u00a0al (2017) Attention is all you need. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp 5998\u20136008, https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"6499_CR4","unstructured":"Hoffmann J, Borgeaud S, Mensch A, et\u00a0al (2024) Training compute-optimal large language models. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS \u201922"},{"key":"6499_CR5","doi-asserted-by":"publisher","unstructured":"Wu Q, Zhang Q, Wei Z, et\u00a0al (2021) Math word problem solving with explicit numerical values. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021. Association for Computational Linguistics, pp 5859\u20135869, https:\/\/doi.org\/10.18653\/V1\/2021.ACL-LONG.455","DOI":"10.18653\/V1\/2021.ACL-LONG.455"},{"key":"6499_CR6","doi-asserted-by":"publisher","unstructured":"Touvron H, Lavril T, Izacard G, et\u00a0al (2023) Llama: Open and efficient foundation language models. CoRR arXiv:abs\/2302.13971. https:\/\/doi.org\/10.48550\/ARXIV.2302.13971","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"6499_CR7","unstructured":"Taori R, Gulrajani I, Zhang T (2023) Stanford alpaca: An instruction-following llama model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"6499_CR8","unstructured":"Chiang WL, Li Z, Lin Z, et\u00a0al (2023) Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"6499_CR9","unstructured":"Hu EJ, Shen Y, Wallis P, et\u00a0al (2022) Lora: Low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net, https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"6499_CR10","unstructured":"Yao S, Yu D, Zhao J, et\u00a0al (2024) Tree of thoughts: deliberate problem solving with large language models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, NIPS \u201923"},{"key":"6499_CR11","unstructured":"Newell A, Shaw JC, Simon HA (1959) Report on a general problem-solving program. In: Information Processing, Proceedings of the 1st International Conference on Information Processing, UNESCO, Paris 15-20 June 1959. UNESCO (Paris), pp 256\u2013264"},{"key":"6499_CR12","volume-title":"Human problem solving","author":"A Newell","year":"1972","unstructured":"Newell A, Simon HA et al (1972) Human problem solving, vol 104. Prentice-hall Englewood Cliffs, NJ"},{"key":"6499_CR13","unstructured":"Lambert N, Castricato L, von Werra L, et\u00a0al (2022) Illustrating reinforcement learning from human feedback (rlhf). Hugging Face Blog https:\/\/huggingface.co\/blog\/rlhf"},{"key":"6499_CR14","doi-asserted-by":"publisher","unstructured":"Li XL, Liang P (2021) Prefix-tuning: Optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), pp 4582\u20134597, https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"6499_CR15","doi-asserted-by":"publisher","unstructured":"Lester B, Al-Rfou R, Constant N (2021) The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event \/ Punta Cana, Dominican Republic, 7-11 November, 2021. Association for Computational Linguistics, pp 3045\u20133059, https:\/\/doi.org\/10.18653\/V1\/2021.EMNLP-MAIN.243","DOI":"10.18653\/V1\/2021.EMNLP-MAIN.243"},{"key":"6499_CR16","doi-asserted-by":"publisher","unstructured":"Hambardzumyan K, Khachatrian H, May J (2021) WARP: word-level adversarial reprogramming. In: Zong C, Xia F, Li W, et\u00a0al (eds) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1\u20136, 2021. Association for Computational Linguistics, pp 4921\u20134933, https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.381","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"6499_CR17","doi-asserted-by":"crossref","unstructured":"Liu X, Zheng Y, Du Z, et\u00a0al (2023) Gpt understands, too. AI Open","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"6499_CR18","unstructured":"Li C, Farkhoor H, Liu R, et\u00a0al (2018) Measuring the intrinsic dimension of objective landscapes. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, https:\/\/openreview.net\/forum?id=ryup8-WCW"},{"issue":"2","key":"6499_CR19","first-page":"264","volume":"57","author":"R Zhao","year":"2020","unstructured":"Zhao R, Xiong X, Ju S et al (2020) Implicit sentiment analysis for Chinese texts based on a hybrid neural network. J Sichuan Univ (Nat Sci Ed) 57(2):264\u2013270","journal-title":"J Sichuan Univ (Nat Sci Ed)"},{"key":"6499_CR20","doi-asserted-by":"publisher","unstructured":"Paranjape B, Michael J, Ghazvininejad M, et\u00a0al (2021) Prompting contrastive explanations for commonsense reasoning tasks. In: Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event, August 1-6, 2021, Findings of ACL, vol ACL\/IJCNLP 2021. Association for Computational Linguistics, pp 4179\u20134192, https:\/\/doi.org\/10.18653\/V1\/2021.FINDINGS-ACL.366","DOI":"10.18653\/V1\/2021.FINDINGS-ACL.366"},{"key":"6499_CR21","doi-asserted-by":"publisher","unstructured":"Liu J, Liu A, Lu X, et\u00a0al (2022) Generated knowledge prompting for commonsense reasoning. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. Association for Computational Linguistics, pp 3154\u20133169, https:\/\/doi.org\/10.18653\/V1\/2022.ACL-LONG.225","DOI":"10.18653\/V1\/2022.ACL-LONG.225"},{"key":"6499_CR22","unstructured":"Li Y, Liang Y, Risteski A (2016) Recovery guarantee of weighted low-rank approximation via alternating minimization. In: Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, JMLR Workshop and Conference Proceedings, vol\u00a048. JMLR.org, pp 2358\u20132367, URL: proceedings.mlr.press\/v48\/lii16.html"},{"issue":"4","key":"6499_CR23","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1137\/080738970","volume":"20","author":"JF Cai","year":"2010","unstructured":"Cai JF, Cand\u00e8s EJ, Shen Z (2010) A singular value thresholding algorithm for matrix completion. SIAM J Optim 20(4):1956\u20131982. https:\/\/doi.org\/10.1137\/080738970","journal-title":"SIAM J Optim"},{"key":"6499_CR24","unstructured":"Li Y, Ma T, Zhang H (2018) Algorithmic regularization in over-parameterized matrix sensing and neural networks with quadratic activations. In: Conference On Learning Theory, COLT 2018, Stockholm, Sweden, 6-9 July 2018, Proceedings of Machine Learning Research, vol\u00a075. PMLR, pp 2\u201347, URL: proceedings.mlr.press\/v75\/li18a.html"},{"issue":"1","key":"6499_CR25","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1002\/gamm.201310004","volume":"36","author":"L Grasedyck","year":"2013","unstructured":"Grasedyck L, Kressner D, Tobler C (2013) A literature survey of low-rank tensor approximation techniques. GAMM-Mitt 36(1):53\u201378","journal-title":"GAMM-Mitt"},{"key":"6499_CR26","unstructured":"Oymak S, Fabian Z, Li M, et\u00a0al (2019) Generalization guarantees for neural networks via harnessing the low-rank structure of the jacobian. CoRR arXiv:abs\/1906.05392"},{"key":"6499_CR27","doi-asserted-by":"publisher","unstructured":"Sainath TN, Kingsbury B, Sindhwani V, et\u00a0al (2013) Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In: 2013 IEEE international conference on acoustics, speech and signal processing. IEEE, pp 6655\u20136659, https:\/\/doi.org\/10.1109\/ICASSP.2013.6638949","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"6499_CR28","doi-asserted-by":"publisher","unstructured":"Povey D, Cheng G, Wang Y, et\u00a0al (2018) Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018. ISCA, pp 3743\u20133747, https:\/\/doi.org\/10.21437\/INTERSPEECH.2018-1417","DOI":"10.21437\/INTERSPEECH.2018-1417"},{"key":"6499_CR29","doi-asserted-by":"publisher","unstructured":"Zhang Y, Chuangsuwanich E, Glass J (2014) Extracting deep neural network bottleneck features using low-rank matrix factorization. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2014, Florence, Italy, May 4-9, 2014. IEEE, pp 185\u2013189, https:\/\/doi.org\/10.1109\/ICASSP.2014.6853583","DOI":"10.1109\/ICASSP.2014.6853583"},{"key":"6499_CR30","doi-asserted-by":"publisher","unstructured":"Zhao Y, Li J, Gong Y (2016) Low-rank plus diagonal adaptation for deep neural networks. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016. IEEE, pp 5005\u20135009, https:\/\/doi.org\/10.1109\/ICASSP.2016.7472630","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"6499_CR31","unstructured":"Khodak M, Tenenholtz NA, Mackey L, et\u00a0al (2021) Initialization and regularization of factorized neural layers. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, https:\/\/openreview.net\/forum?id=KTlJT1nof6d"},{"key":"6499_CR32","unstructured":"Denil M, Shakibi B, Dinh L, et\u00a0al (2013) Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States, pp 2148\u20132156, https:\/\/proceedings.neurips.cc\/paper\/2013\/hash\/7fec306d1e665bc9c748b5d2b99a6e97-Abstract.html"},{"key":"6499_CR33","unstructured":"Paul D, Ismayilzada M, Peyrard M, et\u00a0al (2024) REFINER: Reasoning feedback on intermediate representations. In: Graham Y, Purver M (eds) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, St. Julian\u2019s, Malta, pp 1100\u20131126, https:\/\/aclanthology.org\/2024.eacl-long.67"},{"key":"6499_CR34","unstructured":"Anonymous (2023) Tonggu: Mastering classical chinese understanding with knowledge-grounded large language models. arXiv preprint arXiv:2407.03937https:\/\/ar5iv.labs.arxiv.org\/html\/2407.03937"},{"key":"6499_CR35","doi-asserted-by":"publisher","unstructured":"Cui Y, Che W, Liu T, et\u00a0al (2020) Revisiting pre-trained models for chinese natural language processing. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp 657\u2013668, https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.58, https:\/\/aclanthology.org\/2020.findings-emnlp.58","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"issue":"70","key":"6499_CR36","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung HW, Hou L, Longpre S et al (2024) Scaling instruction-finetuned language models. J Mach Learn Res 25(70):1\u201353","journal-title":"J Mach Learn Res"},{"key":"6499_CR37","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1162\/tacl_a_00305","volume":"8","author":"K Sun","year":"2020","unstructured":"Sun K, Yu D, Yu D et al (2020) Investigating prior knowledge for challenging Chinese machine reading comprehension. Trans Assoc Comput Linguist 8:141\u2013155","journal-title":"Trans Assoc Comput Linguist"},{"key":"6499_CR38","doi-asserted-by":"publisher","unstructured":"Ji Y, Deng Y, Gong Y, et\u00a0al (2023) Exploring the impact of instruction data scaling on large language models: An empirical study on real-world use cases. CoRR abs\/2303.14742. https:\/\/doi.org\/10.48550\/ARXIV.2303.14742","DOI":"10.48550\/ARXIV.2303.14742"},{"key":"6499_CR39","doi-asserted-by":"publisher","unstructured":"Du Z, Qian Y, et\u00a0al XL (2022) Glm: General language model pretraining with autoregressive blank infilling. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. Association for Computational Linguistics, pp 320\u2013335, https:\/\/doi.org\/10.18653\/V1\/2022.ACL-LONG.26","DOI":"10.18653\/V1\/2022.ACL-LONG.26"},{"key":"6499_CR40","unstructured":"(2023) Moss. https:\/\/moss.fastnlp.top\/"},{"key":"6499_CR41","unstructured":"Li Z (2023) Billa: A bilingual llama with enhanced reasoning ability. https:\/\/github.com\/Neutralzz\/BiLLa"},{"key":"6499_CR42","unstructured":"Chen Z, Chen J, Zhang H (2023) Llm zoo: democratizing chatgpt. https:\/\/github.com\/FreedomIntelligence\/LLMZoo"},{"key":"6499_CR43","unstructured":"Yang J (2023) Firefly(). https:\/\/github.com\/yangjianxin1\/Firefly"},{"key":"6499_CR44","unstructured":"(2023) Chinese idioms natural language inference dataset. https:\/\/openi.pcl.ac.cn\/ZhangbuDong\/CINLID\/datasetsa"},{"key":"6499_CR45","doi-asserted-by":"publisher","unstructured":"Hu B, Chen Q, Zhu F (2015) Lcsts: A large scale chinese short text summarization dataset. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015. The Association for Computational Linguistics, pp 1967\u20131972, https:\/\/doi.org\/10.18653\/V1\/D15-1229","DOI":"10.18653\/V1\/D15-1229"},{"key":"6499_CR46","doi-asserted-by":"publisher","unstructured":"Shao Z, Huang M, Wen J, et\u00a0al (2019) Long and diverse text generation with planning-based hierarchical variational model. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019. Association for Computational Linguistics, pp 3255\u20133266, https:\/\/doi.org\/10.18653\/V1\/D19-1321","DOI":"10.18653\/V1\/D19-1321"},{"key":"6499_CR47","unstructured":"(2021) Smp2021-ecisa. https:\/\/github.com\/sxu-nlp\/ECISA2021"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06499-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06499-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06499-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T05:11:31Z","timestamp":1729573891000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06499-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,22]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6499"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06499-7","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,22]]},"assertion":[{"value":"2 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"50"}}