{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:04:34Z","timestamp":1784012674591,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234431","type":"print"},{"value":"9789819234448","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3444-8_30","type":"book-chapter","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:16:40Z","timestamp":1784009800000},"page":"354-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Outlier-Aware and Task-Oriented Quantization-Based Low-Rank Adaptation of Large Language Models"],"prefix":"10.1007","author":[{"given":"Chao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"30_CR1","unstructured":"Achiam, J., et al.: Gpt-4 Technical Report. arXiv preprint https:\/\/arxiv.org\/abs\/2303.08774 (2023)"},{"key":"30_CR2","first-page":"7319","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"A Aghajanyan","year":"2021","unstructured":"Aghajanyan, A., Gupta, S., Zettlemoyer, L.: Intrinsic dimensionality explains the effectiveness of language model fine-tuning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 7319\u20137328 (2021)"},{"key":"30_CR3","first-page":"7432","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Y Bisk","year":"2020","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y., et al.: PIQA: reasoning about physical commonsense in natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7432\u20137439 (2020)"},{"key":"30_CR4","unstructured":"Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with Gpt-4. arXiv 2023. arXiv preprint arXiv:2303.12712 10 (2024)"},{"key":"30_CR5","first-page":"2924","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"C Clark","year":"2019","unstructured":"Clark, C., Lee, K., Chang, M.-W., Kwiatkowski, T., Collins, M., Toutanova, K.: BoolQ: exploring the surprising difficulty of natural yes\/no questions. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 2924\u20132936 (2019)"},{"key":"30_CR6","unstructured":"Clark, P., et al.: Think you have solved question answering? Try ARC, the AI2 reasoning challenge. arXiv preprint https:\/\/arxiv.org\/abs\/1803.05457 (2018)"},{"key":"30_CR7","unstructured":"Comanici, G., Bieber, E., Schaekermann, M., Pasupat, I., Sachdeva, N. et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint https:\/\/arxiv.org\/abs\/2507.06261 (2025)"},{"key":"30_CR8","unstructured":"Deng, Y., Zhang, A., Gurses, S., Wang, N., Yang, Z., Yin, P.: CLoQ: enhancing fine-tuning of quantized LLMs via calibrated LoRA initialization. arXiv preprint https:\/\/arxiv.org\/abs\/2501.18475 (2025)"},{"key":"30_CR9","doi-asserted-by":"publisher","first-page":"10088","DOI":"10.52202\/075280-0441","volume":"36","author":"T Dettmers","year":"2023","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient finetuning of quantized LLMs. Adv. Neural Inf. Process. Syst. 36, 10088\u201310115 (2023)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR10","doi-asserted-by":"publisher","first-page":"4475","DOI":"10.52202\/068431-0323","volume":"35","author":"E Frantar","year":"2022","unstructured":"Frantar, E., Alistarh, D.: Optimal brain compression: a framework for accurate post-training quantization and pruning. Adv. Neural Inf. Process. Syst. 35, 4475\u20134488 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR11","volume-title":"The Eleventh International Conference on Learning Representations","author":"E Frantar","year":"2023","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: GPTQ: accurate post-training quantization for generative pre-trained transformers. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"30_CR12","volume-title":"A Framework for Few-Shot Language Model Evaluation","author":"L Gao","year":"2021","unstructured":"Gao, L., et al.: A Framework for Few-Shot Language Model Evaluation. Zenodo (2021)"},{"key":"30_CR13","volume-title":"International Conference on Learning Representations","author":"D Hendrycks","year":"2021","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2021)"},{"key":"30_CR14","volume-title":"International Conference on Learning Representations","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"30_CR15","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.18653\/v1\/2025.acl-long.99","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"H Jeon","year":"2025","unstructured":"Jeon, H., Kim, Y., Kim, J.-J.: L4Q: parameter efficient quantization-aware fine-tuning on large language models. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2002\u20132024 (2025)"},{"key":"30_CR16","doi-asserted-by":"publisher","first-page":"28415","DOI":"10.18653\/v1\/2025.acl-long.1379","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Z Jia","year":"2025","unstructured":"Jia, Z., Wang, A., Qu, X., Yang, X., Wang, J.: Hierarchical-task-aware multi-modal mixture of incremental LoRA experts for embodied continual learning. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 28415\u201328427 (2025)"},{"key":"30_CR17","doi-asserted-by":"publisher","first-page":"36187","DOI":"10.52202\/075280-1569","volume":"36","author":"J Kim","year":"2023","unstructured":"Kim, J., et al.: Memory-efficient fine-tuning of compressed large language models via Sub-4-bit integer quantization. Adv. Neural Inf. Proces. Syst. 36, 36187\u201336207 (2023)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"30_CR18","unstructured":"Kumar, S., Kaloga, Y., Mitros, J., Motlicek, P., Kodrasi, I.: Latent space factorization in LoRA. arXiv preprint https:\/\/arxiv.org\/abs\/2510.19640 (2025)"},{"key":"30_CR19","first-page":"13355","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"C Lee","year":"2024","unstructured":"Lee, C., Jin, J., Kim, T., Kim, H., Park, E.: OWQ: outlier-aware weight quantization for efficient fine-tuning and inference of large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 13355\u201313364 (2024)"},{"key":"30_CR20","first-page":"87","volume-title":"Proceedings of Machine Learning and Systems","author":"J Lin","year":"2024","unstructured":"Lin, J., et al.: AWQ: activation-aware weight quantization for on-device LLM compression and acceleration. In: Proceedings of Machine Learning and Systems, vol. 6, pp. 87\u2013100 (2024)"},{"key":"30_CR21","volume-title":"PEFT: State-of-the-Art Parameter-Efficient Fine-Tuning Methods","author":"S Mangrulkar","year":"2022","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S., Bossan, B.: PEFT: State-of-the-Art Parameter-Efficient Fine-Tuning Methods (2022)"},{"key":"30_CR22","unstructured":"AI at Meta: The Llama 4 herd: the beginning of a new era of natively multimodal AI innovations. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/. 4(7) (2025)"},{"key":"30_CR23","doi-asserted-by":"publisher","first-page":"2381","DOI":"10.18653\/v1\/D18-1260","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"T Mihaylov","year":"2018","unstructured":"Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Can a suit of armor conduct electricity? A new dataset for open book question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2381\u20132391 (2018)"},{"key":"30_CR24","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"30_CR25","unstructured":"Qin, H., et al.: Accurate LoRA-finetuning quantization of LLMs via information retention. arXiv preprint https:\/\/arxiv.org\/abs\/2402.05445 (2024)"},{"issue":"9","key":"30_CR26","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3474381","volume":"64","author":"K Sakaguchi","year":"2021","unstructured":"Sakaguchi, K., Bras, R.L., Bhagavatula, C., Choi, Y.: Winogrande: an adversarial winograd schema challenge at scale. Commun. ACM. 64(9), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"30_CR27","volume-title":"Stanford Alpaca: An Instruction-Following LLaMA Model","author":"R Taori","year":"2023","unstructured":"Taori, R., et al.: Stanford Alpaca: An Instruction-Following LLaMA Model (2023)"},{"key":"30_CR28","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint https:\/\/arxiv.org\/abs\/2302.13971 (2023)"},{"key":"30_CR29","volume-title":"Transactions on Machine Learning Research","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Emergent abilities of large language models. In: Transactions on Machine Learning Research (2022)"},{"key":"30_CR30","first-page":"38087","volume-title":"International Conference on Machine Learning","author":"G Xiao","year":"2023","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning, pp. 38087\u201338099 (2023)"},{"key":"30_CR31","volume-title":"The Twelfth International Conference on Learning Representations","author":"Y Xu","year":"2024","unstructured":"Xu, Y., et al.: QA-LoRA: quantization-aware low-rank adaptation of large language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"30_CR32","unstructured":"Yang, A., et al.: Qwen3 Technical Report. arXiv preprint https:\/\/arxiv.org\/abs\/2505.09388 (2025)"},{"key":"30_CR33","doi-asserted-by":"publisher","first-page":"4791","DOI":"10.18653\/v1\/P19-1472","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"R Zellers","year":"2019","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)"},{"key":"30_CR34","volume-title":"11th International Conference on Learning Representations, ICLR 2023","author":"Q Zhang","year":"2023","unstructured":"Zhang, Q., et al.: Adaptive budget allocation for parameter-efficient fine-tunin. In: 11th International Conference on Learning Representations, ICLR 2023 (2023)"},{"key":"30_CR35","unstructured":"Zhang, Z., et al.: The primacy of magnitude in low-rank adaptation. arXiv preprint arXiv:2507.06558 (2025)"},{"key":"30_CR36","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1145\/3695053.3731412","volume-title":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","author":"C Zhao","year":"2025","unstructured":"Zhao, C., et al.: Insights into DeepSeek-v3: scaling challenges and reflections on hardware for AI architectures. In: Proceedings of the 52nd Annual International Symposium on Computer Architecture, pp. 1731\u20131745 (2025)"},{"key":"30_CR37","doi-asserted-by":"publisher","first-page":"4779","DOI":"10.18653\/v1\/2025.emnlp-main.240","volume-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","author":"J Zhao","year":"2025","unstructured":"Zhao, J., Lu, W., Wang, S., Kong, L., Wu, C.: QSpec: Speculative decoding with complementary quantization schemes. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 4779\u20134795 (2025)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3444-8_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:16:43Z","timestamp":1784009803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3444-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"ISBN":["9789819234431","9789819234448"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3444-8_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"assertion":[{"value":"15 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}