{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T14:44:55Z","timestamp":1769093095204,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819605729","type":"print"},{"value":"9789819605736","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0573-6_12","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:12:32Z","timestamp":1732608752000},"page":"161-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deconfounded Causality-Aware Parameter-Efficient Fine-Tuning for\u00a0Problem-Solving Improvement of\u00a0LLMs"],"prefix":"10.1007","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiaoxuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Besta, M., Blach, N., Kubicek, A., et\u00a0al.: Graph of thoughts: Solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687 (2023)","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"12_CR2","unstructured":"Chiang, W.L., Li, Z., Lin, Z., Sheng, Y., et\u00a0al.: Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality. https:\/\/vicuna.lmsys.org (2023)"},{"key":"12_CR3","unstructured":"Edalati, A., Tahaei, M., Kobyzev, I., Nia, V.P., et\u00a0al.: KronA: Parameter efficient tuning with kronecker adapter. arXiv preprint arXiv:2212.10650 (2022)"},{"key":"12_CR4","unstructured":"Geng, X., et al.: Koala: A dialogue model for academic research. Blog post, April 1 (2023)"},{"key":"12_CR5","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Hosseini, M.J., Hajishirzi, H., Etzioni, O., Kushman, N.: Learning to solve arithmetic word problems with verb categorization. In: EMNLP, pp. 523\u2013533 (2014)","DOI":"10.3115\/v1\/D14-1058"},{"key":"12_CR7","unstructured":"Houlsby, N., Giurgiu, A., Jastrzebski, S., Morrone, B., et\u00a0al.: Parameter-efficient transfer learning for NLP. In: ICML, pp. 2790\u20132799. PMLR (2019)"},{"key":"12_CR8","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., et\u00a0al.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Z., Lan, Y., et\u00a0al.: LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"12_CR10","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"12_CR11","unstructured":"Jin, Z., Liu, J., Lyu, Z., Poff, Spencer\u00a0Sch\u00f6lkopf, B., et\u00a0al.: Can large language models infer causation from correlation? arXiv preprint arXiv:2306.05836 (2023)"},{"key":"12_CR12","unstructured":"Kocaoglu, M., Snyder, C., et\u00a0al.: CausalGAN: Learning causal implicit generative models with adversarial training. arXiv preprint arXiv:1709.02023 (2017)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"12_CR15","unstructured":"Li, Y., Yu, Y., Liang, C., He, P., et\u00a0al.: LoftQ: Lora-fine-tuning-aware quantization for large language models. arXiv preprint arXiv:2310.08659 (2023)"},{"key":"12_CR16","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., et\u00a0al.: PEFT: State-of-the-art parameter-efficient fine-tuning methods. https:\/\/github.com\/huggingface\/peft (2022)"},{"key":"12_CR17","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"12_CR18","unstructured":"Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., Vuli\u0107, I., Gurevych, I., Ruder, S.: MAD-X: An adapter-based framework for multi-task cross-lingual transfer. arXiv preprint arXiv:2005.00052 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Qiao, S., Ou, Y., Zhang, N., Chen, X., Yao, Y., Deng, S., et\u00a0al.: Reasoning with language model prompting: A survey. arXiv preprint arXiv:2212.09597 (2022)","DOI":"10.18653\/v1\/2023.acl-long.294"},{"key":"12_CR21","unstructured":"Schaeffer, R., Miranda, B., Koyejo, S.: Are emergent abilities of large language models a mirage? arXiv preprint arXiv:2304.15004 (2023)"},{"key":"12_CR22","unstructured":"Shen, X., Liu, F., Dong, H., Lian, Q., et\u00a0al.: Weakly supervised disentangled generative causal representation learning. JMLR 23(1), 10994\u201311048 (2022)"},{"key":"12_CR23","unstructured":"Srivastava, A., et\u00a0al.: Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)"},{"key":"12_CR24","unstructured":"Tang, K., Huang, J., Zhang, H.: Long-tailed classification by keeping the good and removing the bad momentum causal effect. NeurIPS 33, 1513\u20131524 (2020)"},{"key":"12_CR25","unstructured":"Taori, R., et al.: Stanford alpaca: An instruction-following llama model (2023)"},{"key":"12_CR26","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., et\u00a0al.: LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"12_CR27","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"12_CR28","unstructured":"Vig, J.: BertViz: A tool for visualizing multihead self-attention in the BERT model. In: ICLR Workshop: Debugging Machine Learning Models. vol.\u00a023 (2019)"},{"key":"12_CR29","unstructured":"Wei, J., et\u00a0al.: Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)"},{"key":"12_CR30","unstructured":"Wei, J., et\u00a0al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 24824\u201324837 (2022)"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Xu, C., Guo, D., et\u00a0al.: Baize: An open-source chat model with parameter-efficient tuning on self-chat data. arXiv preprint arXiv:2304.01196 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.385"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Yang, M., Liu, F., Chen, Z., Shen, X., et\u00a0al.: CausalVAE: disentangled representation learning via neural structural causal models. In: CVPR, pp. 9593\u20139602 (2021)","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"12_CR33","unstructured":"Yao, S., Yu, D., Zhao, J., Shafran, I., et\u00a0al.: Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023)"},{"key":"12_CR34","unstructured":"Yuan, Z., Yuan, H., Tan, C., Wang, W., Huang, S.: How well do large language models perform in arithmetic tasks? (2023)"},{"key":"12_CR35","unstructured":"Yue, Z., Zhang, H., Sun, Q., Hua, X.S.: Interventional few-shot learning. Adv. Neural Inf. Process. Syst. 33, 2734\u20132746 (2020)"},{"key":"12_CR36","unstructured":"Zhang, Q., Chen, M., Bukharin, A., He, P., et\u00a0al.: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512 (2023)"},{"key":"12_CR37","unstructured":"Zhang, R., Han, J., Zhou, A., Hu, X., et\u00a0al.: LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"12_CR38","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"}],"container-title":["Lecture Notes in Computer Science","Web Information Systems Engineering \u2013 WISE 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0573-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T08:45:24Z","timestamp":1732610724000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0573-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9789819605729","9789819605736"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0573-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WISE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Web Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Doha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Qatar","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wise2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/wise2024-qatar.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}