{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T14:29:09Z","timestamp":1782829749520,"version":"3.54.5"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819603473","type":"print"},{"value":"9789819603480","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"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\/978-981-96-0348-0_6","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T18:38:45Z","timestamp":1732387125000},"page":"73-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["REFINE on\u00a0Scarce Data: Retrieval Enhancement Through Fine-Tuning via\u00a0Model Fusion of\u00a0Embedding Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4230-1440","authenticated-orcid":false,"given":"Ambuje","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4900-0733","authenticated-orcid":false,"given":"Mrinal","family":"Rawat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9925-905X","authenticated-orcid":false,"given":"Andreas","family":"Stolcke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2608-6184","authenticated-orcid":false,"given":"Roberto","family":"Pieraccini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Aleixo, E.L., Colonna, J.G., Cristo, M., Fernandes, E.: Catastrophic forgetting in deep learning: a comprehensive taxonomy. arXiv:2312.10549 (2023)","DOI":"10.5753\/jbcs.2024.3966"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., Liu, Z.: BGE M3-Embedding: multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv:2309.07597 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Hou, Y., Cui, Y., Che, W., Liu, T., Yu, X.: Recall and Learn: fine-tuning deep pretrained language models with less forgetting. In: Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 7870\u20137881 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.634"},{"key":"6_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) 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. 4171\u20134186. Minneapolis, Minnesota (2019)"},{"key":"6_CR5","unstructured":"Douze, M., et al.: The Faiss library. arXiv:2401.08281 (2024)"},{"key":"6_CR6","unstructured":"FlagOpen: FlagEmbedding: retrieval and retrieval-augmented LLMs. https:\/\/github.com\/FlagOpen\/FlagEmbedding (2024), gitHub repository"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Gilardi, F., Alizadeh, M., Kubli, M.: ChatGPT outperforms crowd workers for text-annotation tasks. In: Proceedings of National Academy of Sciences, vol. 120, issue 30, e2305016120 (2023)","DOI":"10.1073\/pnas.2305016120"},{"key":"6_CR8","unstructured":"Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv:1312.6211 (2015)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: adapt language models to domains and tasks. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of 58th Annual Meeting of the Association for Computational Linguistics, pp. 8342\u20138360 (2020)","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"6_CR10","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1017\/S1351324901002807","volume":"7","author":"L Hirschman","year":"2001","unstructured":"Hirschman, L., Gaizauskas, R.: Natural language question answering: the view from here. Natl. Lang. Eng. 7, 275\u2013300 (2001)","journal-title":"Natl. Lang. Eng."},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, K., Dutta, S., Patel, R., Glava\u0161, G., Gurevych, I.: AdaSent: efficient domain-adapted sentence embeddings for few-shot classification. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of Conference on Empirical Methods in Natural Language Processing, pp. 3420\u20133434 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.208"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Joshi, M., Chen, D., Liu, Y., Weld, D.S., Zettlemoyer, L., Levy, O.: SpanBERT: improving pre-training by representing and predicting spans. arXiv:1907.10529 (2020)","DOI":"10.1162\/tacl_a_00300"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., Yih, W.t.: Dense passage retrieval for open-domain question answering. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"6_CR14","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of 34th International Conference on Neural Information Processing Systems. NIPS \u201920 (2020)"},{"key":"6_CR15","unstructured":"Merrick, L., Xu, D., Nuti, G., Campos, D.: Arctic-Embed: scalable, efficient, and accurate text embedding models. arXiv:2405.05374 (2024)"},{"key":"6_CR16","unstructured":"OpenAI: New embedding models and API updates (2024). https:\/\/openai.com\/index\/new-embedding-models-and-api-updates\/"},{"key":"6_CR17","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022). arXiv:2203.02155"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning (2017). arXiv:1611.07725","DOI":"10.1109\/CVPR.2017.587"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of Conference on Empirical Methods in Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-1410"},{"issue":"4","key":"6_CR20","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1561\/1500000019","volume":"3","author":"S Robertson","year":"2009","unstructured":"Robertson, S., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr. 3(4), 333\u2013389 (2009)","journal-title":"Found. Trends Inf. Retr."},{"key":"6_CR21","unstructured":"Rolnick, D., Ahuja, A., Schwarz, J., Lillicrap, T.P., Wayne, G.: Experience replay for continual learning. arXiv:1811.11682 (2019)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Thakur, N., Reimers, N., Daxenberger, J., Gurevych, I.: Augmented SBERT: data augmentation method for improving bi-encoders for pairwise sentence scoring tasks. In: Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 296\u2013310 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.28"},{"key":"6_CR23","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv:2307.09288 (2023)"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Voorhees, E.M., Tice, D.M.: The TREC-8 question answering track. In: Gavrilidou, M., Carayannis, G., Markantonatou, S., Piperidis, S., Stainhauer, G. (eds.) Proceedings of 2nd International Conference on Language Resources and Evaluation (LREC\u201900). European Language Resources Association (ELRA), Athens, Greece (2000)","DOI":"10.6028\/NIST.SP.500-246.qa-overview"},{"key":"6_CR25","unstructured":"Wu, M., Cao, S.: LLM-augmented retrieval: enhancing retrieval models through language models and doc-level embedding. arXiv:2404.05825 (2024)"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N.: C-Pack: packaged resources to advance general Chinese embedding. arXiv:2309.07597 (2024)","DOI":"10.1145\/3626772.3657878"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Xing, X.: LM-Cocktail: resilient tuning of language models via model merging. arXiv:2311.13534 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.145"},{"key":"6_CR28","unstructured":"Xu, Z., Jain, S., Kankanhalli, M.: Hallucination is inevitable: an innate limitation of large language models. arXiv:2401.11817 (2024)"}],"container-title":["Lecture Notes in Computer Science","AI 2024: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0348-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:03:10Z","timestamp":1732388590000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0348-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"ISBN":["9789819603473","9789819603480"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0348-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"18 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2024.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}