{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T22:33:03Z","timestamp":1758925983342,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031724398"},{"type":"electronic","value":"9783031724404"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72440-4_5","type":"book-chapter","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:01:50Z","timestamp":1727197310000},"page":"51-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Sensitive Topics Retrieval in\u00a0Digital Libraries: A\u00a0Case Study of\u00a0\u1e25ad\u012b\u1e6f collections"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5556-1827","authenticated-orcid":false,"given":"Giovanni","family":"Sullutrone","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4643-6128","authenticated-orcid":false,"given":"Riccardo Amerigo","family":"Vigliermo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-8882","authenticated-orcid":false,"given":"Luca","family":"Sala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-6587","authenticated-orcid":false,"given":"Sonia","family":"Bergamaschi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,25]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. 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). Ed. by Jill Burstein, Christy Doran, and Thamar Solorio. Minneapolis, Minnesota: Association for Computational Linguistics, June 2019, pp. 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"5_CR2","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., et al. (eds.) Advances in Neural Information Processing Systems, vol. 33. Curran Associates, Inc., pp. 1877\u20131901 (2020)"},{"key":"5_CR3","unstructured":"OpenAI: GPT-4 technical report (2024). arXiv: 2303.08774"},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Zhang, Q., et al.: A survey for efficient open domain question answering. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Toronto, Canada: Association for Computational Linguistics, pp. 14447\u201314465 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.808, https:\/\/aclanthology.org\/2023.acl-long.808","DOI":"10.18653\/v1\/2023.acl-long.808"},{"key":"5_CR5","doi-asserted-by":"publisher","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. arXiv:2311.05232 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2311.05232 (visited on 05\/10\/2024). Publisher: [object Object] Version Number: 1","DOI":"10.48550\/ARXIV.2311.05232"},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Xu, Z., Jain, S., Kankanhalli, M.: Hallucination is inevitable: an innate limitation of large language models. arXiv:2401.11817(2024). https:\/\/doi.org\/10.48550\/arXiv.2401.11817. (visited on 05\/10\/2024)","DOI":"10.48550\/arXiv.2401.11817"},{"key":"5_CR7","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR8","doi-asserted-by":"publisher","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arXiv:2312.10997 (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.10997. (visited on 05\/10\/2024)","DOI":"10.48550\/arXiv.2312.10997"},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Gao, L., et al.: Precise zero-shot dense retrieval without relevance labels. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Toronto, Canada: Association for Computational Linguistics, pp. 1762\u20131777 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.99, https:\/\/aclanthology.org\/2023.acl-long.99","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"5_CR10","doi-asserted-by":"publisher","unstructured":"Ma, X., et al.: Query rewriting in retrieval-augmented large language models. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics, pp. 5303\u20135315 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.322, https:\/\/aclanthology.org\/2023.emnlp-main.322","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Liu, T.-Y., et al.: Learning to rank for information retrieval. In: Foundations and Trends\u00ae in Information Retrieval 3.3, pp. 225\u2013331 (2009)","DOI":"10.1561\/1500000016"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"Jones, K.S., Walker, S., Robertson, S.E.: A probabilistic model of information retrieval: development and comparative experiments: Part 2. In: Information Processing Management, vol. 36 (2000), pp. 809\u2013840. https:\/\/doi.org\/10.1016\/S0306-4573(00)00016-9","DOI":"10.1016\/S0306-4573(00)00016-9"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Webber, B., et al. (eds.)Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Online: Association for Computational Linguistics (2020), pp. 6769\u20136781. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.550, https:\/\/aclanthology.org\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"5_CR14","doi-asserted-by":"publisher","unstructured":"Izacard, G., Grave, E.: Leveraging passage retrieval with generative models for open domain question answering. In: Merlo, P., Tiedemann, J., Tsarfaty, R. (eds.)Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Online: Association for Computational Linguistics, pp. 874\u2013880, (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.74, https:\/\/aclanthology.org\/2021.eacl-main.74","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"5_CR15","unstructured":"Wang, L., et al.: Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368 (2023)"},{"key":"5_CR16","unstructured":"Gallegos, I.O., et al.: Bias and fairness in large language models: a survey. arXiv preprint arXiv:2309.00770 (2023)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Mei, K., Fereidooni, S., Caliskan, A.: Bias against 93 stigmatized groups in masked language models and downstream sentiment classification tasks. In: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, pp. 1699\u20131710 (2023)","DOI":"10.1145\/3593013.3594109"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Mozafari, M., Farahbakhsh, R., Crespi, N.: Hate speech detection and racial bias mitigation in social media based on BERT model. PloS one 15(8), e0237861 (2020)","DOI":"10.1371\/journal.pone.0237861"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Rekabsaz, N., Schedl, M.: Do neural ranking models intensify gender bias? In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2065\u20132068 (2020)","DOI":"10.1145\/3397271.3401280"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Rekabsaz, N., Kopeinik, S., Schedl, M.: Societal biases in retrieved contents: measurement framework and adversarial mitigation of BERT rankers. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 306\u2013316 (2021)","DOI":"10.1145\/3404835.3462949"},{"key":"5_CR21","unstructured":"Gallegos, I.O., et al.: Bias and fairness in large language models: a survey. arXiv: 2309.00770 (2024)"},{"key":"5_CR22","doi-asserted-by":"publisher","unstructured":"Bergamaschi, S., et al.: Preserving and conserving culture: first steps towards a knowledge extractor and cataloguer for multilingual and multi-alphabetic heritages. In: Proceedings of the Conference on Information Technology for Social Good. GoodIT 2021. Roma, Italy: Association for Computing Machinery, pp. 301\u2013304 (2021). ISBN: 9781450384780. https:\/\/doi.org\/10.1145\/3462203.3475927, https:\/\/doi.org\/10.1145\/3462203.3475927","DOI":"10.1145\/3462203.3475927"},{"key":"5_CR23","doi-asserted-by":"publisher","unstructured":"Bergamaschi, S., et al.: Novel perspectives for the management of multilingual and multialphabetic heritages through automatic knowledge extraction: the DigitalMaktaba approach. In: Sensors 22.11 (2022). ISSN: 1424\u20138220. https:\/\/doi.org\/10.3390\/s22113995, https:\/\/www.mdpi.com\/1424-8220\/22\/11\/3995","DOI":"10.3390\/s22113995"},{"key":"5_CR24","unstructured":"Martoglia, R., et al.: A tool for semiautomatic cataloguing of an islamic digital library: a use case from the digital Maktaba project. In: Paschke, A., et al. (eds.) Proceedings of the Third Conference on Digital Curation Technologies (Qurator 2022), Berlin, Germany, 19th\u201323rd Sept. 2022, vol. 3234. CEUR Workshop Proceedings. CEUR-WS.org (2022). https:\/\/ceur-ws.org\/Vol-3234\/paper1.pdf"},{"key":"5_CR25","unstructured":"Martoglia, R., et al.: Knowledge extraction, management and longterm preservation of non-Latin cultural heritages - Digital Maktaba project presentation. In:Alessia, B., et al. (eds.) Proceedings of the 19th Conference on Information and Research Science Connecting to Digital and Library Science, vol. 3365. CEUR Workshop Proceedings. ISSN: 1613\u20130073. Bari, Italy: CEUR, pp. 153\u2013161 (2023). https:\/\/ceur-ws.org\/Vol-3365\/#short11 (visited on 09\/14\/2023)"},{"key":"5_CR26","unstructured":"El Ganadi, A., et al.: Bridging Islamic knowledge and AI: inquiring ChatGPT on possible categorizations for an Islamic digital library (full paper). In: 2nd Italian Workshop on Artificial Intelligence for Cultural Heritage, co-located with the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023), vol. 3536. Rome, Italy, pp. 21\u201333 (2023). https:\/\/ai4ch.di.unito.it\/"},{"key":"5_CR27","unstructured":"Ab\u016b al-\u1e24asan A\u1e25mad bin F\u0101rs\u012b Ibn Zakariyy\u0101. Mu$$^c$$\u01e7am maq\u0101y\u012bs \n\n                  \n                 ar. Ed. by $$^{\\rm c}$$A. M. H\u0101r\u016bn. Bayr\u016bt: D\u0101r al-fikr (1979)"},{"key":"5_CR28","unstructured":"Mu\u1e25ammad Murta\u1e0d\u00e0 al-\u1e24useiyn\u012b al-Zubaiyd\u012b. T\u0101\u01e7 al-$$^c$$ar\u016bs min \u01e7awhar al-qa\u016bms. ar. Ed. by \u1e24asan Na\u1e63\u1e63\u0101r. al-tur\u0101th al-$$^{\\rm c}$$arab\u012b. Kuwayt: Ma\u1e6dba$$^{\\rm c}$$a \u1e25uk\u016bma Kuwayt (2001)"},{"key":"5_CR29","unstructured":"Encyclopaedia of Islam new edition online (EI-2 English). https:\/\/referenceworks.brill.com\/display\/db\/eieo (visited on 05\/10\/2024)"},{"key":"5_CR30","unstructured":"Siddiqi, M.Z.: \u1e24ad\u012bth Literature: its origin, development and special features. In: Google-Books-ID: cCnYAAAAMAAJ. Islamic Texts Society (1993). ISBN: 978-0-946621-38-5"},{"key":"5_CR31","unstructured":"Allport, G.W.: Taboo Topics. In: Farberow, N.L. (ed.) Atherton Press, New York (1963). ISBN: 978-1-4128-5236-4"},{"key":"5_CR32","unstructured":"Lee, R.M.: Doing research on sensitive topics. In: Google-Books- ID: AVW_MGH5ZsIC. Sage (1993). ISBN: 978-1-4462-2691-9"},{"key":"5_CR33","doi-asserted-by":"publisher","unstructured":"Dickson-Swift, V., James, E., Liamputtong, P.: Undertaking sensitive research in the health and social sciences: managing boundaries, emotions and risks. Cambridge: Cambridge University Press (2008). ISBN: 978-0-521-71823-3. https:\/\/doi.org\/10.1017\/CBO9780511545481. (Visited on 05\/13\/2024)","DOI":"10.1017\/CBO9780511545481"},{"key":"5_CR34","unstructured":"Touvron, H., et al.: LLama2: open foundation and fine-tuned chat models. arXiv: 2307.09288 (2023)"},{"key":"5_CR35","unstructured":"LLama-3: LLama-3-8B-Instruct 4b-quantized. https:\/\/ai.meta.com\/blog\/meta-llama-3 (visited on 05\/03\/2024)"},{"key":"5_CR36","unstructured":"Lin, S., Hilton, J., Evans, O.: Teaching models to express their uncertainty in words (2022). arXiv: 2205.14334"},{"key":"5_CR37","doi-asserted-by":"publisher","unstructured":"Muennighoff, N., et al.: MTEB: Massive Text Embedding Benchmark. In: arXiv preprint arXiv:2210.07316 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2210.07316","DOI":"10.48550\/ARXIV.2210.07316"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics (2019). https:\/\/arxiv.org\/abs\/1908.10084","DOI":"10.18653\/v1\/D19-1410"},{"key":"5_CR39","unstructured":"Li, Z., et al.: Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)"},{"key":"5_CR40","unstructured":"Wang, L., et al.: Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)"},{"key":"5_CR41","unstructured":"Merrick, L., et al.: Arctic-embed: scalable, efficient, and accurate text embedding models (2024). arXiv: 2405.05374"},{"key":"5_CR42","unstructured":"SFR-Embedding-Mistral: Enhance text retrieval with transfer learning"},{"key":"5_CR43","unstructured":"OpenAI. Embeddings - OpenAI API. https:\/\/platform.openai.com\/docs\/guides\/embeddings (visited on 05\/13\/2024)"}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72440-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:02:31Z","timestamp":1727197351000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72440-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031724398","9783031724404"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72440-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","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":"24 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2024.nuk.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}