{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:37:19Z","timestamp":1780357039917,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657949","type":"proceedings-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T18:52:02Z","timestamp":1721328722000},"page":"2492-2496","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Large Language Models Based Stemming for Information Retrieval: Promises, Pitfalls and Failures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-5250","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"first","affiliation":[{"name":"The University of Queensland Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6711-0955","authenticated-orcid":false,"given":"Shengyao","family":"Zhuang","sequence":"additional","affiliation":[{"name":"CSIRO, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5563","authenticated-orcid":false,"given":"Guido","family":"Zuccon","sequence":"additional","affiliation":[{"name":"The University of Queensland Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Wolf","author":"Beeching E.","year":"2023","unstructured":"Beeching, E., Fourrier, C., Habib, N., Han, S., Lambert, N., Rajani, N., Sanseviero, O., Tunstall, L., Wolf, T.: Open llm leaderboard. https:\/\/huggingface.co\/spaces\/ HuggingFaceH4\/open_llm_leaderboard (2023)"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531863"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_2_1_5_1","volume-title":"Strohman","author":"Croft B.","year":"2009","unstructured":"Croft, B., Metzler, D., Strohman, T.: Search Engines: Information Retrieval in Practice. Addison-Wesley Publishing Company, USA, 1st edn. (2009)","edition":"1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331303"},{"key":"e_1_3_2_1_7_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Dai Z.","year":"2023","unstructured":"Dai, Z., Zhao, V.Y., Ma, J., Luan, Y., Ni, J., Lu, J., Bakalov, A., Guu, K., Hall, K., Chang, M.W.: Promptagator: Few-shot dense retrieval from 8 examples. In: The Eleventh International Conference on Learning Representations (2023), https: \/\/openreview.net\/forum?id=gmL46YMpu2J"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Dietz F. Petras V.: A component-level analysis of an academic search test collection. part i: system and collection configurations. In: Experimental IR Meets Multilinguality Multimodality and Interaction: 8th International Conference of the CLEF Association CLEF 2017 Dublin Ireland September 11-14 2017 Proceedings 8. pp. 16--28. Springer (2017)","DOI":"10.1007\/978-3-319-65813-1_2"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2301.01820"},{"key":"e_1_3_2_1_12_1","volume-title":"Kim","author":"Kim D.","year":"2023","unstructured":"Kim, D., Park, C., Kim, S., Lee, W., Song, W., Kim, Y., Kim, H., Kim, Y., Lee, H., Kim, J., Ahn, C., Yang, S., Lee, S., Park, H., Gim, G., Cha, M., Lee, H., Kim, S.: Solar 10.7b: Scaling large language models with simple yet effective depth up-scaling (2023)"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tele.2023.102085"},{"key":"e_1_3_2_1_14_1","unstructured":"K\u00f6pf A. Kilcher Y. von R\u00fctte D. Anagnostidis S. Tam Z.R. Stevens K. Barhoum A. Duc N.M. Stanley O. Nagyfi R. et al.: Openassistant conversations-democratizing large language model alignment. arXiv preprint arXiv:2304.07327 (2023)"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/160688.160718"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591633"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_18_1","volume-title":"Lin","author":"Ma X.","year":"2023","unstructured":"Ma, X., Zhang, X., Pradeep, R., Lin, J.: Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156 (2023)"},{"key":"e_1_3_2_1_19_1","volume-title":"Launay","author":"Penedo G.","year":"2023","unstructured":"Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cappelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., Launay, J.: The refined web dataset for falcon llm: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277851"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Porter M.F.: An algorithm for suffix stripping. Programming 14(3) (1980)","DOI":"10.1108\/eb046814"},{"key":"e_1_3_2_1_22_1","unstructured":"Porter M.F.: Snowball: A language for stemming algorithms (2001)"},{"key":"e_1_3_2_1_23_1","volume-title":"Lin","author":"Pradeep R.","year":"2023","unstructured":"Pradeep, R., Sharifymoghaddam, S., Lin, J.: Rankvicuna: Zero-shot listwise document reranking with open-source large language models. arXiv preprint arXiv:2309.15088 (2023)"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Qin Z. Jagerman R. Hui K. Zhuang H. Wu J. Shen J. Liu T. Liu J. Metzler D. Wang X. et al.: Large language models are effective text rankers with pairwise ranking prompting. arXiv preprint arXiv:2306.17563 (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.249"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_29"},{"key":"e_1_3_2_1_27_1","unstructured":"Singhal K. Tu T. Gottweis J. Sayres R. Wulczyn E. Hou L. Clark K. Pfohl S. Cole-Lewis H. Neal D. et al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"e_1_3_2_1_28_1","volume-title":"Ren","author":"Sun W.","year":"2023","unstructured":"Sun, W., Yan, L., Ma, X., Ren, P., Yin, D., Ren, Z.: Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542 (2023)"},{"key":"e_1_3_2_1_29_1","volume-title":"Mitra","author":"Thomas P.","year":"2023","unstructured":"Thomas, P., Spielman, S., Craswell, N., Mitra, B.: Large language models can accurately predict searcher preferences. arXiv preprint arXiv:2309.10621 (2023)"},{"key":"e_1_3_2_1_30_1","unstructured":"Touvron H. Lavril T. Izacard G. Martinet X. Lachaux M.A. Lacroix T. Rozi\u00e8re B. Goyal N. Hambro E. Azhar F. et al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"e_1_3_2_1_31_1","unstructured":"Touvron H. Martin L. Stone K. Albert P. Almahairi A. Babaei Y. Bashlykov N. Batra S. Bhargava P. Bhosale S. et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625322"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591703"},{"key":"e_1_3_2_1_34_1","volume-title":"Chen","author":"Yang C.","year":"2023","unstructured":"Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q.V., Zhou, D., Chen, X.: Large language models as optimizers. arXiv preprint arXiv:2309.03409 (2023)"},{"key":"e_1_3_2_1_35_1","volume-title":"Zuccon","author":"Zhuang S.","year":"2023","unstructured":"Zhuang, S., Shou, L., Zuccon, G.: Augmenting passage representations with query generation for enhanced cross-lingual dense retrieval. arXiv preprint arXiv:2305.03950 (2023)"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Zhuang S. Zhuang H. Koopman B. Zuccon G.: A setwise approach for effective and highly efficient zero-shot ranking with large language models. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 195--204. SIGIR '24 Association for Computing Machinery Association for Computing Machinery New York NY USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657813 https:\/\/doi.org\/10.1145\/3626772.3657813","DOI":"10.1145\/3626772.3657813"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657949","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:37:48Z","timestamp":1755841068000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":36,"alternative-id":["10.1145\/3626772.3657949","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657949","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}