{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:42:14Z","timestamp":1773247334205,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"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":[[2024,10,21]]},"DOI":"10.1145\/3627673.3680093","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"4349-4357","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Leveraging Large Language Models for Improving Keyphrase Generation for Contextual Targeting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7491-2454","authenticated-orcid":false,"given":"Xiao","family":"Bai","sequence":"first","affiliation":[{"name":"Yahoo Research, Mountain View, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1091-3805","authenticated-orcid":false,"given":"Xue","family":"Wu","sequence":"additional","affiliation":[{"name":"Yahoo Research, Mountain View, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5957-7395","authenticated-orcid":false,"given":"Ivan","family":"Stojkovic","sequence":"additional","affiliation":[{"name":"Zmaitech, Hayward, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2505-653X","authenticated-orcid":false,"given":"Kostas","family":"Tsioutsiouliklis","sequence":"additional","affiliation":[{"name":"Yahoo Research, Mountain View, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_2_1","volume-title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. arxiv: 2305.13245 [cs.CL]","author":"Ainslie Joshua","year":"2023","unstructured":"Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebr\u00f3n, and Sumit Sanghai. 2023. GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. arxiv: 2305.13245 [cs.CL]"},{"key":"e_1_3_2_1_3_1","unstructured":"Ebtesam Almazrouei Hamza Alobeidli Abdulaziz Alshamsi Alessandro Cappelli Ruxandra Cojocaru M\u00e9rouane Debbah \u00c9tienne Goffinet Daniel Hesslow Julien Launay Quentin Malartic et al. 2023. The falcon series of open language models. arXiv preprint arXiv:2311.16867 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557129"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML'20)","author":"Bao Hangbo","year":"2020","unstructured":"Hangbo Bao, Li Dong, Furu Wei, Wenhui Wang, Nan Yang, Xiaodong Liu, Yu Wang, Songhao Piao, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2020. UNILMv2: pseudo-masked language models for unified language model pre-training. In Proceedings of the 37th International Conference on Machine Learning (ICML'20). JMLR.org, Article 60, 11 pages."},{"key":"e_1_3_2_1_6_1","volume-title":"Longformer: The Long-Document Transformer. CoRR","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The Long-Document Transformer. CoRR, Vol. abs\/2004.05150 (2020). showeprint[arXiv]2004.05150 https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of 5th International Joint Conference on Natural Language Processing, Haifeng Wang and David Yarowsky (Eds.). Asian Federation of Natural Language Processing","author":"Berend G\u00e1bor","year":"2011","unstructured":"G\u00e1bor Berend. 2011. Opinion Expression Mining by Exploiting Keyphrase Extraction. In Proceedings of 5th International Joint Conference on Natural Language Processing, Haifeng Wang and David Yarowsky (Eds.). Asian Federation of Natural Language Processing, Chiang Mai, Thailand, 1162--1170. https:\/\/aclanthology.org\/I11--1130"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_9_1","volume-title":"Topicrank: Graph-based topic ranking for keyphrase extraction. In International joint conference on natural language processing (IJCNLP). 543--551.","author":"Bougouin Adrien","year":"2013","unstructured":"Adrien Bougouin, Florian Boudin, and B\u00e9atrice Daille. 2013. Topicrank: Graph-based topic ranking for keyphrase extraction. In International joint conference on natural language processing (IJCNLP). 543--551."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277837"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.09.013"},{"key":"e_1_3_2_1_12_1","unstructured":"Erion cCano and Ondvrej Bojar. 2020. Two Huge Title and Keyword Generation Corpora of Research Articles. In Proceedings of the Twelfth Language Resources and Evaluation Conference Nicoletta Calzolari Fr\u00e9d\u00e9ric B\u00e9chet Philippe Blache Khalid Choukri Christopher Cieri Thierry Declerck Sara Goggi Hitoshi Isahara Bente Maegaard Joseph Mariani H\u00e9l\u00e8ne Mazo Asuncion Moreno Jan Odijk and Stelios Piperidis (Eds.). European Language Resources Association Marseille France 6663--6671. https:\/\/aclanthology.org\/2020.lrec-1.823"},{"key":"e_1_3_2_1_13_1","volume-title":"The power of noise: Redefining retrieval for rag systems. arXiv preprint arXiv:2401.14887","author":"Cuconasu Florin","year":"2024","unstructured":"Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, and Fabrizio Silvestri. 2024. The power of noise: Redefining retrieval for rag systems. arXiv preprint arXiv:2401.14887 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_15_1","volume-title":"A survey of data augmentation approaches for NLP. arXiv preprint arXiv:2105.03075","author":"Feng Steven Y","year":"2021","unstructured":"Steven Y Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021. A survey of data augmentation approaches for NLP. arXiv preprint arXiv:2105.03075 (2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592067"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-8617"},{"key":"e_1_3_2_1_18_1","unstructured":"Maarten Grootendorst. 2020. KeyBERT: Minimal keyword extraction with BERT."},{"key":"e_1_3_2_1_19_1","unstructured":"Maarten Grootendorst. 2023. KeyLLM: A minimal method for keyword extraction with Large Language Models."},{"key":"e_1_3_2_1_20_1","volume-title":"Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al.","author":"Gunasekar Suriya","year":"2023","unstructured":"Suriya Gunasekar, Yi Zhang, Jyoti Aneja, Caio C\u00e9sar Teodoro Mendes, Allie Del Giorno, Sivakanth Gopi, Mojan Javaheripi, Piero Kauffmann, Gustavo de Rosa, Olli Saarikivi, et al. 2023. Textbooks are all you need. arXiv preprint arXiv:2306.11644 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Kamel","author":"Hammouda Khaled M.","year":"2005","unstructured":"Khaled M. Hammouda, Diego N. Matute, and Mohamed S. Kamel. 2005. CorePhrase: Keyphrase Extraction for Document Clustering. In Machine Learning and Data Mining in Pattern Recognition, Petra Perner and Atsushi Imiya (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 265--274."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IATW.2007.46"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1119"},{"key":"e_1_3_2_1_24_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_25_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. CoRR","author":"Hu Edward J.","year":"2021","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. CoRR, Vol. abs\/2106.09685 (2021). showeprint[arXiv]2106.09685 https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119355.1119383"},{"key":"e_1_3_2_1_27_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12224560"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581754.3584126"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Mike Lewis Yinhan Liu Naman Goyal Marjan Ghazvininejad Abdelrahman Mohamed Omer Levy Veselin Stoyanov and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation Translation and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Dan Jurafsky Joyce Chai Natalie Schluter and Joel Tetreault (Eds.). Association for Computational Linguistics Online 7871--7880. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11859-007-0038-4"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120587"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380232"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_35_1","volume-title":"Scientific Information Extraction with Semi-supervised Neural Tagging. CoRR","author":"Luan Yi","year":"2017","unstructured":"Yi Luan, Mari Ostendorf, and Hannaneh Hajishirzi. 2017. Scientific Information Extraction with Semi-supervised Neural Tagging. CoRR, Vol. abs\/1708.06075 (2017). showeprint[arXiv]1708.06075 http:\/\/arxiv.org\/abs\/1708.06075"},{"key":"e_1_3_2_1_36_1","volume-title":"LLM-TAKE: Theme-Aware Keyword Extraction Using Large Language Models. In 2023 IEEE International Conference on Big Data (BigData). IEEE, 4318--4324","author":"Maragheh Reza Yousefi","year":"2023","unstructured":"Reza Yousefi Maragheh, Chenhao Fang, Charan Chand Irugu, Parth Parikh, Jason Cho, Jianpeng Xu, Saranyan Sukumar, Malay Patel, Evren Korpeoglu, Sushant Kumar, et al. 2023. LLM-TAKE: Theme-Aware Keyword Extraction Using Large Language Models. In 2023 IEEE International Conference on Big Data (BigData). IEEE, 4318--4324."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1054"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 2004 conference on empirical methods in natural language processing. 404--411","author":"Mihalcea Rada","year":"2004","unstructured":"Rada Mihalcea and Paul Tarau. 2004. Textrank: Bringing order into text. In Proceedings of the 2004 conference on empirical methods in natural language processing. 404--411."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_40_1","unstructured":"Guilherme Penedo Quentin Malartic Daniel Hesslow Ruxandra Cojocaru Alessandro Cappelli Hamza Alobeidli Baptiste Pannier Ebtesam Almazrouei and Julien Launay. 2023. The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data and Web Data Only. arxiv: 2306.01116 [cs.CL]"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2350716.2350728"},{"key":"e_1_3_2_1_42_1","volume-title":"Liu","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. CoRR, Vol. abs\/1910.10683 (2019). showeprint[arXiv]1910.10683 http:\/\/arxiv.org\/abs\/1910.10683"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"e_1_3_2_1_44_1","volume-title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. CoRR","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. CoRR, Vol. abs\/1908.10084 (2019). showeprint[arXiv]1908.10084 http:\/\/arxiv.org\/abs\/1908.10084"},{"key":"e_1_3_2_1_45_1","volume-title":"Automatic keyword extraction from individual documents. Text mining: applications and theory","author":"Rose Stuart","year":"2010","unstructured":"Stuart Rose, Dave Engel, Nick Cramer, and Wendy Cowley. 2010. Automatic keyword extraction from individual documents. Text mining: applications and theory (2010), 1--20."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132934"},{"key":"e_1_3_2_1_47_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Learning algorithms for keyphrase extraction. Information retrieval","author":"Turney Peter D","year":"2000","unstructured":"Peter D Turney. 2000. Learning algorithms for keyphrase extraction. Information retrieval, Vol. 2 (2000), 303--336."},{"key":"e_1_3_2_1_49_1","volume-title":"2023 IEEE International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT). IEEE, 357--361","author":"V\u00f6r\u00f6s Tam\u00e1s","year":"2023","unstructured":"Tam\u00e1s V\u00f6r\u00f6s, Sean Paul Bergeron, and Konstantin Berlin. 2023. Web content filtering through knowledge distillation of large language models. In 2023 IEEE International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT). IEEE, 357--361."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"e_1_3_2_1_51_1","volume-title":"One-step Reach: LLM-based Keyword Generation for Sponsored Search Advertising. In Companion Proceedings of the ACM on Web Conference","author":"Wang Yang","year":"2024","unstructured":"Yang Wang, Zheyi Sha, Kunhai Lin, Chaobing Feng, Kunhong Zhu, Lipeng Wang, Xuewu Jiao, Fei Huang, Chao Ye, Dengwu He, et al. 2024. One-step Reach: LLM-based Keyword Generation for Sponsored Search Advertising. In Companion Proceedings of the ACM on Web Conference 2024. 1604--1608."},{"key":"e_1_3_2_1_52_1","volume-title":"Nevill-Manning","author":"Witten Ian H.","year":"1999","unstructured":"Ian H. Witten, Gordon W. Paynter, Eibe Frank, Carl Gutwin, and Craig G. Nevill-Manning. 1999. KEA: Practical Automatic Keyphrase Extraction. arxiv: cs\/9902007 [cs.DL]"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_54_1","volume-title":"Wasi Uddin Ahmad, and Kai-Wei Chang","author":"Wu Di","year":"2022","unstructured":"Di Wu, Wasi Uddin Ahmad, and Kai-Wei Chang. 2022. Pre-trained language models for keyphrase generation: A thorough empirical study. arXiv preprint arXiv:2212.10233 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367723"},{"key":"e_1_3_2_1_56_1","volume-title":"A survey on knowledge distillation of large language models. arXiv preprint arXiv:2402.13116","author":"Xu Xiaohan","year":"2024","unstructured":"Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. 2024. A survey on knowledge distillation of large language models. arXiv preprint arXiv:2402.13116 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539189"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1080"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680093","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3680093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:18Z","timestamp":1750294698000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3680093"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":60,"alternative-id":["10.1145\/3627673.3680093","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3680093","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}