{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T23:41:34Z","timestamp":1774309294084,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/S02266X\/1"],"award-info":[{"award-number":["EP\/S02266X\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3748149","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:48:44Z","timestamp":1757155724000},"page":"755-763","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Fashion-AlterEval: A Dataset for Improved Evaluation of Conversational Recommendation Systems with Alternative Relevant Items"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8685-693X","authenticated-orcid":false,"given":"Maria","family":"Vlachou","sequence":"first","affiliation":[{"name":"University of Glasgow, Glasgow, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"DESIRES","author":"Balog Krisztian","year":"2021","unstructured":"Krisztian Balog. 2021. Conversational AI from an information retrieval perspective: Remaining challenges and a case for user simulation. In DESIRES."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/792550.792552"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Chris Buckley Darrin Dimmick Ian Soboroff and Ellen Voorhees. 2007. Bias and the limits of pooling for large collections. Information retrieval 10 (2007) 491\u2013508.","DOI":"10.1007\/s10791-007-9032-x"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1008992.1009000"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02272-2"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240370"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Christina\u00a0F Chick Valerie\u00a0F Reyna and Jonathan\u00a0C Corbin. 2016. Framing effects are robust to linguistic disambiguation: A critical test of contemporary theory. Journal of Experimental Psychology: Learning Memory and Cognition 42 2 (2016) 238.","DOI":"10.1037\/xlm0000158"},{"key":"e_1_3_3_2_10_2","unstructured":"Kyunghyun Cho Bart Van\u00a0Merri\u00ebnboer Caglar Gulcehre Dzmitry Bahdanau Fethi Bougares Holger Schwenk and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1406.1078 (2014)."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218964"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz Daniel Campos and Ellen\u00a0M Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2003.07820 (2020).","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564429"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Dalton Chenyan Xiong and Jamie Callan. 2020. TREC CAsT 2019: The conversational assistance track overview. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2003.13624 (2020).","DOI":"10.6028\/NIST.SP.1266.cast-overview"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401206"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"David Griol Javier Carb\u00f3 and Jos\u00e9\u00a0M Molina. 2013. An automatic dialog simulation technique to develop and evaluate interactive conversational agents. Applied Artificial Intelligence 27 9 (2013) 759\u2013780.","DOI":"10.1080\/08839514.2013.835230"},{"key":"e_1_3_3_2_17_2","first-page":"678","volume-title":"Proc. NeurIPS","author":"Guo Xiaoxiao","year":"2018","unstructured":"Xiaoxiao Guo, Hui Wu, Yu Cheng, Steven Rennie, Gerald Tesauro, and Rogerio Feris. 2018. Dialog-based interactive image retrieval. In Proc. NeurIPS. 678\u2013688."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123394"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_3_3_2_20_2","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1511.06939 (2015)."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401230"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Amir\u00a0H. Jadidinejad Craig Macdonald and Iadh Ounis. 2021. The Simpson\u2019s Paradox in the Offline Evaluation of Recommendation Systems. ACM Trans. Inf. Syst. 40 1 Article 4 (sep 2021) 22\u00a0pages.","DOI":"10.1145\/3458509"},{"key":"e_1_3_3_2_23_2","volume-title":"Proc. INTERSPEECH","author":"Jurc\u0131cek Filip","year":"2011","unstructured":"Filip Jurc\u0131cek, Simon Keizer, Milica Ga\u0161ic, Francois Mairesse, Blaise Thomson, Kai Yu, and Steve Young. 2011. Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk. In Proc. INTERSPEECH , Vol.\u00a011."},{"key":"e_1_3_3_2_24_2","unstructured":"RA Klein K Ratliff M Vianello RB Adams\u00a0Jr S Bahn\u00edk MJ Bernstein et\u00a0al. 2014. Investigating variation in replicability: a \u201cmany labs\u201d replication project. Open Science Framework."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.44"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Adriana Kovashka and Kristen Grauman. 2017. Attributes for image retrieval. Visual Attributes (2017) 89\u2013117.","DOI":"10.1007\/978-3-319-50077-5_5"},{"key":"e_1_3_3_2_27_2","unstructured":"Xiujun Li Zachary\u00a0C Lipton Bhuwan Dhingra Lihong Li Jianfeng Gao and Yun-Nung Chen. 2016. A user simulator for task-completion dialogues. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1612.05688 (2016)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.124"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.98"},{"key":"e_1_3_3_2_30_2","unstructured":"Sean MacAvaney and Luca Soldaini. 2023. One-Shot Labeling for Automatic Relevance Estimation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.11266 (2023)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591683"},{"key":"e_1_3_3_2_33_2","unstructured":"Jeffrey\u00a0M O\u2019Brien. 2006. The race to create a \u2018smart\u2019google. Fortune Magazine (2006)."},{"key":"e_1_3_3_2_34_2","unstructured":"Adelson Pi\u00f1on and Hilda Gambara. 2005. A meta-analytic review of framming effect: risky attribute and goal framing. Psicothema 17 2 (2005) 325\u2013331."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3121050.3121051"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Jennifer Rowley. 2000. Product search in e-shopping: a review and research propositions. Journal of consumer marketing 17 1 (2000) 20\u201335.","DOI":"10.1108\/07363760010309528"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Mark Sanderson et\u00a0al. 2010. Test collection based evaluation of information retrieval systems. Foundations and Trends\u00ae in Information Retrieval 4 4 (2010) 247\u2013375.","DOI":"10.1561\/1500000009"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614146"},{"key":"e_1_3_3_2_39_2","unstructured":"Weiyan Shi Kun Qian Xuewei Wang and Zhou Yu. 2019. How to build user simulators to train rl-based dialog systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1909.01388 (2019)."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Anna Shtok Oren Kurland David Carmel Fiana Raiber and Gad Markovits. 2012. Predicting query performance by query-drift estimation. ACM Transactions on Information Systems (TOIS) 30 2 (2012) 1\u201335.","DOI":"10.1145\/2180868.2180873"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Weiwei Sun Shuyu Guo Shuo Zhang Pengjie Ren Zhumin Chen Maarten de Rijke and Zhaochun Ren. 2023. Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems. ACM Transactions on Information Systems (2023).","DOI":"10.1145\/3596510"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463241"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210002"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Amos Tversky and Daniel Kahneman. 1981. The framing of decisions and the psychology of choice. science 211 4481 (1981) 453\u2013458.","DOI":"10.1126\/science.7455683"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15712-8_35"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16354-3_75"},{"key":"e_1_3_3_2_47_2","volume-title":"Proc. KaRS workshop at RecSys","author":"Vlachou Maria","year":"2022","unstructured":"Maria Vlachou and Craig Macdonald. 2022. Performance Predictors for Conversational Fashion Recommendation. In Proc. KaRS workshop at RecSys."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Xiao Wang Craig Macdonald Nicola Tonellotto and Iadh Ounis. 2023. ColBERT-PRF: Semantic pseudo-relevance feedback for dense passage and document retrieval. ACM Transactions on the Web 17 1 (2023) 1\u201339.","DOI":"10.1145\/3572405"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474256"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546774"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Aron Yu and Kristen Grauman. 2017. Fine-grained comparisons with attributes. Visual Attributes (2017) 119\u2013154.","DOI":"10.1007\/978-3-319-50077-5_6"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330991"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5465"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403202"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531936"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Kun Zhou Yuanhang Zhou Wayne\u00a0Xin Zhao Xiaoke Wang and Ji-Rong Wen. 2020. Towards topic-guided conversational recommender system. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.04125 (2020).","DOI":"10.18653\/v1\/2020.coling-main.365"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357967"}],"event":{"name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","location":"Prague Czech Republic","acronym":"RecSys '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3748149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:51:09Z","timestamp":1757159469000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3748149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":58,"alternative-id":["10.1145\/3705328.3748149","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3748149","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}