{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T09:30:55Z","timestamp":1775899855595,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","funder":[{"name":"This research was partly supported by the Swiss National Science Foundation (SNSF), under the project PACINO (Personality And Conversational INformatiOn Access)","award":["215742"],"award-info":[{"award-number":["215742"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730316","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"3455-3465","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Conversational Gold: Evaluating Personalized Conversational Search System Using Gold Nuggets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4046-3419","authenticated-orcid":false,"given":"Zahra","family":"Abbasiantaeb","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2383-4557","authenticated-orcid":false,"given":"Simon","family":"Lupart","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6900-0557","authenticated-orcid":false,"given":"Leif","family":"Azzopardi","sequence":"additional","affiliation":[{"name":"University of Strathclyde, Glasgow, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-8651","authenticated-orcid":false,"given":"Jeffrey","family":"Dalton","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9447-4172","authenticated-orcid":false,"given":"Mohammad","family":"Aliannejadi","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amstedam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Zahra Abbasiantaeb and Mohammad Aliannejadi. 2024. Generate then Retrieve: Conversational Response Retrieval Using LLMs as Answer and Query Generators. https:\/\/doi.org\/10.48550\/ARXIV.2403.19302 showeprint[arXiv]2403.19302","DOI":"10.48550\/ARXIV.2403.19302"},{"key":"e_1_3_2_1_2_1","unstructured":"Zahra Abbasiantaeb Chuan Meng Leif Azzopardi and Mohammad Aliannejadi. 2024a. Can We Use Large Language Models to Fill Relevance Judgment Holes? https:\/\/ceur-ws.org\/Vol-3854\/emtcir-2.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Advances in Information Retrieval","author":"Abbasiantaeb Zahra","unstructured":"Zahra Abbasiantaeb, Chuan Meng, Leif Azzopardi, and Mohammad Aliannejadi. 2025. Improving the\u00a0Reusability of\u00a0Conversational Search Test Collections. In Advances in Information Retrieval, Claudia Hauff, Craig Macdonald, Dietmar Jannach, Gabriella Kazai, Franco Maria Nardini, Fabio Pinelli, Fabrizio Silvestri, and Nicola Tonellotto (Eds.). Springer Nature Switzerland, Cham, 196-213."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635856"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.08137"},{"key":"e_1_3_2_1_6_1","volume-title":"The Thirty-Second Text REtrieval Conference Proceedings (TREC 2023","author":"Aliannejadi Mohammad","year":"2023","unstructured":"Mohammad Aliannejadi, Zahra Abbasiantaeb, Shubham Chatterjee, Jeffery Dalton, and Leif Azzopardi. 2023. TREC iKAT 2023: The Interactive Knowledge Assistance Track Overview. In The Thirty-Second Text REtrieval Conference Proceedings (TREC 2023), Gaithersburg, MD, USA, November 14-17, 2023 (NIST Special Publication, Vol. 500-xxx), Ian Soboroff and Angela Ellis (Eds.). National Institute of Standards and Technology (NIST). https:\/\/trec.nist.gov\/pubs\/trec32\/papers\/Overview_ikat.pdf"},{"key":"e_1_3_2_1_7_1","volume-title":"Text REtrieval Conference (TREC). NIST.","author":"Aliannejadi Mohammad","year":"2025","unstructured":"Mohammad Aliannejadi, Zahra Abbasiantaeb, Simon Lupart, Shubham Chatterjee, Jeffery Dalton, and Leif Azzopardi. 2025. TREC iKAT 2024: The Interactive Knowledge Assistance Track Overview. In Text REtrieval Conference (TREC). NIST."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331265"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.02043"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2404.08630"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1394251.1394261"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Jannis Bulian Christian Buck Wojciech Gajewski Benjamin B\u00f6rschinger and Tal Schuster. 2022. Tomayto Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation. (2022) 291-305. https:\/\/doi.org\/10.18653\/V1\/2022.EMNLP-MAIN.20","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.20"},{"key":"e_1_3_2_1_13_1","volume-title":"Text REtrieval Conference (TREC). NIST.","author":"Dalton Jeffrey","year":"2020","unstructured":"Jeffrey Dalton, Chenyan Xiong, and Jamie Callan. 2020a. CAsT 2019: The conversational assistance track overview. In Text REtrieval Conference (TREC). NIST."},{"key":"e_1_3_2_1_14_1","volume-title":"Text REtrieval Conference (TREC). NIST.","author":"Dalton Jeffrey","year":"2021","unstructured":"Jeffrey Dalton, Chenyan Xiong, and Jamie Callan. 2021. TREC CAsT 2021: The Conversational Assistance Track Overview. In Text REtrieval Conference (TREC). NIST."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401206"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_2_1_17_1","first-page":"150","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - System Demonstrations, St. Julians","author":"Jithin James Shahul ES","year":"2024","unstructured":"Shahul ES, Jithin James, Luis Espinosa Anke, and Steven Schockaert. 2024. RAGAs: Automated Evaluation of Retrieval Augmented Generation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - System Demonstrations, St. Julians, Malta, March 17-22, 2024, Nikolaos Aletras and Orph\u00e9e De Clercq (Eds.). Association for Computational Linguistics, 150-158. https:\/\/aclanthology.org\/2024.eacl-demo.16"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37256-8_36"},{"key":"e_1_3_2_1_20_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. Deberta: decoding-Enhanced Bert with Disentangled Attention. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=XPZIaotutsD"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.07998"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford Aleksander Madry Alex Baker-Whitcomb Alex Beutel Alex Borzunov Alex Carney Alex Chow Alex Kirillov Alex Nichol Alex Paino Alex Renzin Alex Tachard Passos Alexander Kirillov Alexi Christakis Alexis Conneau Ali Kamali Allan Jabri Allison Moyer Allison Tam Amadou Crookes Amin Tootoonchian Ananya Kumar Andrea Vallone Andrej Karpathy Andrew Braunstein Andrew Cann Andrew Codispoti Andrew Galu Andrew Kondrich Andrew Tulloch Andrey Mishchenko Angela Baek Angela Jiang Antoine Pelisse Antonia Woodford Anuj Gosalia Arka Dhar Ashley Pantuliano Avi Nayak Avital Oliver Barret Zoph Behrooz Ghorbani Ben Leimberger Ben Rossen Ben Sokolowsky Ben Wang Benjamin Zweig Beth Hoover Blake Samic Bob McGrew Bobby Spero Bogo Giertler Bowen Cheng Brad Lightcap Brandon Walkin Brendan Quinn Brian Guarraci Brian Hsu Bright Kellogg Brydon Eastman Camillo Lugaresi Carroll L. Wainwright Cary Bassin Cary Hudson Casey Chu Chad Nelson Chak Li Chan Jun Shern Channing Conger Charlotte Barette Chelsea Voss Chen Ding Cheng Lu Chong Zhang Chris Beaumont Chris Hallacy Chris Koch Christian Gibson Christina Kim Christine Choi Christine McLeavey Christopher Hesse Claudia Fischer Clemens Winter Coley Czarnecki Colin Jarvis Colin Wei Constantin Koumouzelis and Dane Sherburn. 2024. GPT-4o System Card. CoRR Vol. abs\/2410.21276 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2410.21276 showeprint[arXiv]2410.21276","DOI":"10.48550\/ARXIV.2410.21276"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.307"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.03468"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Sanghoon Kim Dahyun Kim Chanjun Park Wonsung Lee Wonho Song Yunsu Kim Hyeonwoo Kim Yungi Kim Hyeonju Lee Jihoo Kim Changbae Ahn Seonghoon Yang Sukyung Lee Hyunbyung Park Gyoungjin Gim Mikyoung Cha Hwalsuk Lee and Sunghun Kim. 2024. SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling. (2024) 23-35. https:\/\/doi.org\/10.18653\/V1\/2024.NAACL-INDUSTRY.3","DOI":"10.18653\/V1\/2024.NAACL-INDUSTRY.3"},{"key":"e_1_3_2_1_26_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74-81. https:\/\/aclanthology.org\/W04-1013\/"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Jimmy Lin Xueguang Ma Sheng-Chieh Lin Jheng-Hong Yang Ronak Pradeep and Rodrigo Nogueira. 2021. Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations. In SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval Virtual Event Canada July 11-15 2021 Fernando Diaz Chirag Shah Torsten Suel Pablo Castells Rosie Jones and Tetsuya Sakai (Eds.). ACM 2356-2362. https:\/\/doi.org\/10.1145\/3404835.3463238","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.14739"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.14609"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.86"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657846"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.135"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.15576"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4573(00)00053-4"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Arnold Overwijk Chenyan Xiong Xiao Liu Cameron VandenBerg and Jamie Callan. 2022. ClueWeb22: 10 Billion Web Documents with Visual and Semantic Information. arxiv: 2211.15848 [cs.IR]","DOI":"10.1145\/3477495.3536321"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Thirty-First Text REtrieval Conference, TREC 2022","author":"Owoicho Paul","year":"2022","unstructured":"Paul Owoicho, Jeff Dalton, Mohammad Aliannejadi, Leif Azzopardi, Johanne R. Trippas, and Svitlana Vakulenko. 2022. TREC CAsT 2022: Going Beyond User Ask and System Retrieve with Initiative and Response Generation. In Proceedings of the Thirty-First Text REtrieval Conference, TREC 2022, online, November 15-19, 2022 (NIST Special Publication, Vol. 500-338), Ian Soboroff and Angela Ellis (Eds.). National Institute of Standards and Technology (NIST). https:\/\/trec.nist.gov\/pubs\/trec31\/papers\/Overview_cast.pdf"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.09607"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3020183"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657992"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2408.05388"},{"key":"e_1_3_2_1_42_1","volume-title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Rau David","year":"2024","unstructured":"David Rau, Herv\u00e9 D\u00e9jean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, St\u00e9phane Clinchant, and Vassilina Nikoulina. 2024. BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). Association for Computational Linguistics, 7640-7663. https:\/\/aclanthology.org\/2024.findings-emnlp.449"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.NAACL-LONG.20"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Chris Samarinas Alexander Krubner Alireza Salemi Youngwoo Kim and Hamed Zamani. 2025. Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation. https:\/\/doi.org\/10.48550\/ARXIV.2501.03545 showeprint[arXiv]2501.03545","DOI":"10.48550\/ARXIV.2501.03545"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624918.3625338"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657707"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of The Twelfth Text REtrieval Conference, TREC 2003","author":"Voorhees Ellen M.","year":"2003","unstructured":"Ellen M. Voorhees. 2003. Overview of the TREC 2003 Question Answering Track. In Proceedings of The Twelfth Text REtrieval Conference, TREC 2003, Gaithersburg, Maryland, USA, November 18-21, 2003 (NIST Special Publication, Vol. 500-255), Ellen M. Voorhees and Lori P. Buckland (Eds.). National Institute of Standards and Technology (NIST), 54-68. http:\/\/trec.nist.gov\/pubs\/trec12\/papers\/QA.OVERVIEW.pdf"},{"key":"e_1_3_2_1_48_1","first-page":"332","article-title":"Eval4RAG: Workshop on Evaluation of Retrieval-Augmented Generation Systems. In ECIR (5) (Lecture Notes in Computer Science, Vol. 15576)","author":"Yang Eugene","year":"2025","unstructured":"Eugene Yang, Ronak Pradeep, Dake Zhang, Sean MacAvaney, Maria Maistro, and Mohammad Aliannejadi. 2025. Eval4RAG: Workshop on Evaluation of Retrieval-Augmented Generation Systems. In ECIR (5) (Lecture Notes in Computer Science, Vol. 15576). Springer, 332-338.","journal-title":"Springer"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.500-321.domain-overview"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.500-324.domain-overview"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.500-319.domain-overview"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000081"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.415"},{"key":"e_1_3_2_1_54_1","volume-title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/91f18a1287b398d378ef22505bf41832-Abstract-Datasets_and_Benchmarks.html"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:11:33Z","timestamp":1755864693000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":54,"alternative-id":["10.1145\/3726302.3730316","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730316","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}