{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:22Z","timestamp":1786120762035,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Science Foundation","award":["IIS 2524379"],"award-info":[{"award-number":["IIS 2524379"]}]},{"name":"National Science Foundation","award":["NAIRR 250188"],"award-info":[{"award-number":["NAIRR 250188"]}]},{"name":"National Science Foundation","award":["NAIRR 260016"],"award-info":[{"award-number":["NAIRR 260016"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817524","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"9718-9729","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation (RAG)"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4961-8223","authenticated-orcid":false,"given":"Zhisheng","family":"Qi","sequence":"first","affiliation":[{"name":"University of Oregon, Eugene, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3596-2996","authenticated-orcid":false,"given":"Utkarsh","family":"Sahu","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, Oregon, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6081-370X","authenticated-orcid":false,"given":"Li","family":"Ma","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2529-6042","authenticated-orcid":false,"given":"Haoyu","family":"Han","sequence":"additional","affiliation":[{"name":"Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-0635","authenticated-orcid":false,"given":"Ryan","family":"Rossi","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1119-1346","authenticated-orcid":false,"given":"Franck","family":"Dernoncourt","sequence":"additional","affiliation":[{"name":"Adobe Research, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2323-4753","authenticated-orcid":false,"given":"Mahantesh","family":"Halappanavar","sequence":"additional","affiliation":[{"name":"PNNL, Richland, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7913-4962","authenticated-orcid":false,"given":"Nesreen","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Cisco AI Research, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7504-6159","authenticated-orcid":false,"given":"Yushun","family":"Dong","sequence":"additional","affiliation":[{"name":"Florida State University, Tallahassee, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3401-4921","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0540-6758","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-508X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, OR, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"11","author":"Liu Jerry","year":"2022","unstructured":"Jerry Liu. Llamaindex. 11 2022. https:\/\/github.com\/jerryjliu\/llama_index, 2022.","journal-title":"Llamaindex."},{"key":"e_1_3_2_1_2_1","volume-title":"https:\/\/github.com\/hwchase17\/langchain","author":"Chase Harrison","year":"2022","unstructured":"Harrison Chase. Langchain. October 2022. https:\/\/github.com\/hwchase17\/langchain, 2022."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Dave Van Veen Cara Van Uden Louis Blankemeier Jean-Benoit Delbrouck Asad Aali Christian Bluethgen Anuj Pareek Malgorzata Polacin William Collins Neera Ahuja et al. Clinical text summarization: Adapting large language models can outperform human experts. arXiv preprint arXiv:2309.07430 2023.","DOI":"10.21203\/rs.3.rs-3483777\/v1"},{"key":"e_1_3_2_1_4_1","volume-title":"In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083","author":"Ram Ori","year":"2023","unstructured":"Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083, 2023."},{"key":"e_1_3_2_1_5_1","volume-title":"Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. Replug: Retrieval-augmented black-box language models. arXiv preprint arXiv:2301.12652, 2023."},{"key":"e_1_3_2_1_6_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459-9474, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Face the facts! evaluating rag-based fact-checking pipelines in realistic settings. arXiv preprint arXiv:2412.15189","author":"Russo Daniel","year":"2024","unstructured":"Daniel Russo, Stefano Menini, Jacopo Staiano, and Marco Guerini. Face the facts! evaluating rag-based fact-checking pipelines in realistic settings. arXiv preprint arXiv:2412.15189, 2024."},{"key":"e_1_3_2_1_8_1","volume-title":"A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110","author":"Li Huayang","year":"2022","unstructured":"Huayang Li, Yixuan Su, Deng Cai, Yan Wang, and Lemao Liu. A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110, 2022."},{"key":"e_1_3_2_1_9_1","volume-title":"On the structural memory of llm agents. arXiv preprint arXiv:2412.15266","author":"Zeng Ruihong","year":"2024","unstructured":"Ruihong Zeng, Jinyuan Fang, Siwei Liu, and Zaiqiao Meng. On the structural memory of llm agents. arXiv preprint arXiv:2412.15266, 2024."},{"key":"e_1_3_2_1_10_1","volume-title":"Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges. arXiv preprint arXiv:2505.10468","author":"Sapkota Ranjan","year":"2025","unstructured":"Ranjan Sapkota, Konstantinos I Roumeliotis, and Manoj Karkee. Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenges. arXiv preprint arXiv:2505.10468, 2025."},{"issue":"3","key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3698590","article-title":"Knowledge editing for large language models: A survey","volume":"57","author":"Wang Song","year":"2024","unstructured":"Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. Knowledge editing for large language models: A survey. ACM Computing Surveys, 57(3):1-37, 2024.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_1_12_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2(1)","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2(1), 2023."},{"key":"e_1_3_2_1_13_1","volume-title":"The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag). arXiv preprint arXiv:2402.16893","author":"Zeng Shenglai","year":"2024","unstructured":"Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, et al. The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag). arXiv preprint arXiv:2402.16893, 2024."},{"key":"e_1_3_2_1_14_1","first-page":"2633","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, et al. Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21), pages 2633-2650, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"10697","volume-title":"International Conference on Machine Learning","author":"Kandpal Nikhil","year":"2022","unstructured":"Nikhil Kandpal, Eric Wallace, and Colin Raffel. Deduplicating training data mitigates privacy risks in language models. In International Conference on Machine Learning, pages 10697-10707. PMLR, 2022."},{"key":"e_1_3_2_1_16_1","volume-title":"Quantifying memorization across neural language models. arXiv preprint arXiv:2202.07646","author":"Carlini Nicholas","year":"2022","unstructured":"Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang. Quantifying memorization across neural language models. arXiv preprint arXiv:2202.07646, 2022."},{"key":"e_1_3_2_1_17_1","volume-title":"Exploring memorization in fine-tuned language models. arXiv preprint arXiv:2310.06714","author":"Zeng Shenglai","year":"2023","unstructured":"Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, and Dawei Yin. Exploring memorization in fine-tuned language models. arXiv preprint arXiv:2310.06714, 2023."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3634737.3657002"},{"key":"e_1_3_2_1_19_1","volume-title":"Agentic retrieval-augmented generation: A survey on agentic rag. arXiv preprint arXiv:2501.09136","author":"Singh Aditi","year":"2025","unstructured":"Aditi Singh, Abul Ehtesham, Saket Kumar, and Tala Talaei Khoei. Agentic retrieval-augmented generation: A survey on agentic rag. arXiv preprint arXiv:2501.09136, 2025."},{"key":"e_1_3_2_1_20_1","volume-title":"A-mem: Agentic memory for llm agents. arXiv preprint arXiv:2502.12110","author":"Xu Wujiang","year":"2025","unstructured":"Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, and Yongfeng Zhang. A-mem: Agentic memory for llm agents. arXiv preprint arXiv:2502.12110, 2025."},{"key":"e_1_3_2_1_21_1","volume-title":"https:\/\/huggingface.co\/datasets\/lavita\/ChatDoctor-HealthCareMagic-100k","year":"2023","unstructured":"lavita. Chatdoctor-healthcaremagic-100k. https:\/\/huggingface.co\/datasets\/lavita\/ChatDoctor-HealthCareMagic-100k, 2023."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.176240542.22279040\/v1"},{"key":"e_1_3_2_1_23_1","unstructured":"Mohammad Zahangir Alam Khandoker Ashik Uz Zaman and Mahdi H Miraz. Astuterag-fqa: Task-aware retrieval-augmented generation framework for proprietary data challenges in financial question answering. arXiv preprint arXiv:2510.27537 2025."},{"key":"e_1_3_2_1_24_1","volume-title":"Feedback-guided extraction of knowledge base from retrieval-augmented llm applications. arXiv preprint arXiv:2411.14110","author":"Jiang Changyue","year":"2025","unstructured":"Changyue Jiang, Xudong Pan, Geng Hong, Chenfu Bao, and Min Yang. Feedback-guided extraction of knowledge base from retrieval-augmented llm applications. arXiv preprint arXiv:2411.14110, 2025."},{"key":"e_1_3_2_1_25_1","volume-title":"Silent leaks: Implicit knowledge extraction attack on rag systems through benign queries. arXiv preprint","author":"Wang Yuhao","year":"2025","unstructured":"Yuhao Wang, Wenjie Qu, Shengfang Zhai, Yanze Jiang, Zichen Liu, Yue Liu, Yinpeng Dong, and Jiaheng Zhang. Silent leaks: Implicit knowledge extraction attack on rag systems through benign queries. arXiv preprint, 2025."},{"key":"e_1_3_2_1_26_1","volume-title":"Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking. arXiv preprint arXiv:2409.08045","author":"Cohen Stav","year":"2024","unstructured":"Stav Cohen, Ron Bitton, and Ben Nassi. Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking. arXiv preprint arXiv:2409.08045, 2024."},{"key":"e_1_3_2_1_27_1","volume-title":"Exposing privacy risks in graph retrieval-augmented generation. arXiv preprint arXiv:2508.17222","author":"Liu Jiale","year":"2025","unstructured":"Jiale Liu, Jiahao Zhang, and Suhang Wang. Exposing privacy risks in graph retrieval-augmented generation. arXiv preprint arXiv:2508.17222, 2025."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics","author":"Zhang Yuqi","year":"2025","unstructured":"Yuqi Zhang, Liang Ding, Lefei Zhang, and Dacheng Tao. Intention analysis makes llms a good jailbreak defender. In Proceedings of the 31st International Conference on Computational Linguistics, 2025."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_22"},{"key":"e_1_3_2_1_30_1","volume-title":"https:\/\/huggingface.co\/datasets\/vapit\/HarryPotterQA","year":"2023","unstructured":"vapit. Harrypotterqa. https:\/\/huggingface.co\/datasets\/vapit\/HarryPotterQA, 2023."},{"key":"e_1_3_2_1_31_1","volume-title":"Pok\u00e9mon qa dataset. https:\/\/huggingface.co\/datasets\/tungdop2\/pokemon","author":"Duong Quang Tung","year":"2023","unstructured":"Quang Tung Duong. Pok\u00e9mon qa dataset. https:\/\/huggingface.co\/datasets\/tungdop2\/pokemon, 2023."},{"key":"e_1_3_2_1_32_1","volume-title":"Knowledge homophily in large language models. arXiv preprint arXiv:2509.23773","author":"Sahu Utkarsh","year":"2025","unstructured":"Utkarsh Sahu, Zhisheng Qi, Mahantesh Halappanavar, Nedim Lipka, Ryan A Rossi, Franck Dernoncourt, Yu Zhang, Yao Ma, and Yu Wang. Knowledge homophily in large language models. arXiv preprint arXiv:2509.23773, 2025."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3764579"},{"key":"e_1_3_2_1_34_1","unstructured":"Zhehao Zhang Ryan A Rossi Branislav Kveton Yijia Shao Diyi Yang Hamed Zamani Franck Dernoncourt Joe Barrow Tong Yu Sungchul Kim et al. Personalization of large language models: A survey."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781394293773.ch04"},{"key":"e_1_3_2_1_36_1","volume-title":"WA (United States)","author":"Rahman Moqsadur","year":"2024","unstructured":"Moqsadur Rahman, Krish O Piryani, Aaron M Sanchez, Sai Munikoti, Luis De La Torre, Maxwell S Levin, Monika Akbar, Mahmud Hossain, Monowar Hasan, and Mahantesh Halappanavar. Retrieval augmented generation for robust cyber defense. Technical report, Pacific Northwest National Laboratory (PNNL), Richland, WA (United States), 2024."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103158"},{"key":"e_1_3_2_1_38_1","volume-title":"Retrieval-augmented generation with graphs (graphrag). arXiv preprint arXiv:2501.00309","author":"Han Haoyu","year":"2024","unstructured":"Haoyu Han, Yu Wang, Harry Shomer, Kai Guo, Jiayuan Ding, Yongjia Lei, Mahantesh Halappanavar, Ryan A Rossi, Subhabrata Mukherjee, Xianfeng Tang, et al. Retrieval-augmented generation with graphs (graphrag). arXiv preprint arXiv:2501.00309, 2024."},{"key":"e_1_3_2_1_39_1","volume-title":"Hypercube-rag: Hypercube-based retrieval-augmented generation for in-domain scientific question-answering. arXiv preprint","author":"Shi Jimeng","year":"2025","unstructured":"Jimeng Shi, Sizhe Zhou, Bowen Jin, Wei Hu, Shaowen Wang, Giri Narasimhan, and Jiawei Han. Hypercube-rag: Hypercube-based retrieval-augmented generation for in-domain scientific question-answering. arXiv preprint, 2025."},{"key":"e_1_3_2_1_40_1","volume-title":"Benchmarking poisoning attacks against retrieval-augmented generation. arXiv preprint arXiv:2505.18543","author":"Zhang Baolei","year":"2025","unstructured":"Baolei Zhang, Haoran Xin, Jiatong Li, Dongzhe Zhang, Minghong Fang, Zhuqing Liu, Lihai Nie, and Zheli Liu. Benchmarking poisoning attacks against retrieval-augmented generation. arXiv preprint arXiv:2505.18543, 2025."},{"key":"e_1_3_2_1_41_1","volume-title":"Adversarial hubness in multi-modal retrieval. arXiv preprint arXiv:2412.14113","author":"Zhang Tingwei","year":"2024","unstructured":"Tingwei Zhang, Fnu Suya, Rishi Jha, Collin Zhang, and Vitaly Shmatikov. Adversarial hubness in multi-modal retrieval. arXiv preprint arXiv:2412.14113, 2024."},{"key":"e_1_3_2_1_42_1","first-page":"3827","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Zou Wei","year":"2025","unstructured":"Wei Zou, Runpeng Geng, Binghui Wang, and Jinyuan Jia. : Knowledge corruption attacks to generation of large language models. In 34th USENIX Security Symposium (USENIX Security 25), pages 3827-3844, 2025."},{"key":"e_1_3_2_1_43_1","volume-title":"Gim, and Lin Zhong. Confidential prompting: Privacy-preserving llm inference on cloud","author":"Li Caihua","year":"2025","unstructured":"Caihua Li, In Gim, and Lin Zhong. Confidential prompting: Privacy-preserving llm inference on cloud, 2025."},{"key":"e_1_3_2_1_44_1","volume-title":"Privacybench: A conversational benchmark for evaluating privacy in personalized ai. arXiv preprint arXiv:2512.24848","author":"Mukhopadhyay Srija","year":"2025","unstructured":"Srija Mukhopadhyay, Sathwik Reddy, Shruthi Muthukumar, Jisun An, and Ponnurangam Kumaraguru. Privacybench: A conversational benchmark for evaluating privacy in personalized ai. arXiv preprint arXiv:2512.24848, 2025."},{"key":"e_1_3_2_1_45_1","volume-title":"Fan Zhang. Understanding PII Leakage in Large Language Models: A Systematic Survey. In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-25)","author":"Cheng Shuai","year":"2025","unstructured":"Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, and Fan Zhang. Understanding PII Leakage in Large Language Models: A Systematic Survey. In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI-25), Survey Track, pages 10409-10416, 2025."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494859"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3710848.3710870"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589105"},{"key":"e_1_3_2_1_49_1","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Chandrasekaran Varun","year":"2020","unstructured":"Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, and Songbai Yan. Exploring connections between active learning and model extraction. In 29th USENIX Security Symposium (USENIX Security 20), 2020."},{"key":"e_1_3_2_1_50_1","volume-title":"Emailsum: Abstractive email thread summarization. arXiv preprint arXiv:2107.14691","author":"Zhang Shiyue","year":"2021","unstructured":"Shiyue Zhang, Asli Celikyilmaz, Jianfeng Gao, and Mohit Bansal. Emailsum: Abstractive email thread summarization. arXiv preprint arXiv:2107.14691, 2021."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/972684.972687"},{"key":"e_1_3_2_1_52_1","first-page":"11","author":"Liu Jerry","year":"2022","unstructured":"Jerry Liu. LlamaIndex, 11 2022.","journal-title":"LlamaIndex"},{"key":"e_1_3_2_1_53_1","volume-title":"Equilibrate rlhf: Towards balancing helpfulness-safety trade-off in large language models. arXiv preprint arXiv:2502.11555","author":"Tan Yingshui","year":"2025","unstructured":"Yingshui Tan, Yilei Jiang, Yanshi Li, Jiaheng Liu, Xingyuan Bu, Wenbo Su, Xiangyu Yue, Xiaoyong Zhu, and Bo Zheng. Equilibrate rlhf: Towards balancing helpfulness-safety trade-off in large language models. arXiv preprint arXiv:2502.11555, 2025."},{"key":"e_1_3_2_1_54_1","volume-title":"Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843","author":"Merity Stephen","year":"2016","unstructured":"Stephen Merity, Caiming Xiong, James Bradbury, and Richard Socher. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843, 2016."},{"key":"e_1_3_2_1_55_1","volume-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems, 2020."},{"key":"e_1_3_2_1_56_1","volume-title":"Towards general text embeddings with multi-stage contrastive learning. arXiv preprint","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint, 2023."},{"key":"e_1_3_2_1_57_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint, 2024."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3508"},{"key":"e_1_3_2_1_59_1","volume-title":"Follow my instruction and spill the beans: Scalable data extraction from retrieval-augmented generation systems. arXiv preprint arXiv:2402.17840","author":"Qi Zhenting","year":"2024","unstructured":"Zhenting Qi, Hanlin Zhang, Eric Xing, Sham Kakade, and Himabindu Lakkaraju. Follow my instruction and spill the beans: Scalable data extraction from retrieval-augmented generation systems. arXiv preprint arXiv:2402.17840, 2024."},{"key":"e_1_3_2_1_60_1","volume-title":"Rag vs. graphrag: A systematic evaluation and key insights. arXiv preprint arXiv:2502.11371","author":"Han Haoyu","year":"2025","unstructured":"Haoyu Han, Li Ma, Yu Wang, Harry Shomer, Yongjia Lei, Zhisheng Qi, Kai Guo, Zhigang Hua, Bo Long, Hui Liu, et al. Rag vs. graphrag: A systematic evaluation and key insights. arXiv preprint arXiv:2502.11371, 2025."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.743"},{"key":"e_1_3_2_1_62_1","volume-title":"Vietnamese medical qa: Question answering dataset for medical in vietnamese","author":"Nguyen Hung","year":"2024","unstructured":"Hung Nguyen. Vietnamese medical qa: Question answering dataset for medical in vietnamese, 2024."},{"key":"e_1_3_2_1_63_1","volume-title":"100,000 questions for machine comprehension of text. arXiv preprint","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. Squad: 100,000 questions for machine comprehension of text. arXiv preprint, 2016."},{"key":"e_1_3_2_1_64_1","first-page":"311","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311-318, 2002."},{"key":"e_1_3_2_1_65_1","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74-81, 2004."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1247"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-long.194"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:25:27Z","timestamp":1786065927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817524"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":67,"alternative-id":["10.1145\/3770855.3817524","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817524","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}