{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:07:12Z","timestamp":1784178432039,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676674","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:53:56Z","timestamp":1744203236000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0827-2257","authenticated-orcid":false,"given":"Ruiyang","family":"Qin","sequence":"first","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1830-606X","authenticated-orcid":false,"given":"Zheyu","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0028-8854","authenticated-orcid":false,"given":"Dewen","family":"Zeng","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0554-3608","authenticated-orcid":false,"given":"Zhenge","family":"Jia","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6107-5612","authenticated-orcid":false,"given":"Dancheng","family":"Liu","sequence":"additional","affiliation":[{"name":"University at Buffalo--SUNY, Buffalo, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4768-7797","authenticated-orcid":false,"given":"Jianbo","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7698-7794","authenticated-orcid":false,"given":"Ahmed","family":"Abbasi","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5274-8721","authenticated-orcid":false,"given":"Zhi","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-1051","authenticated-orcid":false,"given":"Ningyuan","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3628-3431","authenticated-orcid":false,"given":"Kai","family":"Ni","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2620-4859","authenticated-orcid":false,"given":"Jinjun","family":"Xiong","sequence":"additional","affiliation":[{"name":"University at Buffalo--SUNY, Buffalo, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6788-9823","authenticated-orcid":false,"given":"Yiyu","family":"Shi","sequence":"additional","affiliation":[{"name":"University of Notre Dame, Notre Dame, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"When automated assessment meets automated content generation: Examining text quality in the era of gpts. arXiv preprint arXiv:2309.14488","author":"Bevilacqua Marialena","year":"2023","unstructured":"Marialena Bevilacqua, Kezia Oketch, Ruiyang Qin, Will Stamey, Xinyuan Zhang, Yi Gan, Kai Yang, and Ahmed Abbasi. When automated assessment meets automated content generation: Examining text quality in the era of gpts. arXiv preprint arXiv:2309.14488, 2023."},{"key":"e_1_3_2_1_2_1","volume-title":"Fl-nas: Towards fairness of nas for resource constrained devices via large language models. arXiv preprint arXiv:2402.06696","author":"Qin Ruiyang","year":"2024","unstructured":"Ruiyang Qin, Yuting Hu, Zheyu Yan, Jinjun Xiong, Ahmed Abbasi, and Yiyu Shi. Fl-nas: Towards fairness of nas for resource constrained devices via large language models. arXiv preprint arXiv:2402.06696, 2024."},{"key":"e_1_3_2_1_3_1","volume-title":"Privacy issues in large language models: A survey","author":"Neel Seth","year":"2023","unstructured":"Seth Neel and Peter Chang. Privacy issues in large language models: A survey, 2023."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.39305"},{"key":"e_1_3_2_1_5_1","volume-title":"Can large language models be good companions? an llm-based eyewear system with conversational common ground","author":"Xu","year":"2023","unstructured":"Xu et al. Can large language models be good companions? an llm-based eyewear system with conversational common ground, 2023."},{"key":"e_1_3_2_1_6_1","volume-title":"Personal llm agents: Insights and survey about the capability, efficiency and security","author":"Li","year":"2024","unstructured":"Li et al. Personal llm agents: Insights and survey about the capability, efficiency and security, 2024."},{"key":"e_1_3_2_1_7_1","volume-title":"Enabling on-device large language model personalization with self-supervised data selection and synthesis. arXiv preprint arXiv:2311.12275","author":"Qin Ruiyang","year":"2023","unstructured":"Ruiyang Qin, Jun Xia, Zhenge Jia, Meng Jiang, Ahmed Abbasi, Peipei Zhou, Jingtong Hu, and Yiyu Shi. Enabling on-device large language model personalization with self-supervised data selection and synthesis. arXiv preprint arXiv:2311.12275, 2023."},{"key":"e_1_3_2_1_8_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar","year":"2022","unstructured":"Frantar et al. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323, 2022."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614307"},{"key":"e_1_3_2_1_10_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","unstructured":"Lewis 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_11_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu","year":"2021","unstructured":"Hu et al. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021."},{"key":"e_1_3_2_1_12_1","volume-title":"2013 IEEE 29th symposium on mass storage systems and technologies (MSST). IEEE.","author":"Kang","unstructured":"Kang et al. Enabling cost-effective data processing with smart ssd. In 2013 IEEE 29th symposium on mass storage systems and technologies (MSST). IEEE."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 22nd International Workshop on Software and Compilers for Embedded Systems.","author":"BanaGozar","unstructured":"BanaGozar et al. Cim-sim: computation in memory simuiator. In Proceedings of the 22nd International Workshop on Software and Compilers for Embedded Systems."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_2_1_15_1","first-page":"32","volume-title":"Dnn+ neurosim: An end-to-end benchmarking framework for compute-in-memory accelerators with versatile device technologies. In 2019 IEEE international electron devices meeting(IEDM)","author":"Peng","year":"2019","unstructured":"Peng et al. Dnn+ neurosim: An end-to-end benchmarking framework for compute-in-memory accelerators with versatile device technologies. In 2019 IEEE international electron devices meeting(IEDM), pages 32--5. IEEE, 2019."},{"key":"e_1_3_2_1_16_1","volume-title":"Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH computer architecture news, 44(3):367--379","author":"Chen","year":"2016","unstructured":"Chen et al. Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH computer architecture news, 44(3):367--379, 2016."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3365633"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3165352"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2991575"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00015"},{"key":"e_1_3_2_1_21_1","volume-title":"2022 59th ACM\/IEEE Design Automation Conference (DAC). IEEE.","author":"Swim Yan","unstructured":"Yan et al. Swim: Selective write-verify for computing-in-memory neural accelerators. In 2022 59th ACM\/IEEE Design Automation Conference (DAC). IEEE."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431635"},{"key":"e_1_3_2_1_23_1","volume-title":"2021 58th ACM\/IEEE Design Automation Conference (DAC). IEEE.","author":"Gao","unstructured":"Gao et al. Bayesian inference based robust computing on memristor crossbar. In 2021 58th ACM\/IEEE Design Automation Conference (DAC). IEEE."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323830"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530478"},{"key":"e_1_3_2_1_26_1","unstructured":"Shim et al. Two-step write-verify scheme and impact of the read noise in multilevel rram-based inference engine. Semiconductor Science and Technology."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-1942-4"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586286"},{"key":"e_1_3_2_1_29_1","first-page":"1597","volume-title":"International conference on machine learning","author":"Chen","year":"2020","unstructured":"Chen et al. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597--1607. PMLR, 2020."},{"key":"e_1_3_2_1_30_1","volume-title":"Distance metric learning for large margin nearest neighbor classification. Advances in neural information processing systems, 18","author":"Weinberger","year":"2005","unstructured":"Weinberger et al. Distance metric learning for large margin nearest neighbor classification. Advances in neural information processing systems, 18, 2005."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_21"},{"key":"e_1_3_2_1_32_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao","year":"2021","unstructured":"Gao et al. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821, 2021."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3213517"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","first-page":"88","DOI":"10.18653\/v1\/2020.acl-srw.13","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop","author":"Scar Malireddy","year":"2020","unstructured":"Malireddy et al. Scar: Sentence compression using autoencoders for reconstruction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 88--94, 2020."},{"key":"e_1_3_2_1_35_1","volume-title":"Lamp: When large language models meet personalization. arXiv preprint arXiv:2304.11406","author":"Salemi","year":"2023","unstructured":"Salemi et al. Lamp: When large language models meet personalization. arXiv preprint arXiv:2304.11406, 2023."},{"key":"e_1_3_2_1_36_1","volume-title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1--19","author":"Maxwell Harper F","year":"2015","unstructured":"F Maxwell Harper and Joseph A Konstan. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1--19, 2015."},{"key":"e_1_3_2_1_37_1","first-page":"188","volume-title":"EMNLP-IJCNLP","author":"Ni","year":"2019","unstructured":"Ni et al. Justifying recommendations using distantly-labeled reviews and finegrained aspects. In EMNLP-IJCNLP, pages 188--197, 2019."},{"key":"e_1_3_2_1_38_1","volume-title":"News category dataset. arXiv preprint arXiv:2209.11429","author":"Misra Rishabh","year":"2022","unstructured":"Rishabh Misra. News category dataset. arXiv preprint arXiv:2209.11429, 2022."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1145\/1401890.1402008","volume-title":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","author":"Arnetminer Tang","year":"2008","unstructured":"Tang et al. Arnetminer: extraction and mining of academic social networks. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 990--998, 2008."},{"key":"e_1_3_2_1_40_1","unstructured":"Hugging Face. Sentence transformers: all-minilm-l6-v2. https:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L6-v2."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3785-8"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0084660"},{"key":"e_1_3_2_1_43_1","volume-title":"Root mean square error (rmse) or mean absolute error (mae)?-arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247--1250","author":"Chai","year":"2014","unstructured":"Chai et al. Root mean square error (rmse) or mean absolute error (mae)?-arguments against avoiding rmse in the literature. Geoscientific model development, 7(3):1247--1250, 2014."},{"key":"e_1_3_2_1_44_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_45_1","volume-title":"Cxdnn: Hardware-software compensation methods for deep neural networks on resistive crossbar systems. ACM Transactions on Embedded Computing Systems (TECS), 18(6):1--23","author":"Jain","year":"2019","unstructured":"Jain et al. Cxdnn: Hardware-software compensation methods for deep neural networks on resistive crossbar systems. ACM Transactions on Embedded Computing Systems (TECS), 18(6):1--23, 2019."},{"key":"e_1_3_2_1_46_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE.","author":"Correctnet Eldebiky","unstructured":"Eldebiky et al. Correctnet: Robustness enhancement of analog in-memory computing for neural networks by error suppression and compensation. In 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE."},{"key":"e_1_3_2_1_47_1","volume-title":"Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295","author":"Team Gemma","year":"2024","unstructured":"Gemma Team. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295, 2024."},{"key":"e_1_3_2_1_48_1","volume-title":"Openllama: An open reproduction of llama","author":"Geng","year":"2023","unstructured":"Geng et al. Openllama: An open reproduction of llama, 2023."},{"key":"e_1_3_2_1_49_1","volume-title":"Textbooks are all you need. arXiv preprint arXiv:2306.11644","author":"Gunasekar","year":"2023","unstructured":"Gunasekar et al. Textbooks are all you need. arXiv preprint arXiv:2306.11644, 2023."},{"key":"e_1_3_2_1_50_1","volume-title":"Mistral 7b. arXiv preprint arXiv:2310.06825","author":"Jiang","year":"2023","unstructured":"Jiang et al. Mistral 7b. arXiv preprint arXiv:2310.06825, 2023."}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:43:57Z","timestamp":1750290237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":50,"alternative-id":["10.1145\/3676536.3676674","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676674","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}