{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:47:14Z","timestamp":1783784834414,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657662","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2765-2770","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4360-1423","authenticated-orcid":false,"given":"Zijie J.","family":"Wang","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9824-3323","authenticated-orcid":false,"given":"Duen Horng","family":"Chau","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"i","volume":"202","author":"Abdin Marah","unstructured":"Marah Abdin, Jyoti Aneja, Sebastien Bubeck, Caio C\u00e9sar Teodoro Mendes, Weizhu Chen, Allie Del Giorno, Ronen Eldan, Sivakanth Gopi, Suriya Gunasekar, Mojan Javaheripi, Piero Kauffmann, Yin Tat Lee, Yuanzhi Li, Anh Nguyen, Gustavo de Rosa, Olli Saarikivi, Adil Salim, Shital Shah, Michael Santacroce, Harkirat Singh Behl, Adam Taumann Kalai, Xin Wang, Rachel Ward, Philipp Witte, Cyril Zhang, and Yi Zhang. 2023. Phi-2: The Surprising Power of Small Language Models. (2023). https:\/\/www.microsoft.com\/en-us\/research\/blog\/phi-2-the-surprising-power-of-small-language-models\/","journal-title":"Yi Zhang."},{"key":"e_1_3_2_1_2_1","unstructured":"Apple. 2017. Core ML : Integrate Machine Learning Models into Your App. https:\/\/developer.apple.com\/documentation\/coreml"},{"key":"e_1_3_2_1_3_1","volume-title":"ONNX : Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx","author":"Bai Junjie","year":"2019","unstructured":"Junjie Bai, Fang Lu, and Ke Zhang. 2019. ONNX : Open Neural Network Exchange. https:\/\/github.com\/onnx\/onnx"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Angels Balaguer Vinamra Benara Renato Luiz de Freitas Cunha Roberto de M. Estev ao Filho Todd Hendry Daniel Holstein Jennifer Marsman Nick Mecklenburg Sara Malvar Leonardo O. Nunes Rafael Padilha Morris Sharp Bruno Silva Swati Sharma Vijay Aski and Ranveer Chandra. 2024. RAG vs Fine-tuning : Pipelines Tradeoffs and a Case Study on Agriculture. (2024). https:\/\/doi.org\/10.48550\/ARXIV.2401.08406","DOI":"10.48550\/ARXIV.2401.08406"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/357489.357513"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nphys1130"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066289"},{"key":"e_1_3_2_1_8_1","unstructured":"Harrison Chase. 2022. LangChain : Building Applications with LLMs through Composability. https:\/\/github.com\/langchain-ai\/langchain"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357208"},{"key":"e_1_3_2_1_10_1","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM : An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_2_1_11_1","volume-title":"Challenges of Large Language Models for Mental Health Counseling. arXiv 2311.13857","author":"Chung Neo Christopher","year":"2023","unstructured":"Neo Christopher Chung, George Dyer, and Lennart Brocki. 2023. Challenges of Large Language Models for Mental Health Counseling. arXiv 2311.13857 (2023). http:\/\/arxiv.org\/abs\/2311.13857"},{"key":"e_1_3_2_1_12_1","volume-title":"The Power of Noise : Redefining Retrieval for RAG Systems. 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 2401.14887 (2024). http:\/\/arxiv.org\/abs\/2401.14887"},{"key":"e_1_3_2_1_13_1","volume-title":"Cross-Platform JavaScript Runtime Environment.","author":"Dahl Ryan","year":"2009","unstructured":"Ryan Dahl. 2009. Node.Js: An Open-Source, Cross-Platform JavaScript Runtime Environment. (2009). https:\/\/nodejs.org\/en\/"},{"key":"e_1_3_2_1_14_1","first-page":"08281","volume":"240","author":"Douze Matthijs","year":"2024","unstructured":"Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazar\u00e9, Maria Lomeli, Lucas Hosseini, and Herv\u00e9 J\u00e9gou. 2024. The Faiss Library. arXiv 2401.08281 (2024). http:\/\/arxiv.org\/abs\/2401.08281","journal-title":"Xiv"},{"key":"e_1_3_2_1_15_1","volume-title":"arXiv 2310.06556","author":"Draxler Fiona","year":"2023","unstructured":"Fiona Draxler, Daniel Buschek, Mikke Tavast, Perttu H\"am\"al\"ainen, Albrecht Schmidt, Juhi Kulshrestha, and Robin Welsch. 2023. Gender, Age, and Technology Education Influence the Adoption and Appropriation of LLMs. arXiv 2310.06556 (2023). http:\/\/arxiv.org\/abs\/2310.06556"},{"key":"e_1_3_2_1_16_1","volume-title":"React: The Library for Web and Native User Interfaces. https:\/\/react.dev\/","year":"2013","unstructured":"Facebook. 2013. React: The Library for Web and Native User Interfaces. https:\/\/react.dev\/"},{"key":"e_1_3_2_1_17_1","unstructured":"David Fahlander. 2021. Dexie.Js - Minimalistic IndexedDB Wrapper. https:\/\/dexie.org\/"},{"key":"e_1_3_2_1_18_1","volume-title":"Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. arXiv 2310.09235","author":"Feng Felicia Li","year":"2023","unstructured":"Felicia Li Feng, Ryan Yen, Yuzhe You, Mingming Fan, Jian Zhao, and Zhicong Lu. 2023. CoPrompt : Supporting Prompt Sharing and Referring in Collaborative Natural Language Programming. arXiv 2310.09235 (2023). http:\/\/arxiv.org\/abs\/2310.09235"},{"key":"e_1_3_2_1_19_1","unstructured":"Tiago Forte. 2022. Building a Second Brain: A Proven Method to Organize Your Digital Life and Unlock Your Creative Potential first atria books hardcover edition ed.). BF408"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/381854.381893"},{"key":"e_1_3_2_1_21_1","unstructured":"Georg Fuchsbauer Riddhi Ghosal Nathan Hauke and Adam O'Neill. 2021. Approximate Distance-Comparison-Preserving Symmetric Encryption. Cryptology ePrint Archive Paper 2021\/1666. https:\/\/eprint.iacr.org\/2021\/1666"},{"key":"e_1_3_2_1_22_1","volume-title":"Personalized Information Retrieval : Methods and Implications. arXiv 2311.12287","author":"Ghodratnama Samira","year":"2023","unstructured":"Samira Ghodratnama and Mehrdad Zakershahrak. 2023. Adapting LLMs for Efficient, Personalized Information Retrieval : Methods and Implications. arXiv 2311.12287 (2023). http:\/\/arxiv.org\/abs\/2311.12287"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412700"},{"key":"e_1_3_2_1_24_1","volume-title":"Lit: Simple Fast Web Components. https:\/\/lit.dev\/","year":"2015","unstructured":"Google. 2015. Lit: Simple Fast Web Components. https:\/\/lit.dev\/"},{"key":"e_1_3_2_1_25_1","volume-title":"Svelte: Cybernetically Enhanced Web Apps. https:\/\/svelte.dev\/","author":"Harris Rich","year":"2016","unstructured":"Rich Harris. 2016. Svelte: Cybernetically Enhanced Web Apps. https:\/\/svelte.dev\/"},{"key":"e_1_3_2_1_26_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Hashimoto Tatsunori B","year":"2018","unstructured":"Tatsunori B Hashimoto, Kelvin Guu, Yonatan Oren, and Percy S Liang. 2018. A Retrieve-and-Edit Framework for Predicting Structured Outputs. Advances in Neural Information Processing Systems , Vol. 31 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models. arXiv 2308.00675","author":"Hsieh Cheng-Yu","year":"2023","unstructured":"Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li, Yasuhisa Fujii, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, and Tomas Pfister. 2023. Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models. arXiv 2308.00675 (2023). http:\/\/arxiv.org\/abs\/2308.00675"},{"key":"e_1_3_2_1_28_1","volume-title":"Low-Rank Adaptation of Large Language Models. arXiv 2106.09685","author":"Hu Edward J.","year":"2021","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. LoRA : Low-Rank Adaptation of Large Language Models. arXiv 2106.09685 (2021). http:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1526709.1526817"},{"key":"e_1_3_2_1_32_1","volume-title":"Pgvector: Open-source Vector Similarity Search for Postgres. pgvector. https:\/\/github.com\/pgvector\/pgvector","author":"Kane Andrew","year":"2021","unstructured":"Andrew Kane. 2021. Pgvector: Open-source Vector Similarity Search for Postgres. pgvector. https:\/\/github.com\/pgvector\/pgvector"},{"key":"e_1_3_2_1_33_1","volume-title":"WASP : Web Archiving and Search Personalized. In DESIRES.","author":"Kiesel Johannes","year":"2018","unstructured":"Johannes Kiesel, Arjen P de Vries, Matthias Hagen, Benno Stein, and Martin Potthast. 2018. WASP : Web Archiving and Search Personalized. In DESIRES."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/35022643"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3233\/978--1--61499--649--1--87"},{"key":"e_1_3_2_1_36_1","volume-title":"Gu-Yeon Wei, David Brooks, and G. Edward Suh.","author":"Lam Maximilian","year":"2023","unstructured":"Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Yang Li, Liangzhen Lai, Ilias Leontiadis, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, and G. Edward Suh. 2023. GPU-based Private Information Retrieval for On-Device Machine Learning Inference. arXiv 2301.10904 (2023). http:\/\/arxiv.org\/abs\/2301.10904"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/383952.383972"},{"key":"e_1_3_2_1_38_1","volume-title":"The Power of Scale for Parameter-Efficient Prompt Tuning. arXiv 2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The Power of Scale for Parameter-Efficient Prompt Tuning. arXiv 2104.08691 (2021). http:\/\/arxiv.org\/abs\/2104.08691"},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","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\"aschel, et al. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. Advances in Neural Information Processing Systems , Vol. 33 (2020)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591799"},{"key":"e_1_3_2_1_41_1","volume-title":"2023 b. Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv 2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023 b. Towards General Text Embeddings with Multi-stage Contrastive Learning. arXiv 2308.03281 (2023). http:\/\/arxiv.org\/abs\/2308.03281"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_43_1","unstructured":"Joshua Lochner. 2023. Transformers.Js: State-of-the-art Machine Learning for the Web. https:\/\/github.com\/xenova\/transformers.js"},{"key":"e_1_3_2_1_44_1","volume-title":"Interspeech","author":"Macoskey Jonathan","year":"2021","unstructured":"Jonathan Macoskey, Grant Strimel, and Ariya Rastrow. 2021a. Learning a Neural Diff for Speech Models. In Interspeech 2021. https:\/\/www.amazon.science\/publications\/learning-a-neural-diff-for-speech-models"},{"key":"e_1_3_2_1_45_1","volume-title":"Interspeech","author":"Macoskey Jonathan","year":"2021","unstructured":"Jonathan Macoskey, Grant Strimel, Jinru Su, and Ariya Rastrow. 2021b. Amortized Neural Networks for Low-Latency Speech Recognition. In Interspeech 2021. https:\/\/www.amazon.science\/publications\/amortized-neural-networks-for-low-latency-speech-recognition"},{"key":"e_1_3_2_1_46_1","unstructured":"Ogier Maitre. 2018. Total Canvas Memory Use Exceeds the Maximum Limit (Safari 12) - Stack Overflow. https:\/\/stackoverflow.com\/questions\/52532614\/total-canvas-memory-use-exceeds-the-maximum-limit-safari-12"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_48_1","unstructured":"Kim Martineau. 2023. What Is Retrieval-Augmented Generation? https:\/\/research.ibm.com\/blog\/retrieval-augmented-generation-RAG"},{"key":"e_1_3_2_1_49_1","unstructured":"MDN. 2021. IndexedDB API - Web APIs. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/IndexedDB_API"},{"key":"e_1_3_2_1_50_1","unstructured":"MDN. 2023 a. Storage Quotas and Eviction Criteria - Web APIs textbar MDN. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Storage_API\/Storage_quotas_and_eviction_criteria"},{"key":"e_1_3_2_1_51_1","unstructured":"MDN. 2023 b. Streams API - Web APIs. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Streams_API"},{"key":"e_1_3_2_1_52_1","unstructured":"MDN. 2023 c. Web Workers API - Web APIs. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Web_Workers_API"},{"key":"e_1_3_2_1_53_1","unstructured":"Gavin Mendel-Gleason. 2024. Parallelising HNSW. https:\/\/github.com\/GavinMendelGleason\/blog\/blob\/main\/entries\/parallelising_hnsw.md"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","unstructured":"Arvind Neelakantan Tao Xu Raul Puri Alec Radford Jesse Michael Han Jerry Tworek Qiming Yuan Nikolas Tezak Jong Wook Kim Chris Hallacy Johannes Heidecke Pranav Shyam Boris Power Tyna Eloundou Nekoul Girish Sastry Gretchen Krueger David Schnurr Felipe Petroski Such Kenny Hsu Madeleine Thompson Tabarak Khan Toki Sherbakov Joanne Jang Peter Welinder and Lilian Weng. 2022. Text and Code Embeddings by Contrastive Pre-Training. (2022). https:\/\/doi.org\/10.48550\/ARXIV.2201.10005","DOI":"10.48550\/ARXIV.2201.10005"},{"key":"e_1_3_2_1_55_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv 2303.08774 (2023). http:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_56_1","volume-title":"Fine-Tuning or Retrieval ? Comparing Knowledge Injection in LLMs. arXiv 2312.05934","author":"Ovadia Oded","year":"2024","unstructured":"Oded Ovadia, Menachem Brief, Moshik Mishaeli, and Oren Elisha. 2024. Fine-Tuning or Retrieval ? Comparing Knowledge Injection in LLMs. arXiv 2312.05934 (2024). http:\/\/arxiv.org\/abs\/2312.05934"},{"key":"e_1_3_2_1_57_1","volume":"202","author":"Prince Michael H.","unstructured":"Michael H. Prince, Henry Chan, Aikaterini Vriza, Tao Zhou, Varuni K. Sastry, Matthew T. Dearing, Ross J. Harder, Rama K. Vasudevan, and Mathew J. Cherukara. 2023. Opportunities for Retrieval and Tool Augmented Large Language Models in Scientific Facilities. arXiv 2312.01291 (2023). http:\/\/arxiv.org\/abs\/2312.01291","journal-title":"Mathew J. Cherukara."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/78973.78977"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462987"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_61_1","volume-title":"TPTU : Large Language Model-based AI Agents for Task Planning and Tool Usage. arXiv 2308.03427","author":"Ruan Jingqing","year":"2023","unstructured":"Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Ziyue Li, Xingyu Zeng, and Rui Zhao. 2023. TPTU : Large Language Model-based AI Agents for Task Planning and Tool Usage. arXiv 2308.03427 (2023). http:\/\/arxiv.org\/abs\/2308.03427"},{"key":"e_1_3_2_1_62_1","unstructured":"RxDB. 2021. Why IndexedDB Is Slow and What to Use Instead. https:\/\/rxdb.info\/slow-indexeddb.html"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.157"},{"key":"e_1_3_2_1_64_1","volume-title":"Retrieval Augmentation Reduces Hallucination in Conversation. arXiv 2104.07567","author":"Shuster Kurt","year":"2021","unstructured":"Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. Retrieval Augmentation Reduces Hallucination in Conversation. arXiv 2104.07567 (2021). http:\/\/arxiv.org\/abs\/2104.07567"},{"key":"e_1_3_2_1_65_1","volume-title":"TensorFlow. Js: Machine Learning for the Web and Beyond. arXiv","author":"Smilkov Daniel","year":"2019","unstructured":"Daniel Smilkov, Nikhil Thorat, Yannick Assogba, Ann Yuan, Nick Kreeger, Ping Yu, Kangyi Zhang, Shanqing Cai, Eric Nielsen, David Soergel, Stan Bileschi, Michael Terry, Charles Nicholson, Sandeep N. Gupta, Sarah Sirajuddin, D. Sculley, Rajat Monga, Greg Corrado, Fernanda B. Vi\u00e9gas, and Martin Wattenberg. 2019. TensorFlow. Js: Machine Learning for the Web and Beyond. arXiv (2019). https:\/\/arxiv.org\/abs\/1901.05350"},{"key":"e_1_3_2_1_66_1","volume-title":"Seq2seq SQL Generation with Table Documentation. arXiv 2211.06193","author":"Soare Elena","year":"2022","unstructured":"Elena Soare, Iain Mackie, and Jeffrey Dalton. 2022. DocuT5 : Seq2seq SQL Generation with Table Documentation. arXiv 2211.06193 (2022). http:\/\/arxiv.org\/abs\/2211.06193"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153257"},{"key":"e_1_3_2_1_68_1","unstructured":"relax MLC team. 2023. MLC-LLM. https:\/\/github.com\/mlc-ai\/mlc-llm"},{"key":"e_1_3_2_1_69_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv 2307.09288 (2023). https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_70_1","volume-title":"Wordflow: Social Prompt Engineering for Large Language Models. arXiv 2401.14447","author":"Wang Zijie J.","year":"2024","unstructured":"Zijie J. Wang, Aishwarya Chakravarthy, David Munechika, and Duen Horng Chau. 2024. Wordflow: Social Prompt Engineering for Large Language Models. arXiv 2401.14447 (2024). http:\/\/arxiv.org\/abs\/2401.14447"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587362"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.50"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539074"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580816"},{"key":"e_1_3_2_1_75_1","unstructured":"Thomas Wilkerling. 2019. FlexSearch : Next-Generation Full Text Search Library for Browser and Node. Js. https:\/\/github.com\/nextapps-de\/flexsearch"},{"key":"e_1_3_2_1_76_1","volume-title":"Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective. arXiv 2311.15792","author":"Wutschitz Lukas","year":"2023","unstructured":"Lukas Wutschitz, Boris K\u00f6pf, Andrew Paverd, Saravan Rajmohan, Ahmed Salem, Shruti Tople, Santiago Zanella-B\u00e9guelin, Menglin Xia, and Victor R\u00fchle. 2023. Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective. arXiv 2311.15792 (2023). http:\/\/arxiv.org\/abs\/2311.15792"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580364"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"e_1_3_2_1_80_1","volume-title":"Generating Code by Retrieving the Docs. arXiv 2207.05987","author":"Zhou Shuyan","year":"2023","unstructured":"Shuyan Zhou, Uri Alon, Frank F. Xu, Zhiruo Wang, Zhengbao Jiang, and Graham Neubig. 2023. DocPrompting : Generating Code by Retrieving the Docs. arXiv 2207.05987 (2023). http:\/\/arxiv.org\/abs\/2207.05987"},{"key":"e_1_3_2_1_81_1","unstructured":"Eric Zhu. 2016. Ekzhu\/Datasketch: MinHash LSH LSH Forest Weighted MinHash HyperLogLog HyperLogLog LSH Ensemble and HNSW. https:\/\/github.com\/ekzhu\/datasketch"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657662","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:41:28Z","timestamp":1755841288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":81,"alternative-id":["10.1145\/3626772.3657662","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657662","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}