Fetching the paper…
Reading the bibliography…
The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are expected to reason about what to share in their outputs, for what purpose and with whom, within a given context.
Does the chimpanzee have a theory of mind?
David Premack and Guy Woodruff · 1978
Earlier work this paper cites.
Interacting minds–a biological basis
Chris D. Frith and Uta Frith · 1999
Earlier work this paper cites.
Privacy as contextual integrity
Helen Nissenbaum · 2004
Earlier work this paper cites.
Worst-case background knowledge for privacy-preserving data publishing
David J Martin, Daniel Kifer, Ashwin Machanavajjhala, Johannes Gehrke, and Joseph Y Halpern · 2006
Earlier work this paper cites.
Privacy in Context: Technology, Policy, and the Integrity of Social Life
Helen Nissenbaum · 2009
Earlier work this paper cites.
An overview of the schwartz theory of basic values
Shalom H Schwartz · 2012
Earlier work this paper cites.
How virtual reality training can win friends and influence people
John Hart, J. Gratch, and Stacy Marsella · 2013
Earlier work this paper cites.
Public perceptions of privacy and security in the post-snowden era
Mary Madden · 2014
Earlier work this paper cites.
Deep learning with differential privacy
Martin Abadi, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang · 2016
Earlier work this paper cites.
Secret keepers: children’s theory of mind and their conception of secrecy
Malinda J Colwell, Kimberly Corson, Anuradha Sastry, and Holly Wright · 2016
Earlier work this paper cites.
Privacy management in agent-based social networks
Nadin Kökciyan · 2016
Earlier work this paper cites.
Measuring privacy: An empirical test using context to expose confounding variables
Kirsten Martin and Helen Nissenbaum · 2016
Earlier work this paper cites.
Being deceived: Information asymmetry in second-order false belief tasks
Torben Braüner, Patrick Blackburn, and Irina Polyanskaya · 2019
Earlier work this paper cites.
Vaccine: Using contextual integrity for data leakage detection
Yan Shvartzshnaider, Zvonimir Pavlinovic, Ananth Balashankar, Thomas Wies, Lakshminarayanan Subramanian, Helen Nissenbaum, and Prateek Mittal · 2019
Earlier work this paper cites.
A comparative analysis of speed and accuracy for three off-the-shelf de-identification tools
Paul M Heider, Jihad S Obeid, and Stéphane M Meystre · 2020
Earlier work this paper cites.
Retrieval-augmented generation for knowledge-intensive nlp tasks
Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al · 2020
Earlier work this paper cites.
Motivated secrecy: Politics, relationships, and regrets
Rachel I. McDonald, Jessica M. Salerno, Katharine H. Greenaway, and Michael L. Slepian · 2020
Earlier work this paper cites.
Large language models can be strong differentially private learners
Xuechen Li, Florian Tramer, Percy Liang, and Tatsunori Hashimoto · 2021
Earlier work this paper cites.
Selective differential privacy for language modeling
Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, and Zhou Yu · 2021
Cited alongside, same era.
Differentially private fine-tuning of language models
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, et al · 2021
Cited alongside, same era.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al · 2022
Cited alongside, same era.
What does it mean for a language model to preserve privacy?
Hannah Brown, Katherine Lee, Fatemehsadat Mireshghallah, Reza Shokri, and Florian Tramèr · 2022
Cited alongside, same era.
Chatgpt plugins
OpenAI · 2023
Closest in time.
Differentially private in-context learning
Ashwinee Panda, Tong Wu, Jiachen T Wang, and Prateek Mittal · 2023
Closest in time.
Samsung bans use of generative ai tools like chatgpt after april internal data leak
Kate Park · 2023
Closest in time.
Gorilla: Large language model connected with massive apis
Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez · 2023
Closest in time.
Aman Priyanshu, Supriti Vijay, Ayush Kumar, Rakshit Naidu, and Fatemehsadat Mireshghallah · 2023
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, and Chiyuan Zhang · 2022
Cited alongside, same era.
Chatgpt: Optimizing language models for dialogue, 2022
OpenAI · 2022
Cited alongside, same era.
Training language models to follow instructions with human feedback
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al · 2022
Cited alongside, same era.
Morality, punishment, and revealing other people’s secrets
Jessica M Salerno and Michael L Slepian · 2022
Cited alongside, same era.
Neural theory-of-mind? on the limits of social intelligence in large LMs
Maarten Sap, Ronan Le Bras, Daniel Fried, and Yejin Choi · 2022
Cited alongside, same era.
Chain-of-thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al · 2022
Cited alongside, same era.
Intelligent meeting recap in teams premium, now available
Meeraj Ajam · 2023
Cited alongside, same era.
Can language models be instructed to protect personal information?
Yang Chen, Ethan Mendes, Sauvik Das, Wei Xu, and Alan Ritter · 2023
Cited alongside, same era.
Melanie Sclar, Sachin Kumar, Peter West, Alane Suhr, Yejin Choi, and Yulia Tsvetkov · 2023
Closest in time.
Clever hans or neural theory of mind? stress testing social reasoning in large language models
Natalie Shapira, Mosh Levy, Seyed Hossein Alavi, Xuhui Zhou, Yejin Choi, Yoav Goldberg, Maarten Sap, and Vered Shwartz · 2023
Closest in time.
Data is what data does: Regulating use, harm, and risk instead of sensitive data
Daniel J Solove · 2023
Closest in time.
Privacy-preserving in-context learning with differentially private few-shot generation
Xinyu Tang, Richard Shin, Huseyin A Inan, Andre Manoel, Fatemehsadat Mireshghallah, Zinan Lin, Sivakanth Gopi, Janardhan Kulkarni, and Robert Sim · 2023
Closest in time.
Llama: Open and efficient foundation language models
Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al · 2023
Closest in time.
Large language models fail on trivial alterations to theory-of-mind tasks
Tomer Ullman · 2023
Closest in time.
Large language models as optimizers
Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen · 2023
Closest in time.
COBRA frames: Contextual reasoning about effects and harms of offensive statements
Xuhui Zhou, Hao Zhu, Akhila Yerukola, Thomas Davidson, Jena D. Hwang, Swabha Swayamdipta, and Maarten Sap · 2023
Closest in time.
Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al · 2024
Closest in time.
Zhenting Qi, Hanlin Zhang, Eric Xing, Sham Kakade, and Himabindu Lakkaraju · 2024
Closest in time.
(inthe)wildchat: 570k chatGPT interaction logs in the wild
Wenting Zhao, Xiang Ren, Jack Hessel, Claire Cardie, Yejin Choi, and Yuntian Deng · 2024
Closest in time.
Zoom ai companion hits one million meeting summaries milestone
Zoom · 2024
Closest in time.