Fetching the paper…
Reading the bibliography…
Machine learning community is discovering Contextual Integrity (CI) as a useful framework to assess the privacy implications of large language models (LLMs).
Privacy and the limits of law
Gavison, R · 1980
Earlier work this paper cites.
Privacy as contextual integrity
Nissenbaum, H · 2004
Earlier work this paper cites.
Privacy and contextual integrity: Framework and applications
Barth, A., Datta, A., Mitchell, J. C., and Nissenbaum, H · 2006
Earlier work this paper cites.
Privacy in context: Technology, policy, and the integrity of social life
Nissenbaum, H · 2009
Earlier work this paper cites.
Logical specification of the glba and hipaa privacy laws
DeYoung, H., Garg, D., Kaynar, D., and Datta, A · 2010
Earlier work this paper cites.
Law’s empire
Dworkin, R · 2013
Earlier work this paper cites.
Respect for context as a benchmark for privacy online: What it is and isn’t
Nissenbaum, H · 2015
Earlier work this paper cites.
Measuring privacy: An empirical test using context to expose confounding variables
Martin, K. and Nissenbaum, H · 2016
Earlier work this paper cites.
Learning privacy expectations by crowdsourcing contextual informational norms
Shvartzshnaider, Y., Tong, S., Wies, T., Kift, P., Nissenbaum, H., Subramanian, L., and Mittal, P · 2016
Earlier work this paper cites.
Contextual integrity through the lens of computer science
Benthall, S., Gürses, S., and Nissenbaum, H · 2017
Earlier work this paper cites.
Contextual integrity up and down the data food chain
Nissenbaum, H · 2019
Earlier work this paper cites.
VACCINE: Using Contextual Integrity ForData Leakage Detection
Shvartzshnaider, Y., Pavlinovic, Z., Balashankar, A., Wies, T., Subramanian, L., Nissenbaum, H., and Mittal, P · 2019
Earlier work this paper cites.
Individual acceptance of using health data for private and public benefit: Changes during the covid-19 pandemic
Gerdon, F., Nissenbaum, H., Bach, R. L., Kreuter, F., and Zins, S · 2020
Earlier work this paper cites.
More than just privacy: Using contextual integrity to evaluate the long-term risks from covid-19 surveillance technologies
Vitak, J. and Zimmer, M · 2020
Earlier work this paper cites.
Internet-augmented dialogue generation
Komeili, M., Shuster, K., and Weston, J · 2021
Earlier work this paper cites.
Apps against the spread: Privacy implications and user acceptance of covid-19-related smartphone apps on three continents
Utz, C., Becker, S., Schnitzler, T., Farke, F. M., Herbert, F., Schaewitz, L., Degeling, M., and Dürmuth, M · 2021
Earlier work this paper cites.
What does it mean for a language model to preserve privacy?
Brown, H., Lee, K., Mireshghallah, F., Shokri, R., and Tramèr, F · 2022
Earlier work this paper cites.
Foreword by Helen Nissenbaum. Modern Socio-Technical Perspectives on Privacy
Nissenbaum, H · 2022
Cited alongside, same era.
Talm: Tool augmented language models
Parisi, A., Zhao, Y., and Fiedel, N · 2022
Cited alongside, same era.
Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al · 2023
Cited alongside, same era.
Sensitivity and robustness of large language models to prompt template in Japanese text classification tasks
Gan, C. and Mori, T · 2023
Cited alongside, same era.
Pal: Program-aided language models
Gao, L., Madaan, A., Zhou, S., Alon, U., Liu, P., Yang, Y., Callan, J., and Neubig, G · 2023
Cited alongside, same era.
Social bias evaluation for large language models requires prompt variations
Hida, R., Kaneko, M., and Okazaki, N · 2024
Later among the works it cites.
Found in the middle: Calibrating positional attention bias improves long context utilization
Hsieh, C.-Y., Chuang, Y.-S., Li, C.-L., Wang, Z., Le, L. T., Kumar, A., Glass, J., Ratner, A., Lee, C.-Y., Krishna, R., et al · 2024
Later among the works it cites.
Privacy checklist: Privacy violation detection grounding on contextual integrity theory
Li, H., Fan, W., Chen, Y., Cheng, J., Chu, T., Zhou, X., Hu, P., and Song, Y · 2024
Later among the works it cites.
How are prompts different in terms of sensitivity?
Lu, S., Schuff, H., and Gurevych, I · 2024
Later among the works it cites.
State of what art? a call for multi-prompt llm evaluation
Mizrahi, M., Kaplan, G., Malkin, D., Dror, R., Shahaf, D., and Stanovsky, G · 2024
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Gemini-Team · 2023
Cited alongside, same era.
Exploring the sensitivity of LLMs’ decision-making capabilities: Insights from prompt variations and hyperparameters
Loya, M., Sinha, D., and Futrell, R · 2023
Cited alongside, same era.
Can llms keep a secret? testing privacy implications of language models via contextual integrity theory
Mireshghallah, N., Kim, H., Zhou, X., Tsvetkov, Y., Sap, M., Shokri, R., and Choi, Y · 2023
Cited alongside, same era.
On large language models’ selection bias in multi-choice questions
Zheng, C., Zhou, H., Meng, F., Zhou, J., and Huang, M · 2023
Cited alongside, same era.
Air Gap: Protecting Privacy-Conscious Conversational Agents, May 2024
Bagdasaryan, E., Yi, R., Ghalebikesabi, S., Kairouz, P., Gruteser, M., Oh, S., Balle, B., and Ramage, D · 2024
Cited alongside, same era.
On the worst prompt performance of large language models
Cao, B., Cai, D., Zhang, Z., Zou, Y., and Lam, W · 2024
Cited alongside, same era.
Ci-bench: Benchmarking contextual integrity of ai assistants on synthetic data
Cheng, Z., Wan, D., Abueg, M., Ghalebikesabi, S., Yi, R., Bagdasarian, E., Balle, B., Mellem, S., and O’Banion, S · 2024
Cited alongside, same era.
Later among the works it cites.
Protecting users from themselves: Safeguarding contextual privacy in interactions with conversational agents
Ngong, I. C., Kadhe, S., Wang, H., Murugesan, K., Weisz, J. D., Dhurandhar, A., and Ramamurthy, K. N · 2024
Later among the works it cites.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Reid, M., Savinov, N., Teplyashin, D., Lepikhin, D., Lillicrap, T., Alayrac, J.-b., Soricut, R., Lazaridou, A., Firat, O., Schrittwieser, J., et al · 2024
Later among the works it cites.
Toolformer: Language models can teach themselves to use tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Hambro, E., Zettlemoyer, L., Cancedda, N., and Scialom, T · 2024
Later among the works it cites.
Quantifying language models’ sensitivity to spurious features in prompt design or: How i learned to start worrying about prompt formatting
Sclar, M., Choi, Y., Tsvetkov, Y., and Suhr, A · 2024
Later among the works it cites.
Privacylens: Evaluating privacy norm awareness of language models in action
Shao, Y., Li, T., Shi, W., Liu, Y., and Yang, D · 2024
Later among the works it cites.
Shi, L., Ma, C., Liang, W., Ma, W., and Vosoughi, S · 2024
Later among the works it cites.
Privacy mini-publics: A deliberative democratic approach to understanding informational norms
Susser, D. and Bonotti, M · 2024
Later among the works it cites.
Mitigate position bias in large language models via scaling a single dimension
Yu, Y., Jiang, H., Luo, X., Wu, Q., Lin, C.-Y., Li, D., Yang, Y., Huang, Y., and Qiu, L · 2024
Later among the works it cites.
Can we instruct llms to compensate for position bias?
Zhang, M., Meng, Z., and Collier, N · 2024
Later among the works it cites.
ProSA: Assessing and understanding the prompt sensitivity of LLMs
Zhuo, J., Zhang, S., Fang, X., Duan, H., Lin, D., and Chen, K · 2024
Later among the works it cites.
Investigating privacy bias in training data of language models, 2025
Shvartzshnaider, Y. and Duddu, V · 2025
Closest in time.