Text Embeddings Reveal (Almost) As Much As Text
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
How much private information do text embeddings reveal about the original text?We investigate the problem of embedding inversion, reconstructing the full text represented in dense text embeddings.We frame the problem as controlled generation: generating text that, when reembedded, is close to a fixed point in latent space.We find that although a naïve model conditioned on the embedding performs poorly, a multi-step method that iteratively corrects and re-embeds text is able to recover 92% of 32-token text inputs exactly.We train our model to decode text embeddings from two state-of-the-art embedding models, and also show that our model can recover important personal information (full names) from a dataset of clinical notes. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Dense passage retrieval for open-domain question answering
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., & Yih, W.-T. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.550 · Cited by 3,575
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Bajaj, P., Campos, D., Craswell, N., Deng, L., Gao, J., Liu, X., Majumder, R., McNamara, A., Mitra, B., Nguyen, T., et al. (2016) · arXiv · doi:10.48550/arxiv.1611.09268 · Cited by 2,473
Natural Questions: A benchmark for question answering research
Kwiatkowski, T., Palomaki, J., Redfield, O., Collins, M., Parikh, A., Alberti, C., Epstein, D., Polosukhin, I., Devlin, J., Lee, K., et al. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00276 · Cited by 2,069
Zhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
Self-citationReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
MTEB: Massive Text Embedding Benchmark
Muennighoff, N., Tazi, N., Magne, L., & Reimers, N. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.148 · Cited by 548
Plug and Play Language Models: A Simple Approach to Controlled Text Generation
Dathathri, S., Madotto, A., Lan, J., Hung, J., Frank, E., Molino, P., Yosinski, J., & Liu, R. (2019) · arXiv · doi:10.48550/arxiv.1912.02164 · Cited by 508
Cited by
AI agents under threat: A survey of key security challenges and future pathways
Deng, Z., Guo, Y., Han, C., Ma, W., Xiong, J., Wen, S., & Xiang, Y. (2025) · ACM Computing Surveys · doi:10.1145/3716628 · Cited by 210
Deng, Z., Sun, R., Xue, M., Ma, W., Wen, S., Nepal, S., & Xiang, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3581103 · Cited by 36
The Memorization Problem: Can We Trust LLMs' Economic Forecasts?
Lopez-Lira, A., Tang, Y., & Zhu, M. (2025) · doi:10.2139/ssrn.5217505 · Cited by 36
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pang, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.09648 · Cited by 34
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
Yu, M., Meng, F., Zhou, X., Wang, S., Mao, J., Pan, L., Chen, T., Wang, K., Li, X., Zhang, Y., et al. (2025) · Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · doi:10.1145/3711896.3736561 · Cited by 34
Metadata
- Authors
- Morris, J., Kuleshov, V., Shmatikov, V., & Rush, A.
- Venue
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Published
- 2023
- Pages
- 12448-12460
- OpenAlex
- W4389520346
- Cited by
- 90
- References
- 14
- FWCI
- 17.01
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Text Embeddings Reveal (Almost) As Much As Text. https://app.cochat.ai/papers/10.18653/v1/2023.emnlp-main.765
- The paper
- Morris, J., Kuleshov, V., Shmatikov, V., & Rush, A. (2023). Text Embeddings Reveal (Almost) As Much As Text. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2023.emnlp-main.765
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.