Reverse Engineering Configurations of Neural Text Generation Models
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
This paper seeks to develop a deeper understanding of the fundamental properties of neural text generations models.The study of artifacts that emerge in machine generated text as a result of modeling choices is a nascent research area.Previously, the extent and degree to which these artifacts surface in generated text has not been well studied.In the spirit of better understanding generative text models and their artifacts, we propose the new task of distinguishing which of several variants of a given model generated a piece of text, and we conduct an extensive suite of diagnostic tests to observe whether modeling choices (e.g., sampling methods, top-k probabilities, model architectures, etc.) leave detectable artifacts in the text they generate.Our key finding, which is backed by a rigorous set of experiments, is that such artifacts are present and that different modeling choices can be inferred by observing the generated text alone.This suggests that neural text generators may be more sensitive to various modeling choices than previously thought.
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
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1082 · Cited by 1,266
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242
A survey of modern authorship attribution methods
Stamatatos, E. (2009) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21001 · Cited by 1,176
CTRL: A Conditional Transformer Language Model for Controllable Generation
Keskar, N. S., McCann, B., Varshney, L. R., Xiong, C., & Socher, R. (2019) · arXiv · doi:10.48550/arxiv.1909.05858 · Cited by 751
Defending Against Neural Fake News
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1905.12616 · Cited by 569
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3019 · Cited by 470 · cited 3×
“The study of sampling methods for auto-regressive models has also been active where sampling methods such as top-k (Fan et al., 2018) and nucleus sampling (Holtzman et al., 2019) have been proposed.”
BackgroundMethodGLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. M. (2019) · arXiv · doi:10.48550/arxiv.1906.04043 · Cited by 460
Automatic Detection of Generated Text is Easiest when Humans are Fooled
Ippolito, D., Duckworth, D., Callison-Burch, C., & Eck, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.164 · Cited by 264
Neural Text Generation with Unlikelihood Training
Welleck, S., Kulikov, I., Roller, S., Dinan, E., Cho, K., & Weston, J. (2019) · arXiv · doi:10.48550/arxiv.1908.04319 · Cited by 254
Cited by
Machine-Generated Text: A Comprehensive Survey of Threat Models and Detection Methods
Crothers, E. N., Japkowicz, N., & Viktor, H. L. (2023) · IEEE Access · doi:10.1109/access.2023.3294090 · Cited by 196
Automatic Detection of Machine Generated Text: A Critical Survey
Jawahar, G., Abdul-Mageed, M., & Lakshmanan, V. S. (2020) · Proceedings of the 28th International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.208 · Cited by 156
A Watermark for Large Language Models
Kirchenbauer, J., Geiping, J., Wen, Y., Katz, J., Miers, I., & Goldstein, T. (2023) · arXiv · doi:10.48550/arxiv.2301.10226 · Cited by 194
“Implementation details, such as sampling strategies, can be reverse-engineered from text (Tay et al., 2020).”
Ibrahim, K. (2023) · Language Testing in Asia · doi:10.1186/s40468-023-00260-2 · Cited by 66
CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTracts
Yu, P., Chen, J., Feng, X., & Xia, Z. (2023) · arXiv · doi:10.48550/arxiv.2304.12008 · Cited by 45
Metadata
- Authors
- Tay, Y., Bahri, D., Zheng, C., Brunk, C., Metzler, D., & Tomkins, A.
- Venue
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Published
- 2020
- Pages
- 275-279
- OpenAlex
- W3034470897
- Cited by
- 19
- References
- 11
- FWCI
- 1.21
- 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: Reverse Engineering Configurations of Neural Text Generation Models. https://app.cochat.ai/papers/10.18653/v1/2020.acl-main.25
- The paper
- Tay, Y., Bahri, D., Zheng, C., Brunk, C., Metzler, D., & Tomkins, A. (2020). Reverse Engineering Configurations of Neural Text Generation Models. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-main.25
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.