A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Open accessAbstract
Controllable Text Generation (CTG) is an emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used Transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the limited level of interpretability of deep neural networks, the controllability of these methods needs to be guaranteed. To this end, controllable text generation using Transformer-based PLMs has become a rapidly growing yet challenging new research hotspot. A diverse range of approaches have emerged in the past 3 to 4 years, targeting different CTG tasks that require different types of controlled constraints. In this article, we present a systematic critical review on the common tasks, main approaches, and evaluation methods in this area. Finally, we discuss the challenges that the field is facing, and put forward various promising future directions. To the best of our knowledge, this is the first survey article to summarize the state-of-the-art CTG techniques from the perspective of Transformer-based PLMs. We hope it can help researchers and practitioners in the related fields to quickly track the academic and technological frontier, providing them with a landscape of the area and a roadmap for future research.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prompt engineering techniques can effectively enhance large language models' ability to perform tasks, and well-designed prompts allow models to achieve better performance without modifying their core parameters.
“numerous studies have proved that well-designed prompts can significantly improve the performance of LLMs on these tasks.”
From Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style (2024) · cites this paper as [51]
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · see citing works
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · see citing works
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019) · arXiv · doi:10.48550/arxiv.1907.11692 · Cited by 16,515 · see citing works
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983 · see citing works
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 · see citing works
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 1× · see citing works
“Moreover, for ethical development [6] of AI applications, it is crucial to avoid generating mindless and offensive content such as gender bias, racial discrimination, and toxic words.”
BackgroundSurvey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · see citing works
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361 · see citing works
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352 · see citing works
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096 · see citing works
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590 · see citing works
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473 · see citing works
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · see citing works
Hierarchical Neural Story Generation
Fan, A., Lewis, M., & Dauphin, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.04833 · Cited by 1,242 · see citing works
How Can We Know What Language Models Know?
Jiang, Z., Xu, F. F., Araki, J., & Neubig, G. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00324 · Cited by 1,002 · see citing works
Learning to Ask: Neural Question Generation for Reading Comprehension
Du, X., Shao, J., & Cardie, C. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1123 · Cited by 696 · cited 1× · see citing works
“…it is essential to evaluate the quality of generated text in general aspects such as (1) fluency —how fluent the language in the output text is [12, 31], (2) factuality —to what extent the generated text reflects the facts described in the context [46, 146], (3) grammar : —how grammatically…”
BackgroundFine-Tuning Language Models from Human Preferences
Ziegler, D. M., Stiennon, N., Wu, J., Brown, T. B., Radford, A., Amodei, D., Christiano, P., & Irving, G. (2019) · arXiv · doi:10.48550/arxiv.1909.08593 · Cited by 413 · see citing works
Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses
Lowe, R., Noseworthy, M., Serban, I. V., Angelard-Gontier, N., Bengio, Y., & Pineau, J. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1103 · Cited by 341 · see citing works
Unifying Human and Statistical Evaluation for Natural Language Generation
Hashimoto, T. B., Zhang, H., & Liang, P. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1169 · Cited by 161 · see citing works
Self-citationControllable Natural Language Generation with Contrastive Prefixes
Qian, J., Dong, L., Shen, Y., Wei, F., & Chen, W. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.229 · Cited by 74 · see citing works
Plug-and-Blend: A Framework for Plug-and-Play Controllable Story Generation with Sketches
Lin, Z., & Riedl, M. O. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v17i1.18891 · Cited by 16 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376 · see citing works
Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilities
Ferrag, M. A., Alwahedi, F., Battah, A., Cherif, B., Mechri, A., Tihanyi, N., Bisztray, T., & Debbah, M. (2025) · Internet of Things and Cyber-Physical Systems · doi:10.1016/j.iotcps.2025.01.001 · Cited by 148 · see citing works
Language Model Behavior: A Comprehensive Survey
Chang, T. A., & Bergen, B. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00492 · Cited by 105 · see citing works
Veselovsky, V., Ribeiro, M. H., & West, R. (2023) · arXiv · doi:10.48550/arxiv.2306.07899 · Cited by 73 · see citing works
“Typically, these analyses have been done through a variant of controlled text generation (see Zhang et al. (2022) for a comprehensive review).”
Ouis, M. Y., & Akhloufi, M. A. (2024) · Frontiers in Imaging · doi:10.3389/fimag.2024.1373420 · Cited by 12 · see citing works
Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style
Chen, Z., & Moscholios, S. (2024) · arXiv · doi:10.48550/arxiv.2410.03848
“In the field of controllable text generation, prompt-based methods can be applied during the fine-tuning phase of large language models, which helps the model to generate text that meets the requirements of the original task [51].”
Method
- Authors
- Zhang, H., Song, H., Li, S., Zhou, M., & Song, D.
- Affiliations
- Beijing Institute of Technology (CN)
- Langboat Technology, China
- Venue
- ACM Computing Surveys
- Published
- 2023-10-06
- Volume
- 56
- Issue
- 3
- Pages
- 1-37
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4386290290
- Cited by
- 317
- References
- 23
- Citations by year
- 2026: 54 · 2025: 97 · 2024: 97 · 2023: 58 · 2022: 11
- FWCI
- 28.85
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion, public-domain)
- arXiv (Cornell University) (public-domain)
- Funders
- Natural Science Foundation of Beijing (4222036)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- controllable text generation, pre-trained language models, transformer models, natural language generation, controllability, generation constraints, assessment methods, interpretability
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
