Improving Controllable Text Generation with Position-Aware Weighted Decoding
Open accessAbstract
Weighted decoding methods composed of the pretrained language model (LM) and the controller have achieved promising results for controllable text generation.However, these models often suffer from a control strength/fluency trade-off problem as higher control strength is more likely to generate incoherent and repetitive text.In this paper, we illustrate this tradeoff is arisen by the controller imposing the target attribute on the LM at improper positions.And we propose a novel framework based on existing weighted decoding methods called CAT-PAW 1 , which introduces a lightweight regulator to adjust bias signals from the controller at different decoding positions.Experiments on positive sentiment control, topic control, and language detoxification show the effectiveness of our CAT-PAW upon 4 SOTA models 2 .
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
There is an inherent trade-off between diversity and context attribution; overemphasizing contextual information can reduce diversity.
“However, due to the inherent trade-off between diversity and context attribution [103, 363], overemphasizing contextual information can reduce diversity.”
From A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2025) · cites this paper as [103]
The Introduction (page unavailable) reports that stronger attribute control can produce repetitive text, which supports the possibility of reduced diversity. But the paper frames its central trade-off as control strength versus fluency, not diversity versus context attribution, and does not identify overemphasis on contextual information as the cause. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
No citation lists for this paper
No citation lists for this paper yet — checked again daily.
References 30 · Cited by 12
Research works printed but not linked: 28
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems, volume 33, pages 1877-1901.
- Curran Associates, Inc. Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu. 2020. Plug and play language models: A simple approach to controlled text generation. In International Conference on Learning Representa- tions.
- William Fedus, Barret Zoph, and Noam Shazeer. 2021. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. arXiv preprint arXiv:2101.03961. · arXiv
- Jessica Ficler and Yoav Goldberg. 2017. Controlling linguistic style aspects in neural language generation. In Proceedings of the Workshop on Stylistic Variation, pages 94-104, Copenhagen, Denmark. Association for Computational Linguistics. · DOI
- Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A. Smith. 2020. RealToxi- cityPrompts: Evaluating neural toxic degeneration in language models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3356-3369, Online. Association for Computational Linguistics. · DOI · Paper page
- Sayan Ghosh, Mathieu Chollet, Eugene Laksana, Louis- Philippe Morency, and Stefan Scherer. 2017. Affect- LM: A neural language model for customizable af- fective text generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 634-642, Vancouver, Canada. Association for Computational Linguistics. · DOI
- Ruining He and Julian McAuley. 2016. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web, pages 507-517.
- Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward con- trolled generation of text. In International Con- ference on Machine Learning, pages 1587-1596.
- PMLR.
- Nitish Shirish Keskar, Bryan McCann, Lav Varsh- ney, Caiming Xiong, and Richard Socher. 2019. CTRL -A Conditional Transformer Language Model for Controllable Generation. arXiv preprint arXiv:1909.05858. · arXiv
- Muhammad Khalifa, Hady Elsahar, and Marc Dymet- man. 2021. A distributional approach to controlled text generation. In International Conference on Learning Representations.
- Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, and Nazneen Fatema Rajani. 2020. Gedi: Generative discriminator guided sequence generation. arXiv preprint arXiv:2009.06367. · arXiv
- Guillaume Lample, Sandeep Subramanian, Eric Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, and Y-Lan Boureau. 2019. Multiple-attribute text rewriting. In International Conference on Learning Representa- tions.
- Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting ob- jective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computa- tional Linguistics: Human Language Technologies, pages 110-119, San Diego, California. Association for Computational Linguistics. · DOI
- Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, and Yejin Choi. 2021a. DExperts: Decoding-time controlled text generation with experts and anti- experts. In Proceedings of the 59th Annual Meet- ing of the Association for Computational Linguistics and the 11th International Joint Conference on Natu- ral Language Processing (Volume 1: Long Papers), pages 6691-6706, Online. Association for Computa- tional Linguistics. · DOI
- Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021b. Pre- train, prompt, and predict: A systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586. · arXiv
- Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Dan Huang, Andrew Y. Ng, and Christopher Potts. 2011. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 142-150, Portland, Oregon, USA. Association for Computational Lin- guistics.
- Eric Malmi, Aliaksei Severyn, and Sascha Rothe. 2020. Unsupervised text style transfer with padded masked language models. In Proceedings of the 2020 Con- ference on Empirical Methods in Natural Language Processing (EMNLP), pages 8671-8680, Online. As- sociation for Computational Linguistics. · DOI
- Shrimai Prabhumoye, Alan W Black, and Ruslan Salakhutdinov. 2020. Exploring controllable text generation techniques. In Proceedings of the 28th International Conference on Computational Linguis- tics, pages 1-14, Barcelona, Spain (Online). Interna- tional Committee on Computational Linguistics. · DOI
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9.
- Machel Reid and Victor Zhong. 2021. LEWIS: Lev- enshtein editing for unsupervised text style transfer. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3932-3944, Online. Association for Computational Linguistics. · DOI
- Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng. 2020. Towards Controllable Biases in Language Generation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3239-3254, Online. Association for Computational Linguistics. · DOI
- Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empiri- cal Methods in Natural Language Processing, pages 1631-1642, Seattle, Washington, USA. Association for Computational Linguistics.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information pro- cessing systems, pages 5998-6008.
- Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gard- ner, and Sameer Singh. 2019. Universal adversarial triggers for attacking and analyzing NLP. In Proceed- ings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Inter- national Joint Conference on Natural Language Pro- cessing (EMNLP-IJCNLP), pages 2153-2162, Hong Kong, China. Association for Computational Linguis- tics. · DOI · Paper page
- Xing Wu, Tao Zhang, Liangjun Zang, Jizhong Han, and Songlin Hu. 2019. Mask and infill: Applying masked language model for sentiment transfer. In Proceed- ings of the Twenty-Eighth International Joint Con- ference on Artificial Intelligence, IJCAI-19, pages 5271-5277. International Joint Conferences on Arti- ficial Intelligence Organization. · DOI
- Kevin Yang and Dan Klein. 2021. Fudge: Controlled text generation with future discriminators. In Pro- ceedings of the 2021 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3511-3535.
- Dian Yu, Kenji Sagae, and Zhou Yu. 2021. At- tribute alignment: Controlling text generation from pre-trained language models. arXiv preprint arXiv:2103.11070. · arXiv
- Authors
- Gu, Y., Feng, X., Ma, S., Wu, J., Gong, H., & Qin, B.
- Affiliations
- Harbin Institute of Technology (CN)
- Venue
- Findings of the Association for Computational Linguistics: ACL 2022
- Published
- 2022
- Pages
- 3449-3467
- OpenAlex
- W4285286564
- Cited by
- 12
- References
- 30
- Citations by year
- 2025: 3 · 2024: 2 · 2023: 7
- FWCI
- 1.66
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: ACL (Findings of ACL) (publishedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (61976073)
- 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, sentiment control, topic management
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
