Abstract
Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text generation framework grounded in pragmatics. RSA-Control directs the generation process by recursively reasoning between imaginary speakers and listeners, enhancing the likelihood that target attributes are correctly interpreted by listeners amidst distractors. Additionally, we introduce a self-adjustable rationality parameter, which allows for automatic adjustment of control strength based on context. Our experiments, conducted with two task types and two types of language models, demonstrate that RSA-Control achieves strong attribute control while maintaining language fluency and content consistency. Our code is available at https://github.com/Ewanwong/RSA-Control.- Anthology ID:
- 2024.emnlp-main.318
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5561–5582
- Language:
- URL:
- https://aclanthology.org/2024.emnlp-main.318
- DOI:
- 10.18653/v1/2024.emnlp-main.318
- Cite (ACL):
- Yifan Wang and Vera Demberg. 2024. RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5561–5582, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework (Wang & Demberg, EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.emnlp-main.318.pdf