Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 65 tok/s
Gemini 2.5 Pro 51 tok/s Pro
GPT-5 Medium 32 tok/s Pro
GPT-5 High 29 tok/s Pro
GPT-4o 80 tok/s Pro
Kimi K2 182 tok/s Pro
GPT OSS 120B 453 tok/s Pro
Claude Sonnet 4.5 34 tok/s Pro
2000 character limit reached

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework (2410.19109v1)

Published 24 Oct 2024 in cs.AI and cs.CL

Abstract: Despite significant advancements in natural language generation, controlling LLMs 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 LLMs, 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Jacob Andreas and Dan Klein. 2016. Reasoning about pragmatics with neural listeners and speakers. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1173–1182, Austin, Texas. Association for Computational Linguistics.
  3. Director: Generator-classifiers for supervised language modeling. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 512–526, Online only. Association for Computational Linguistics.
  4. Language (technology) is power: A critical survey of “bias” in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454–5476, Online. Association for Computational Linguistics.
  5. Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc.
  6. Inference time style control for summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5942–5953, Online. Association for Computational Linguistics.
  7. Readability Revisited: The New Dale-Chall Readability Formula. Brookline Books.
  8. Reuben Cohn-Gordon and Noah Goodman. 2019. Lost in machine translation: A method to reduce meaning loss. In 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), pages 437–441, Minneapolis, Minnesota. Association for Computational Linguistics.
  9. Pragmatically informative image captioning with character-level inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 439–443, New Orleans, Louisiana. Association for Computational Linguistics.
  10. An incremental iterated response model of pragmatics. In Proceedings of the Society for Computation in Linguistics (SCiL) 2019, pages 81–90.
  11. Meri Coleman and Ta Lin Liau. 1975. A computer readability formula designed for machine scoring. Journal of Applied Psychology, 60(2):283.
  12. Plug and play language models: A simple approach to controlled text generation. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  13. How much does it help to know what she knows you know? an agent-based simulation study. Artificial Intelligence, 199:67–92.
  14. Controlled text generation via language model arithmetic. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
  15. 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.
  16. Michael C Frank. 2016. Rational speech act models of pragmatic reasoning in reference games.
  17. Michael C Frank and Noah D Goodman. 2012. Predicting pragmatic reasoning in language games. Science, 336(6084):998–998.
  18. Michael Franke and Judith Degen. 2016. Reasoning in reference games: Individual-vs. population-level probabilistic modeling. PloS one, 11(5):e0154854.
  19. RealToxicityPrompts: 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.
  20. Overview of the biolaysumm 2023 shared task on lay summarization of biomedical research articles. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 468–477, Toronto, Canada. Association for Computational Linguistics.
  21. Making science simple: Corpora for the lay summarisation of scientific literature. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10589–10604, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  22. HydraSum: Disentangling style features in text summarization with multi-decoder models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 464–479, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  23. R. Gunning. 1952. The Technique of Clear Writing. McGraw-Hill.
  24. Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8342–8360, Online. Association for Computational Linguistics.
  25. Teaching machines to read and comprehend. In Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc.
  26. Mistral 7b. arXiv preprint arXiv:2310.06825.
  27. Formalizing the pragmatics of metaphor understanding. In Proceedings of the annual meeting of the Cognitive Science Society, volume 36.
  28. Nonliteral understanding of number words. Proceedings of the National Academy of Sciences, 111(33):12002–12007.
  29. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858.
  30. Will I sound like me? improving persona consistency in dialogues through pragmatic self-consciousness. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 904–916, Online. Association for Computational Linguistics.
  31. Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2227–2240, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  32. Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel.
  33. Michal Kosinski. 2023. Evaluating large language models in theory of mind tasks. arXiv e-prints, pages arXiv–2302.
  34. GeDi: Generative discriminator guided sequence generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4929–4952, Punta Cana, Dominican Republic. Association for Computational Linguistics.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Authors (2)

  1. Yifan Wang
  2. Vera Demberg
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up