Mova0.5 pre-release⌕
☰
home / docs / papers / English / RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework

What it is about

RSA-Control steers a pretrained language model towards a target attribute (for example non-toxic, or easy to read) without training a classifier. A literal speaker is the same model prompted with an attribute description; a pragmatic listener is a generative classifier that infers the attribute from the words so far, against distractor attributes; a pragmatic speaker picks each next token that the listener is likely to read as the target, weighted by a rationality parameter. This parameter is adjusted per step within a range, using two ratios that check content fit and attribute recognition. On the challenging RealToxicityPrompts subset (1,199 prompts) the average toxicity probability is 22.2% for GPT2-large without control and 8.8% with RSA-Control (range 15 to 25). In readability-controlled summarisation with Llama-2, the Flesch Reading Ease of readable summaries rises from 76.07 (prompting) to 79.58.

Ideas

For Mova

Chapters: 32. Politeness and hedging (the polite and respectful register), 37. Register and variation, 31. Speech acts. Code: a listener over frames in prag, candidate realisations from en/src/lin.rs, story text in world/src/story.rs. Measure: the listener's attribute accuracy on held-out sentences (the paper reports about 75% for its listener across model sizes), with the shuffled-label control.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2024.emnlp-main.318 · arXiv 2410.19109

@inproceedings{wang2024rsa,
  title = {{RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework}},
  author = {Wang, Yifan and Demberg, Vera},
  booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  year = {2024},
  doi = {10.18653/v1/2024.emnlp-main.318},
  eprint = {2410.19109},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2024.emnlp-main.318}
}

References

75 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. 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. find
  3. Kushal Arora, Kurt Shuster, Sainbayar Sukhbaatar, and Jason Weston. 2022. 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. find
  4. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. 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. find
  5. 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, Mateusz 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 Advances in Neural Information Processing Systems, volume 33, pages 1877–1901. Curran Associates, Inc. find
  6. Shuyang Cao and Lu Wang. 2021. 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. find
  7. J.S. Chall and E. Dale. 1995. Readability Revisited: The New Dale-Chall Readability Formula. Brookline Books. find
  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. find
  9. Reuben Cohn-Gordon, Noah Goodman, and Christopher Potts. 2018. 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. find
  10. Reuben Cohn-Gordon, Noah Goodman, and Christopher Potts. 2019. An incremental iterated response model of pragmatics. In Proceedings of the Society for Computation in Linguistics (SCiL) 2019, pages 81–90. find
  11. Meri Coleman and Ta Lin Liau. 1975. A computer readability formula designed for machine scoring. Journal of Applied Psychology, 60(2):283. find
  12. 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 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. find
  13. Harmen De Weerd, Rineke Verbrugge, and Bart Verheij. 2013. How much does it help to know what she knows you know? an agent-based simulation study. Artificial Intelligence, 199:67–92. find
  14. Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, and Martin T. Vechev. 2024. 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. find
  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. find
  16. Michael C Frank. 2016. Rational speech act models of pragmatic reasoning in reference games. find
  17. Michael C Frank and Noah D Goodman. 2012. Predicting pragmatic reasoning in language games. Science, 336(6084):998–998. find
  18. Michael Franke and Judith Degen. 2016. Reasoning in reference games: Individual-vs. population-level probabilistic modeling. PloS one, 11(5):e0154854. find
  19. Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A. Smith. 2020. 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. find
  20. Tomas Goldsack, Zheheng Luo, Qianqian Xie, Carolina Scarton, Matthew Shardlow, Sophia Ananiadou, and Chenghua Lin. 2023. 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. find
  21. Tomas Goldsack, Zhihao Zhang, Chenghua Lin, and Carolina Scarton. 2022. 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. find
  22. Tanya Goyal, Nazneen Rajani, Wenhao Liu, and Wojciech Kryscinski. 2022. 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. find
  23. R. Gunning. 1952. The Technique of Clear Writing. McGraw-Hill. find
  24. Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. 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. find
  25. Karl Moritz Hermann, Tomas Kocisky, Edward Grefenstette, Lasse Espeholt, Will Kay, Mustafa Suleyman, and Phil Blunsom. 2015. Teaching machines to read and comprehend. In Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc. find
  26. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. ↗
  27. Justine Kao, Leon Bergen, and Noah Goodman. 2014a. Formalizing the pragmatics of metaphor understanding. In Proceedings of the annual meeting of the Cognitive Science Society, volume 36. find
  28. Justine T Kao, Jean Y Wu, Leon Bergen, and Noah D Goodman. 2014b. Nonliteral understanding of number words. Proceedings of the National Academy of Sciences, 111(33):12002–12007. find our card
  29. Nitish Shirish Keskar, Bryan McCann, Lav R Varshney, Caiming Xiong, and Richard Socher. 2019. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858. ↗
  30. Hyunwoo Kim, Byeongchang Kim, and Gunhee Kim. 2020. 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. find
  31. Hyunwoo Kim, Byeongchang Kim, and Gunhee Kim. 2021. 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. find
  32. J Peter Kincaid, Robert P Fishburne Jr, Richard L Rogers, and Brad S Chissom. 1975. Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel. find
  33. Michal Kosinski. 2023. Evaluating large language models in theory of mind tasks. arXiv e-prints, pages arXiv–2302. find
  34. Ben Krause, Akhilesh Deepak Gotmare, Bryan McCann, Nitish Shirish Keskar, Shafiq Joty, Richard Socher, and Nazneen Fatema Rajani. 2021. 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. find
  35. Sachin Kumar, Vidhisha Balachandran, Lucille Njoo, Antonios Anastasopoulos, and Yulia Tsvetkov. 2023. Language generation models can cause harm: So what can we do about it? an actionable survey. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3299–3321, Dubrovnik, Croatia. Association for Computational Linguistics. find
  36. Philippe Laban, Tobias Schnabel, Paul N. Bennett, and Marti A. Hearst. 2022. Summac: Re-visiting nli-based models for inconsistency detection in summarization. Transactions of the Association for Computational Linguistics, 10:163–177. find
  37. Daniel Lassiter and Noah D Goodman. 2013. Context, scale structure, and statistics in the interpretation of positive-form adjectives. In Semantics and linguistic theory, pages 587–610. find
  38. Chak Tou Leong, Yi Cheng, Jiashuo Wang, Jian Wang, and Wenjie Li. 2023. Self-detoxifying language models via toxification reversal. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4433–4449, Singapore. Association for Computational Linguistics. 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6691–6706, Online. Association for Computational Linguistics. find
  39. Zheheng Luo, Qianqian Xie, and Sophia Ananiadou. 2022. Readability controllable biomedical document summarization. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4667–4680, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  40. Justus Mattern, Zhijing Jin, Mrinmaya Sachan, Rada Mihalcea, and Bernhard Schölkopf. 2022. Understanding stereotypes in language models: Towards robust measurement and zero-shot debiasing. arXiv preprint arXiv:2212.10678. ↗
  41. Tao Meng, Sidi Lu, Nanyun Peng, and Kai-Wei Chang. 2022. Controllable text generation with neurally-decomposed oracle. In Advances in Neural Information Processing Systems, volume 35, pages 28125– 28139. Curran Associates, Inc. find
  42. Fatemehsadat Mireshghallah, Kartik Goyal, and Taylor Berg-Kirkpatrick. 2022. Mix and match: Learning-free controllable text generationusing energy language models. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 401–415, Dublin, Ireland. Association for Computational Linguistics. find
  43. Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R. Bowman. 2020. CrowS-pairs: A challenge dataset for measuring social biases in masked language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1953–1967, Online. Association for Computational Linguistics. find
  44. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, volume 35, pages 27730–27744. Curran Associates, Inc. find
  45. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics. find
  46. Jonathan Pei, Kevin Yang, and Dan Klein. 2023. PREADD: Prefix-adaptive decoding for controlled text generation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 10018– 10037, Toronto, Canada. Association for Computational Linguistics. find
  47. Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, and Yejin Choi. 2021. DExperts: Decoding-time controlled text generation with experts and anti-experts. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the Luiza Pozzobon, Beyza Ermis, Patrick Lewis, and Sara Hooker. 2023a. Goodtriever: Adaptive toxicity mitigation with retrieval-augmented models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5108–5125, Singapore. Association for Computational Linguistics. find
  48. Luiza Pozzobon, Beyza Ermis, Patrick Lewis, and Sara Hooker. 2023b. On the challenges of using black-box APIs for toxicity evaluation in research. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7595–7609, Singapore. Association for Computational Linguistics. find
  49. Dongqi Pu and Vera Demberg. 2023. ChatGPT vs human-authored text: Insights into controllable text summarization and sentence style transfer. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 1–18, Toronto, Canada. Association for Computational Linguistics. find
  50. Timo Schick, Sahana Udupa, and Hinrich Schütze. 2021. Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in NLP. Transactions of the Association for Computational Linguistics, 9:1408– 1424. find
  51. Sheng Shen, Daniel Fried, Jacob Andreas, and Dan Klein. 2019. Pragmatically informative text generation. 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 4060–4067, Minneapolis, Minnesota. Association for Computational Linguistics. find our card
  52. Dongqi Pu, Yifan Wang, Jia E. Loy, and Vera Demberg. 2024. SciNews: From scholarly complexities to public narratives – a dataset for scientific news report generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14429–14444, Torino, Italia. ELRA and ICCL. find
  53. Emily Sheng, Kai-Wei Chang, Prem Natarajan, and Nanyun Peng. 2021. Societal biases in language generation: Progress and challenges. In 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), pages 4275–4293, Online. Association for Computational Linguistics. find
  54. Raul Puri and Bryan Catanzaro. 2019. Zero-shot text classification with generative language models. arXiv preprint arXiv:1912.10165. ↗
  55. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. ↗
  56. Lianhui Qin, Sean Welleck, Daniel Khashabi, and Yejin Choi. 2022. Cold decoding: Energy-based constrained text generation with langevin dynamics. In Advances in Neural Information Processing Systems, volume 35, pages 9538–9551. Curran Associates, Inc. find
  57. 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. find
  58. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67. find
  59. Leonardo F. R. Ribeiro, Mohit Bansal, and Markus Dreyer. 2023. Generating summaries with controllable readability levels. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11669–11687, Singapore. Association for Computational Linguistics. find
  60. Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https://github.com/kingoflolz/ mesh-transformer-jax. ↗
  61. Boxin Wang, Wei Ping, Chaowei Xiao, Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Bo Li, Anima Anandkumar, and Bryan Catanzaro. 2022. Exploring the limits of domain-adaptive training for detoxifying large-scale language models. In Advances in Neural Information Processing Systems, volume 35, pages 35811–35824. Curran Associates, Inc. find
  62. Yau-Shian Wang and Yingshan Chang. 2022. Toxicity detection with generative prompt-based inference. arXiv preprint arXiv:2205.12390. ↗
  63. Donya Rooein, Amanda Cercas Curry, and Dirk Hovy. 2023. Know your audience: Do llms adapt to different age and education levels? arXiv preprint arXiv:2312.02065. ↗
  64. Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Finetuned language models are zero-shot learners. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. find
  65. Timo Schick and Hinrich Schütze. 2021. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 255–269, Online. Association for Computational Linguistics. ↗
  66. David Wingate, Mohammad Shoeybi, and Taylor Sorensen. 2022. Prompt compression and contrastive conditioning for controllability and toxicity reduction in language models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5621–5634, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  67. Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, and Dan Klein. 2021. Detoxifying language models risks marginalizing minority voices. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2390–2397, Online. Association for Computational Linguistics. find
  68. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. ↗
  69. Kevin Yang and Dan Klein. 2021. FUDGE: Controlled text generation with future discriminators. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3511–3535, Online. Association for Computational Linguistics. the Association for Computational Linguistics: ACL 2023, pages 1022–1040, Toronto, Canada. Association for Computational Linguistics. find
  70. Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2019. Fine-tuning language models from human preferences. arXiv preprint arXiv:1909.08593. A Descriptions used to identify and reduce each toxicity attribute can be found in Table 8. Note that non-toxic descriptions are only used for the evaluation of L 1 . For toxicity reduction, we use 1a from Table 1 as the target prompt. Attribute toxicity Gal Yona, Or Honovich, Itay Laish, and Roee Aharoni. 2023. Surfacing biases in large language models using contrastive input decoding. arXiv preprint arXiv:2305.07378. severe toxicity sexually explicit threat Sina Zarrieß and David Schlangen. 2019. Know what you don’t know: Modeling a pragmatic speaker that refers to objects of unknown categories. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 654–659, Florence, Italy. Association for Computational Linguistics. ↗ our card
  71. Hanqing Zhang and Dawei Song. 2022. DisCup: Discriminator cooperative unlikelihood prompt-tuning for controllable text generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3392–3406, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  72. Hanqing Zhang, Haolin Song, Shaoyu Li, Ming Zhou, and Dawei Song. 2023. A survey of controllable text generation using transformer-based pre-trained language models. ACM Computing Surveys, 56(3):1– 37. find
  73. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with BERT. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenRe-view.net. find
  74. Xu Zhang and Xiaojun Wan. 2023. MIL-decoding: Detoxifying language models at token-level via multiple instance learning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 190–202, Toronto, Canada. Association for Computational Linguistics. find
  75. Chujie Zheng, Pei Ke, Zheng Zhang, and Minlie Huang. 2023. Click: Controllable text generation with sequence likelihood contrastive learning. In Findings of Toxicity Attributes in Perspective API profanity identity attack find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/wang-2024-rsa-control-pragmatics-grounded-lightweight/